From a leading authority in artificial intelligence, this book delivers a synthesis of the major modern techniques and the most current research in natural language processing. The approach is unique in its coverage of semantic interpretation and discourse alongside the foundational material in syntactic processing.

This article contains the results of a theoretical analysis of the phenomenon of natural language understanding (NLU), as a methodological problem. The combination of structural-ontological and informational-psychological approaches provided an opportunity to describe the subject matter field of NLU, as a composite function of the mind, which systemically combines the verbal and discursive structural layers. In particular, the idea of NLU is presented, on the one hand, as the relation between the discourse of a specific speech message and (...) the meta-discourse of a language, in turn, activated by the need-motivational factors. On the other hand, it is conceptualized as a process with a specific structure of information metabolism, the study of which implies the necessity to differentiate the affective (emotional) and need-motivational influences on the NLU, as well as to take into account their interaction. At the same time, the hypothesis about the influence of needs on NLU under the scenario similar to the pattern of Yerkes-Dodson is argued. And the theoretical conclusion that emotions fulfill the function of the operator of the structural features of the information metabolism of NLU is substantiated. Thus, depending on the modality of emotions in the process of NLU, it was proposed to distinguish two scenarios for the implementation of information metabolism - reduction and synthetic. The argument in favor of the conclusion about the productive and constitutive role of emotions in the process of NLU is also given. (shrink)

We introduce a computational theory of situated language understanding in which the meaning of words and utterances depends on the physