Good communication is vital in healthcare both among healthcare professionals and be tween healthcare professionals and their patients And well written documents describing and or explaining the information in structured databases may be easier to comprehend more edifying and even more convincing than the structured data even when presented in tabu lar or graphic form Documents may be automatically generated from structured data using techniques from the eld of natural language generation These techniques are concerned with how (...) the content organisation and language used in a document can be dynamically selected depending on the audience and context They have been used to generate health education ma terials explanations and critiques in decision support systems and medical reports and progress notes.. (shrink)

This article presents an architecture for natural language generation of biomedical argumentation. The goal is to reconstruct the normative arguments that a domain expert would provide, in a manner that is transparent to a lay audience. Transparency means that an argument's structure and functional components are accessible to its audience. Transparency is necessary before an audience can fully comprehend, evaluate or challenge an argument, or re-evaluate it in light of new findings about the case or changes in (...) scientific knowledge. The architecture has been implemented and evaluated in the Genetics Information Expression Assistant, a prototype system for drafting genetic counselling patient letters. Argument generation makes use of abstract argumentation schemes. Derived from the analysis of arguments used in genetic counselling, these mainly causal argument patterns refer to abstract properties of qualitative causal domain models. (shrink)

Algorithms for NLG NLG is typically broken down into stages of discourse planning (to select information and organize it into coherent paragraphs), sentence planning (to choose words and structures to fit information into sentence-sized units), and realization (to determine surface form of output, including word order, morphology and final formatting or intonation). The SPUD system combines the generation steps of sentence planning and surface realization by using a lexicalized grammar to construct the syntax and semantics of a sentence simultaneously.

Syllogism is a type of everyday reasoning. For instance, given that ‘Avicenna wrote the famous book the Canon of Medicine’ and ‘The Canon of Medicine has influenced modern medicine,’ it can be conc...

��We describe a comprehensive framework for text un- derstanding, based on the representation of context. It is designed to serve as a representation of semantics for the full range of in- terpretive and inferential needs of general natural language pro- cessing. Its most distinctive feature is its uniform representation of the various simple and independent linguistic sources that play a role in determining meaning: lexical associations, syntactic re- strictions, case-role expectations, and most importantly, contextual effects. Compositional syntactic structure (...) from a shallow parsing is represented in a neural net-based associative memory, where it then interacts through a Bayesian network with semantic associa- tions and the context or “gist” of the passage carried forward from preceding sentences. Experiments with more than 2000 sentences in different languages are included. (shrink)

Human beings express affinity (Shinwa‐kan in Japanese language) in communicating transactive engagements among healthcare providers, patients and healthcare robots. The appearance of healthcare robots and their language capabilities often feature characteristic and appropriate compassionate dialogical functions in human–robot interactions. Elements of healthcare robot configurations comprising its physiognomy and communication properties are founded on the positivist philosophical perspective of being the summation of composite parts, thereby mimicking human persons. This article reviews Mori's theory of the Uncanny Valley and its (...) consequent debates, and examines "Uncanny" relations with generating healthcare robot conversational content with artificial affective communication (AAC) using natural language processing. With healthcare robots provoking influential physical composition and sensory expressions, the relations in human–healthcare robot transactive engagements are argued as supportive of the design and development in natural language processing. This implies that maintaining human–healthcare robot interaction and assessing the eeriness situations explained in the Uncanny Valley theory are crucial positions for healthcare robot functioning as a valuable commodity in health care. As such, physical features, language capabilities and mobility of healthcare robots establish the primacy of the AAC with natural language processing as integral to healthcare robot–human healthcare practice. (shrink)

We describe a comprehensive framework for text un- derstanding, based on the representation of context. It is designed..

Notice that this paper has not claimed that all natural languages are CFL's. What it has shown is that every published argument purporting to demonstrate the non-context-freeness of some natural language is invalid, either formally or empirically or both.18 Whether non-context-free characteristics can be found in the stringset of some natural language remains an open question, just as it was a quarter century ago.Whether the question is ultimately answered in the negative or the affirmative, there (...) will be interesting further questions to ask. If it turns out that natural languages are indeed always CFL's, it will be reasonable to ask whether this helps to explain why speakers apparently recognize so quickly whether a presented utterance corresponds to a grammatical sentence or not, and to associate structural and semantic details with it. It might also be reasonable to speculate about the explanation for the universally context-free character of the languages used by humans, and to wonder whether evolutionary biological factors are implicated in some way (Sampson (1979) could be read in this light). And naturally, it will be reasonable to pursue the program put forward by Gazdar (1981, in press) to see to what extent CFL-inducing grammatical devices can be exploited to yield insightful descriptions of natural languages that capture generalizations in revealing ways.If a human language that is not a CFL is proved to exist, on the other hand, a different question will be raised: give the non-context-free character of human languages in general, why has this property been so hard to demonstrate that it has taken over twenty-five years to bring it to light since the issue was first explicitly posed? If human languages do not have to be CFL's, why do so many (most?) of them come so close to having the property of context-freeness? And, since the CFL's certainly constitute a very broad class of mathematically natural and computationally tractable languages, what property of human beings or their communicative or cognitive needs is it that has caused some linguistic communities to reach beyond the boundaries of this class in the course of evolving a linguistic system?Either way, we shall be interested to see our initial question resolved, and further questions raised. One cautionary word should be said, however, about the implications (or lack of them) that the answer will have for grammatical studies. Chomsky has repeatedly stated that he does not see weak generative capacity as a theme of central importance in the theory of grammar, and we agree. It is very far from being the case that the recent resurgence of interest in exploring the potential of CF-PSG or equivalent systems will, or should, be halted dead in its tracks by the discovery (if it is ever forthcoming) that some natural language is not a CFL. In the area of parsing, for instance, it seems possible that natural languages are not only parsed on the basis of constituent structure such as a CF-PSG would assign, but are parsed as if they were finite state languages (see Langendoen (1975) and Church (1980) for discussion along these lines). That is, precisely those construction-types that figure in the various proofs that English is not an FSL appear to cause massive difficulty in the human processing system; the sentences crucial to the proofs are for the most part unprocessable unless they are extremely short (yet the arguments for English not being and FSL only go through if length is not an issue). This means that in practice properties of finite state grammars are still of great potential importance to linguistic theory despite the fact that they do not provide the framework for defining the total class of grammatical sentences. The same would almost certannly be true of CF-PSG's if they were shown to be inadequate in a similar sense. It is highly unlikely that the advances made so far in far in phrase structure description could be nullified by a discovery about weak generative capacity. Moreover, there are known to be numerous ways in which the power of CF-PSG's can be marginally enhanced to permit, for example, xx languages to be generated without allowing anything like the full class of recursively enumerable or even context-sensitive languages (see Hopcroft and Ullmann (1979), Chapter 14) for an introduction to this topic, noting especially Figure 14.7 on p. 393. The obvious thing to do if natural languages were ever shown not to be CFL's in the general case would be to start exploring such minimal enhancements of expressive power to determine exactly what natural languages call for in this regard and how it could be effectively but parsimoniously provided in a way that closely modelled human linguistic capacities.In the meantime, it seems reasonable to assume that the natural languages are a proper subset of the infinite-cardinality CFL's until such time as they are validly shown not to be. (shrink)

Natural language syntax yields an unbounded array of hierarchically structured expressions. We claim that these are used in the service of active inference in accord with the free-energy principle (FEP). While conceptual advances alongside modelling and simulation work have attempted to connect speech segmentation and linguistic communication with the FEP, we extend this program to the underlying computations responsible for generating syntactic objects. We argue that recently proposed principles of economy in language design—such as “minimal search” criteria (...) from theoretical syntax—adhere to the FEP. This affords a greater degree of explanatory power to the FEP—with respect to higher language functions—and offers linguistics a grounding in first principles with respect to computability. While we mostly focus on building new principled conceptual relations between syntax and the FEP, we also show through a sample of preliminary examples how both tree-geometric depth and a Kolmogorov complexity estimate (recruiting a Lempel–Ziv compression algorithm) can be used to accurately predict legal operations on syntactic workspaces, directly in line with formulations of variational free energy minimization. This is used to motivate a general principle of language design that we term Turing–Chomsky Compression (TCC). We use TCC to align concerns of linguists with the normative account of self-organization furnished by the FEP, by marshalling evidence from theoretical linguistics and psycholinguistics to ground core principles of efficient syntactic computation within active inference. (shrink)

This paper asks why information should ever be expressed vaguely, re-assessing some previously proposed answers to this question and suggesting some new ones. Particular attention is paid to the benefits that vague expressions can have in situations where agreement over the meaning of an expression cannot be taken for granted. A distinction between two different versions of the above-mentioned question is advocated. The first asks why human languages contain vague expressions, the second question asks when and why a speaker should (...) choose a vague expression when communicating with a hearer. While the former question is purely theoretical, the latter has practical implications for the computational generation of utterances in Natural Language Generation (NLG). (shrink)

This paper asks why information should ever be expressed vaguely, re-assessing some previously proposed answers to this question and suggesting some new ones. Particular attention is paid to the benefits that vague expressions can have in situations where agreement over the meaning of an expression cannot be taken for granted. A distinction between two different versions of the above-mentioned question is advocated. The first asks why human languages contain vague expressions, the second question asks when and why a speaker should (...) choose a vague expression when communicating with a hearer. While the former question is purely theoretical, the latter has practical implications for the computational generation of utterances in Natural Language Generation (NLG). (shrink)

Recent work in natural language semantics leads to some new observations on generalized quantifiers. In § 1 we show that English quantifiers of type $ $ are booleanly generated by their generalized universal and generalized existential members. These two classes also constitute the sortally reducible members of this type. Section 2 presents our main result--the Generalized Prefix Theorem (GPT). This theorem characterizes the conditions under which formulas of the form Q1x 1⋯ Qnx nRx 1⋯ xn and q1x 1⋯ (...) qnx nRx 1⋯ xn are logically equivalent for arbitrary generalized quantifiers Qi, qi. GPT generalizes, perhaps in an unexpectedly strong form, the Linear Prefix Theorem (appropriately modified) of Keisler & Walkoe (1973). (shrink)

This paper presents two projects concerned with the application of natural language processing technology for improving communication between Public Administration and citizens. The first project, GIST,is concerned with automatic multilingual generation of instructional texts for form-filling. The second project, TAMIC, aims at providing an interface for interactive access to information, centered on natural language processing and supposed to be used by the clerk but with the active participation of the citizen.

This informal position paper brings together some recent developments in formal semantics and pragmatics to argue that the discipline of Game Theory is well placed to become the theoretical backbone of Natural Language Generation. To demonstrate some of the strengths and weaknesses of the Game-Theoretical approach, we focus on the utility of vague expressions. More specifically, we ask what light Game Theory can shed on the question when an NLG system should generate vague language.

Automated software engineering has attracted a large amount of research efforts. The use of object-oriented methods for software systems development has made it necessary to develop approaches that automate the construction of different Unified Modeling Language models in a semiautomated approach from textual user requirements. UML use case models represent an essential artifact that provides a perspective of the system under analysis or development. The development of such use case models is very crucial in an object-oriented development method. The (...) main principles used in obtaining these models are described. A natural language processing tool is used to parse different statements of the user requirements written in Arabic to obtain lists of nouns, noun phrases, verbs, verb phrases, etc., that aid in finding potential actors and use cases. A set of steps that represent our approach for constructing a use case model are presented. Finally, the proposed approach is validated using an experiment involving a group of graduate students who are familiar with use case modeling. (shrink)

If the begriffsschrift from Frege does represent the logical form of natural language it either lacks a logical form itself, or its logical form is different to that of natural language. But Frege insists that his notation has a logical form. So the second disjunct holds. This suggests that Frege's notation will generate consequences different to those that can be derived with natural language, with its different logical form. For anyone looking for "a means (...) of avoiding misunderstandings", as Frege does, this would be unpalatable, to say the least. (shrink)

This article engages the anthropological assumptions underlying the apprehensions and promises associated with language in artificial intelligence (AI). First, we present the contours of two rivalling paradigms for assessing artificial language generation: a holistic-enactivist theory of language and an informational theory of language. We then introduce two language generation models – one presently in use and one more speculative: Firstly, the transformer architecture as used in current large language models, such as the (...) GPT-series, and secondly, a model for 'autonomous machine intelligence' recently proposed by Yann LeCun, which involves not only language but a sensory-motor interaction with the world. We then assess the language capacity of these models from the perspectives of the two rivalling language paradigms. Taking a holistic-enactivist stance, we then argue that there is currently no reason to assume a human-comparable language capacity in LLMs and, further, that LeCun's proposed model does not represent a significant step toward artificially generating human language because it still lacks essential features that underlie the linguistic capacity of humans. Finally, we suggest that proponents of these rivalling interpretations of LLMs should enter into a constructive dialogue and that this dialogue should continuously involve further empirical, conceptual, and theoretical research. (shrink)

In a Star Trek: The Next Generation episode, Cpt. Picard is captured and trapped on a planet with an alien captain who speaks a language incompatible with the universal translator, based on their societal historical metaphors. According to Shapiro (2004), the concept of a universal translator removes everything alien from alien languages, and since the Tamarian language refers only to their historical and cultural archetypes, Picard can only establish dialogue by invoking human analogues, such as Gilgamesh. The (...) purpose of this paper is threefold. First, we will tie such communication to standard cognitive models in cognitive linguistics, pioneered by Lakoff and Johnson (1980) and Lakoff (1987). Second, we will show that metaphorical imaging resembling the Tamarian language is already present in our culture, by analyzing Dawkins's (1982) notion of a meme, who presupposes that memes as cultural living structures physically reside in the brain, and comparing that to a common format of a meme in pop culture. We will also contrast this concept with living natural languages such as Wolaytta, using a great number of proverbs, which can be seen as desemanticized metaphors that are used to embody different domains of the social realm of life (Make et al. 2014). Third, we will compare the notion of such a language with the current state of machine-learning and deep-learning techniques for natural language processing of metaphorical phrases, pinpointing that even deep learning today is powerless without sufficient training datasets (cf. Perifanos et al. 2020) or specific known word contexts and embeddings (Rei et al. 2017), compared to the same situation the universal translator was faced with when dealing with the Tamarian language. (shrink)

Algorithmic biases, or algorithmic unfairness, have been a topic of public and scientific scrutiny for the past years, as increasing evidence suggests the pervasive assimilation of human cognitive biases and stereotypes in such systems. This research is specifically concerned with analyzing the presence of discursive biases in the text generated by GPT-3, an NLPM which has been praised in recent years for resembling human language so closely that it is becoming difficult to differentiate between the human and the algorithm. (...) The pertinence of this research object is substantiated by the identification of race, gender and religious biases in the model’s completions in recent research, suggesting that the model is indeed heavily influenced by human cognitive biases. To this end, this research inquires: How does the Natural Language Processing Model GPT-3 replicate existing social biases?. This question is addressed through the scrutiny of GPT-3’s completions using Critical Discourse Analysis (CDA), a method which has been deemed as amply valuable for this research as it is aimed at uncovering power asymmetries in language. As such, the analysis is specifically centered around the analysis of gender and race biases in the model’s generated text. Research findings suggest that GPT-3’s language generation model significantly exacerbates existing social biases while replicating dangerous ideologies akin to white supremacy and hegemonic masculinity as factual knowledge. (shrink)

A certain orthodoxy has it that understanding is essentially computational: that information about what a sentence means is something that may be generated by means of a derivational process from information about the significance of the sentences constituent parts and of the ways in which they are put together. And that it is therefore fruitful to study formal theories acceptable as compositional theories of meaning for natural languages: theories that deliver for each sentence of their object-language a theorem (...) acceptable as statement of its meaning and derivable from axioms characterizing subsentential expressions and operations forming that sentence. This paper is to show that there is something deeply wrong with these ideas, namely that they are based on a certain confusion about ascriptions of semantic knowledge. The paper is to make this point by considering a semantic theorist who has explicit knowledge of a theory of truth for L. And by showing that all the theorist needs to have knowledge of to understand the sentences of L are these axioms -- that the derivation of T-theorems is epistemically redundant. And that this doesnt change when we turn from explicit to what has been called tacit knowledge. (shrink)

J. L. Austin, in "Ifs and Cans," proclaimed the common hope that we soon "may see the birth, through the joint labors of philosophers, grammarians, and numerous other students of language, of a true and comprehensive science of language." The problem has always been with the "joint labors" part. Philosophers have always been willing to issue linguists dictums and linguists have been happy to teach philosophers "plain facts." Austin’s general view of language, and his particular notion of (...) performative utterance, can be found in the writing of J. R. Firth, the most commanding British linguist of Austin’s generation, but Austin never refers to Firth. In the present volume, however, we find clear and exciting evidence of genuinely joint labors on the part of philosophers and linguists. They stem from a summer conference in 1969 rounded out with contributions from notables. To two thick issues of Synthese the editors have added a dazzling piece by Saul Kripke, two substantial pieces by James McCawley and J. R. Ross, a short paper by Paul Ziff, and a reprint of P. F. Strawson’s "Grammar and Philosophy." This is an invaluable book and the best book among the many now available concerning the interaction of linguistics and philosophy: worth the cost, which the contributors attempted to reduce through foregoing royalties. The philosophers in this volume hold, or hold intriguing, the view that the semantics of a natural language can and must, in effect, be a theory of truth for a language in much the manner that Tarski suggested, and provided, for artificial language: the recursive specification of biconditionals in which the left hand gives the structural description of an object language sentence and the right hand, the truth conditions in the metalanguage. In "homophonic" translation this requirement can be trivially satisfied simply by mentioning the sentence on the left that one uses on the right: one makes the requirement non-trivial by forcing enough into the recursive specification so that one captures the native speaker’s implicit semantic competence. In this volume, the "orthodox" Davidsonian program, which takes the syntax of the metalanguage to be standard predicate logic, is ably argued by John Wallace ; Richard Montague, David Lewis, and Jaakko Hintikka would want an intensional logic covering modality and propositional attitudes. The linguists who find this philosophical climate most appealing are called "generative semanticists": McCawley, Ross, George Lakoff and others argue that any proposed semantic rule will eventually prove necessary to syntax too and that, hence, the deepest level of syntactical form will be equivalent to semantic form. Whatever the ultimate fate of this joint program, it leads here to much exciting interaction between linguists and philosophers: linguists who welcome the machinery and conceptual standards of modern logic, and philosophers who try to grasp the specifics of crucial issues in recent linguistic theory. Even if Quine’s doubts, here sketched, and Chomsky’s currently unpublished more technical objections should be well-founded, nonetheless the joint labor will have been very much worthwhile. Aside from this general debate about semantics, there are several papers covering more specific issues. The papers of J. A. Fodor, Terence Parsons, and Ross concern adverbs and the logical form of action sentences; several papers, particularly B. H. Partee’s, examine "Opacity, Coreference, and Pronouns." In all these papers one notes the fulfillment of Austin’s hope that philosophic and linguistic arguments should become intermixed, if not at times properly indistinguishable. Perhaps the most enjoyable and exciting paper stands aside from linguistics: Saul Kripke’s "Naming and Necessity." Kripke here argues quite informally for the separation of analytic, a priori, and necessary that is required for a Kripke style, S5, modal logic with de re modalities. "Gold is a yellow metal," for example, turns out to be contingent, while "Heat is the motion of particles" is necessary but a posteriori ; and that philosopher’s stone of stones, "The morning star is the evening star," is discovered to be necessary but a posteriori.—J. L. (shrink)

In natural language understanding, a crucial goal is correctly interpreting open-textured phrases. In practice, disagreements over the meanings of open-textured phrases are often resolved through the generation and evaluation of interpretive arguments, arguments designed to support or attack a specific interpretation of an expression within a document. In this paper, we discuss some of our work towards the goal of automatically generating and evaluating interpretive arguments. We have curated a set of rules from the code of ethics (...) of various professional organizations and a set of associated scenarios that are ambiguous with respect to some open-textured phrase within the rule. We collected and evaluated arguments from both human annotators and state-of-the-art generative language models in order to determine the relative quality and persuasiveness of both sets of arguments. Finally, we performed a Turing test-inspired study in order to assess whether human annotators can tell the difference between human arguments and machine-generated arguments. The results show that machine-generated arguments, when prompted a certain way, can be consistently rated as more convincing than human-generated arguments, and to the untrained eye, the machine-generated arguments can convincingly sound human-like. (shrink)

A substantial amount of recent work in natural language generation has focused on the generation of ‘‘one-shot’’ referring expressions whose only aim is to identify a target referent. Dale and Reiter's Incremental Algorithm (IA) is often thought to be the best algorithm for maximizing the similarity to referring expressions produced by people. We test this hypothesis by eliciting referring expressions from human subjects and computing the similarity between the expressions elicited and the ones generated by algorithms. (...) It turns out that the success of the IA depends substantially on the ‘‘preference order’’ (PO) employed by the IA, particularly in complex domains. While some POs cause the IA to produce referring expressions that are very similar to expressions produced by human subjects, others cause the IA to perform worse than its main competitors; moreover, it turns out to be difficult to predict the success of a PO on the basis of existing psycholinguistic findings or frequencies in corpora. We also examine the computational complexity of the algorithms in question and argue that there are no compelling reasons for preferring the IA over some of its main competitors on these grounds. We conclude that future research on the generation of referring expressions should explore alternatives to the IA, focusing on algorithms, inspired by the Greedy Algorithm, which do not work with a fixed PO. (shrink)

A large part of philosophical analysis deals with the problem of how language relates to reality. It is assumed that language speaks—or at least may speak—about something, about one or another kind of reality. It speaks truthfully or falsely, with cohesion or with confusion, with precision or loosely, penetratingly or without much depth, assertively, hypothetically, optatively, interrogatively or in some other way, about the real or supposed world. The so-called “real world” is perhaps amorphous, in flux, continuous and (...) indivisible. Language, on the other hand, is usually viewed as well organized, strict, discrete, and decomposable into its generators. But it is an old, Platonic view that the structure of language reflects the structure of the world. (shrink)

A key requirement for the automatic generation of argumentative or explanatory text is to present the constituent propositions in an order that readers will find coherent and natural, to increase the likelihood that they will understand and accept the author’s claims. Natural language generation systems have standardly employed a repertoire of coherence relations such as those defined by Mann and Thompson’s Rhetorical Structure Theory. This paper models the generation of persuasive monologue as the outcome (...) of an “inner dialogue”, where the author attempts to anticipate potential challenges or clarification requests. It is argued that certain RST relations such as Motivate, Evidence and Concession can be seen to emerge from various pre-empting strategies. (shrink)

A substantial amount of recent work in natural language generation has focused on the generation of ‘‘one‐shot’’ referring expressions whose only aim is to identify a target referent. Dale and Reiter's Incremental Algorithm (IA) is often thought to be the best algorithm for maximizing the similarity to referring expressions produced by people. We test this hypothesis by eliciting referring expressions from human subjects and computing the similarity between the expressions elicited and the ones generated by algorithms. (...) It turns out that the success of the IA depends substantially on the ‘‘preference order’’ (PO) employed by the IA, particularly in complex domains. While some POs cause the IA to produce referring expressions that are very similar to expressions produced by human subjects, others cause the IA to perform worse than its main competitors; moreover, it turns out to be difficult to predict the success of a PO on the basis of existing psycholinguistic findings or frequencies in corpora. We also examine the computational complexity of the algorithms in question and argue that there are no compelling reasons for preferring the IA over some of its main competitors on these grounds. We conclude that future research on the generation of referring expressions should explore alternatives to the IA, focusing on algorithms, inspired by the Greedy Algorithm, which do not work with a fixed PO. (shrink)

A fundamental part of the process of referring to an entity is to categorise it (for instance, as the woman). Where multiple categorisations exist, this implicitly involves the adoption of a conceptual perspective. A challenge for the automatic Generation of Referring Expressions is to identify a set of referents coherently, adopting the same conceptual perspective. We describe and evaluate an algorithm to achieve this. The design of the algorithm is motivated by the results of psycholinguistic experiments.

This article explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. We focus on the ambiguities that arise when adjectives occur in coordinated structures. The central idea is to use statistical information about lexical co-occurrence to estimate which interpretation of a phrase is most likely for human readers, and to avoid (...) generating phrases where misunderstandings are likely. Various aspects of the problem were explored in three experiments in which responses by human participants provided evidence about which reading was most likely for certain phrases, which phrases were deemed most suitable for particular referents, and the speed at which various phrases were read. We found a preference for ‘‘clear’’ expressions to ‘‘unclear’’ ones, but if several of the expressions are ‘‘clear,’’ then brief expressions are preferred over non-brief ones even though the brief ones are syntactically ambiguous and the non-brief ones are not; the notion of clarity was made precise using Kilgarriff's Word Sketches. We outline an implemented algorithm that generates noun phrases conforming to our hypotheses. (shrink)

We examine the problem of generating definite noun phrases that are appropriate referring expressions; that is, noun phrases that (a) successfully identify the intended referent to the hearer whilst (b) not conveying to him or her any false conversational implicatures (Grice, 1975). We review several possible computational interpretations of the conversational implicature maxims, with different computational costs, and argue that the simplest may be the best, because it seems to be closest to what human speakers do. We describe our recommended (...) algorithm in detail, along with a specification of the resources a host system must provide in order to make use of the algorithm, and an implementation used in the natural language generation component of the IDAS system. (shrink)

(Near-final version.) Accepted for publication in Artificial Intelligence Journal.

Some of the systems used in natural language generation (NLG), a branch of applied computational linguistics, have the capacity to create or assemble somewhat original messages adapted to new contexts. In this paper, taking Bernard Williams’ account of assertion by machines as a starting point, I argue that NLG systems meet the criteria for being speech actants to a substantial degree. They are capable of authoring original messages, and can even simulate illocutionary force and speaker meaning. Background (...) intelligence embedded in their datasets enhances these speech capacities. Although there is an open question about who is ultimately responsible for their speech, if anybody, we can settle this question by using the notion of proxy speech, in which responsibility for artificial speech acts is assigned legally or conventionally to an entity separate from the speech actant. (shrink)

To what degree can language be acquired from linguistic input alone? This question has vexed scholars for millennia and is still a major focus of debate in the cognitive science of language. The complexity of human language has hampered progress because studies of language–especially those involving computational modeling–have only been able to deal with small fragments of our linguistic skills. We suggest that the most recent generation of Large Language Models (LLMs) might finally provide (...) the computational tools to determine empirically how much of the human language ability can be acquired from linguistic experience. LLMs are sophisticated deep learning architectures trained on vast amounts of natural language data, enabling them to perform an impressive range of linguistic tasks. We argue that, despite their clear semantic and pragmatic limitations, LLMs have already demonstrated that human-like grammatical language can be acquired without the need for a built-in grammar. Thus, while there is still much to learn about how humans acquire and use language, LLMs provide full-fledged computational models for cognitive scientists to empirically evaluate just how far statistical learning might take us in explaining the full complexity of human language. (shrink)

Natural language processing based on large language models (LLMs) is a booming field of AI research. After neural networks have proven to outperform humans in games and practical domains based on pattern recognition, we might stand now at a road junction where artificial entities might eventually enter the realm of human communication. However, this comes with serious risks. Due to the inherent limitations regarding the reliability of neural networks, overreliance on LLMs can have disruptive consequences. Since it (...) will be increasingly difficult to distinguish between human-written and machine-generated text, one is confronted with new ethical challenges. This begins with the no longer undoubtedly verifiable human authorship and continues with various types of fraud, such as a new form of plagiarism. This also concerns the violation of privacy rights, the possibility of circulating counterfeits of humans, and, last but not least, it makes a massive spread of misinformation possible. (shrink)

In this article, the results of conceptualization of the definition of mind as an object of interdisciplinary applied research are described. The purpose of the theoretical analysis is to generate a methodological discourse suitable for a functional understanding of the mind in the context of the problem of natural language processing as one of the components of developments in the field of artificial intelligence. The conceptual discourse was realized with the help of the author's method of structural-ontological analysis, (...) and developed in the mainstream of the system-methodological tradition of the school of G.P. Shchedrovitsky and intended for descriptive research of subject areas of interdisciplinary objects of scientific study. As a result of the structural and ontological analysis of the super-system, the relevant place and role of the directly studied system (mind) are determined, and its primary process and material are localized and structural and functional connections are described. At the basic level, the mind is conceptualized as an energy process unfolding in a spatio-temporal environment and accompanied by archetypal structuring of neural impulses into images. The genesis of the system is separately analyzed by constructing a structural-ontological matrix that reflects the initial stage of the development of the mind. The primary process is concretized with the help of hetero- and homeostatic dichotomy, and also the most significant features of the consistent transformation of the material of the system and its ascent to verbal morphology are described. The structural-ontological comparison of the functioning of the verbal intelligence with the preverbal level has been carried out. The transformation of neural impulses of needs into words, as verbal units fixing semiotic values is analyzed. Structural-ontological connections that determine the reactive and prospective characteristics of the functioning of the system are disclosed. The position of the chronological primacy of "semiotic readiness" for language with respect to the debut of the latter as an information-sign model of the environment is argued. The hypothesis of domination at the initial stage of the development of the mind of exopsychic functions over endopsychic ones is formulated. The theoretical substantiation of the hypothesis of the inevitability of the ontology of language in the functional understanding of the mind is given, corresponding structural and ontological arguments are given, including those based on the ideas about the information relationship between affects and needs, according to the views of P.V. Simonov. The arguments are presented in favor of the non-alternative methodology of A. Turing in studies of artificial intelligence. (shrink)

Philosophers disagree, with some rare exceptions. One of those exceptions is the broadest-brush account of what language is. Language is a system of signs used for the communication of --well, and here the agreement begins to break down--thoughts, ideas, messages, propositions or propositional contents, intentions, and a host of technical terms offer themselves to chink the cracks. A list of philosophers subscribing would be impossible to complete. Locke, Carnap, Augustine, Hobbes, Fodor, Katz, Chomsky, Derrida, --well, and on and (...) on. Easier would be to list those who dissent. Heraclitus, Wittgenstein, maybe J.L. Austin, Frank Ebersole, and NOT on and on. The first chapter lays out the view that language is a system of signs in sympathetic terms. The second provides a selection of what are usually called “ordinary language” arguments against the view--reminders about how the view requires us to think in terms which are not consistent with how we think about language and signs when we are not doing philosophy. Those arguments have been unpersuasive among philosophers, and Chapter Three begins the work of investigating separate pieces of the view in detail. Chapter Three takes up an argument for the view which is familiar among philosophers, using Jerry Fodor’s formulation: we cannot be thinking in a public, natural language, because animals and preverbal infants think with no such language. I show this argument is not an argument at all but is rather an expression of the view in question. Chapter Four takes up the argument that the relations between particular words and their meanings is arbitrary or conventional rather than natural or necessary, otherwise there would be only one language among mankind. I argue that the alternatives (conventional vs. natural or necessary) are both generated by taking the division between words and their meanings to be the division between signs and signified--in other words, the question is a result of adopting the view of language as signs. Attempts to argue for the legitimacy of the question without taking the view for granted only serve to call it into question more. In Chapter Five I investigate whether we talk in order to communicate something which is otherwise hidden and invisible. We are tempted to think that you and I talk because I cannot read your mind or you mine. Though Wittgenstein has a famous set of comments on the notion of a private language, it remains a strong temptation to think that language gives public form to something (thoughts, ideas, intentions, feelings, content, meaning) which without language would be unknowable to all but the person whose something it is. Examples help point to the incoherence of this view and show that even if it were not incoherent, remedying the invisibility of those internal whatnots would still leave us with a need for language. Chapter Six takes up a hoary question about boundaries of effability--the possibility that there are limits to what can be said which are more restrictive than what can be thought or felt. The account of language as signs provides one easy way to make sense of this idea, but investigation into examples shows the problem is not one that makes sense unless we just grant that account. Chapter Seven investigates how to make sense of the notion that there are things which are in language and other things which are not. I spell out how the view of language as signs gives us a way to think this, and then show how one reaction to finding problems with the notion resonates with Wittgenstein’s early work and with some work of Jacques Derrida, who bite similar bullets and agree that everything is language, that the limits of language are the limits of our world. I then subject that reaction to critical investigation using examples, which reveals their reaction as a rear-guard attempt to save the view of language as signs. Chapter Eight uses examples as guides toward alternative views of language, feeling our way toward what language might be if it is not a system of signs. Finally, the appendix takes up what I take to be the serious arguments against the methods I use in this work, the first two articulated by John Searle (“the assertion fallacy”) and H. P. Grice (“conversational implicature”), and another the generally unspoken belief that philosophical work is like scientific work. (shrink)

One of the constants in Noam Chomsky’s philosophical, linguistic and ethical positions is the existence of what he calls “human nature”. Following Marx, Darwin and last century’s revolutions in the social sciences, human nature has been one of the most contested conceptual holdovers from modern European philosophy. Chomsky’s discoveries and models on syntax and language make up one of the frameworks to most critically offset the traditional moral dimension of human nature. Contrary to most traditions prior to his work, (...) language can no longer be restricted to either mind, soul or spirit. Language, as Chomsky has continually upheld and sharply refined, is a physical and biological process. But how his notion of human nature derives from this process is complex, as he seems to disregard philosophy’s classic analytic delineation between the descriptive causal realm of human nature and the normative axiological extensions of the same concept. In this paper, we seek to examine the philosophical and ontological implications of Chomsky’s claim that human nature derives from the innate dimension of the language faculty. Not only does Chomsky maintain the category of human nature, he also indexes it to the question of freedom. We thereby argue for the coherence of his proposal and show how it operates to weld the perspective of a modal theory of biologically-rooted creativity to innate conditions specific to his theory of language generation. However, we question whether its restriction to humans alone is sustainable from a scientific perspective by putting forth the claim that Chomsky’s science is in fact a radical ontology of social subjectivation. (shrink)

The concept of argumentation in AI is based almost exclusively on the use of formal, abstract representations. Despite their appealing computational properties, these abstractions become increasingly divorced from their real world counterparts, and, crucially, lose the ability to express the rich gamut of natural argument forms required for creating effective text. In this paper, the demands that socially situated argumentation places on knowledge representation are explored, and the various problems with existing formalisations are discussed. Insights from argumentation theory and (...) social psychology are then adduced as key contributions to a notion of social context which is both computationally tractable and suitably expressive for handling the complexities of argumentation found in natural language. (shrink)

This article explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. We focus on the ambiguities that arise when adjectives occur in coordinated structures. The central idea is to use statistical information about lexical co‐occurrence to estimate which interpretation of a phrase is most likely for human readers, and to avoid (...) generating phrases where misunderstandings are likely. Various aspects of the problem were explored in three experiments in which responses by human participants provided evidence about which reading was most likely for certain phrases, which phrases were deemed most suitable for particular referents, and the speed at which various phrases were read. We found a preference for ‘‘clear’’ expressions to ‘‘unclear’’ ones, but if several of the expressions are ‘‘clear,’’ then brief expressions are preferred over non‐brief ones even though the brief ones are syntactically ambiguous and the non‐brief ones are not; the notion of clarity was made precise using Kilgarriff's Word Sketches. We outline an implemented algorithm that generates noun phrases conforming to our hypotheses. (shrink)

In previous work we have developed Property Theory with Curry Typing (PTCT), an intensional first-order logic for natural language semantics. PTCT permits fine-grained specifications of meaning. It also supports polymorphic types and separation types. We develop an intensional number theory within PTCT in order to represent proportional generalized quantifiers like "most", and we suggest a dynamic type-theoretic approach to anaphora and ellipsis resolution. Here we extend the type system to include product types, and use these to define a (...) permutation function that generates underspecified scope representations within PTCT. We indicate how filters can be added to encode constraints on possible scope readings. Our account offers several important advantages over other current theories of underspecification. (shrink)

Holistic theories of meaning have, at least since Dummett’s Frege: The Philosophy of language, been assumed to be problematic from the perspective of the incremental nature of natural language learning. In this essay I argue that the general relationship between holism and language learning is in fact the opposite of that claimed by Dummett. It is only given a particular form of language learning, and a particular form of holism, that there is a problem at (...) all; in general, for all forms of holism, and irrespective of how language learning is understood, semantic holism is conducive to language learning. The paper has three main parts. In the first, I demonstrate with the use of a simple formal system, that the form of holism that generates the problem that Dummett draws attention to is really decomposable into three distinct components, each of which is necessary for the problem to arise. In the second part, I demonstrate that even Dummett’s strong form of holism is compatible with one natural way in which to understand the incremental nature of language learning. In the third part, I outline the reasons why all forms of holism are conducive to language learning and offer two ways in which this general fact can be spelled out precisely. I end the paper by addressing some possible objections, and in doing so I draw attention to some affinities between semantic holism and the principle of compositionality, a semantic principle which has long been assumed to be conducive to language learning. (shrink)

Rapid handwriting, popularly known as shorthand, involves writing symbols and abbreviations in lieu of common words or phrases. This method increases the speed of transcription and is primarily used to record oral dictation. Someone skilled in shorthand will be able to write as fast as the dictation occurs, and these patterns are later transliterated into actual, natural language words. A new kind of rapid handwriting scheme is proposed, called the Pattern-Based Shorthand. A word on a keyboard involves pressing (...) a unique sequence of keys in a particular order. This sequence forms a pattern that defines the word. Such a pattern forms the shorthand for that word. Speech recognition involves identifying, by a machine, the words spoken by a speaker. These spoken words form speech input signals to a computer that is equipped to correctly recognize the words and do further action, such as convert it to text. From this text input, unique shorthand patterns are generated by the system. The system employs machine learning to improve its performance with experience, by creating a dictionary of mappings from word to patterns in such a way that the access to existing patterns is faster with progression. This forms a new knowledge representation schema that reduces the redundancy in the storage of words and the length of information content. In conclusion, the speech is converted into textual form and then reconstructed into Pattern-Based Shorthand. (shrink)

We introduce a set of biologically and computationally motivated design choices for modeling the learning of language, or of other types of sequential, hierarchically structured experience and behavior, and describe an implemented system that conforms to these choices and is capable of unsupervised learning from raw natural-language corpora. Given a stream of linguistic input, our model incrementally learns a grammar that captures its statistical patterns, which can then be used to parse or generate new data. The grammar (...) constructed in this manner takes the form of a directed weighted graph, whose nodes are recursively (hierarchically) defined patterns over the elements of the input stream. We evaluated the model in seventeen experiments, grouped into five studies, which examined, respectively, (a) the generative ability of grammar learned from a corpus of natural language, (b) the characteristics of the learned representation, (c) sequence segmentation and chunking, (d) artificial grammar learning, and (e) certain types of structure dependence. The model's performance largely vindicates our design choices, suggesting that progress in modeling language acquisition can be made on a broad front—ranging from issues of generativity to the replication of human experimental findings—by bringing biological and computational considerations, as well as lessons from prior efforts, to bear on the modeling approach. (shrink)

This informal position paper brings together some recent developments in formal semantics and pragmatics to argue that the discipline of Game Theory is well placed to become the theoretical backbone of Natural Language Generation. To demonstrate some of the strengths and weaknesses of the Game-Theoretical approach, we focus on the utility of vague expressions. More specifically, we ask what light Game Theory can shed on the question when an NLG system should generate vague language.

Large language models (LLMs) have now entered the realm of medical ethics. In a recent study, Balaset alexamined the performance of GPT-4, a commercially available LLM, assessing its performance in generating responses to diverse medical ethics cases. Their findings reveal that GPT-4 demonstrates an ability to identify and articulate complex medical ethical issues, although its proficiency in encoding the depth of real-world ethical dilemmas remains an avenue for improvement. Investigating the integration of LLMs into medical ethics decision-making appears to (...) be an interesting avenue of research. However, despite the promising trajectory of LLM technology in medicine, it is crucial to exercise caution and refrain from attributing their expertise to medical ethics. Our thesis follows an examination of the nature of expertise and the epistemic limitations that affect LLM technology. As a result, we propose two more fitting applications of LLMs in medical ethics: first, as tools for mining electronic health records or scientific literature, thereby supplementing evidence for resolving medical ethics cases, and second, as educational platforms to foster ethical reflection and critical thinking skills among students and residents. The integration of LLMs in medical ethics, while promising, requires careful consideration of their epistemic limitations. Consequently, a well-considered definition of their role in ethically sensitive decision-making is crucial. (shrink)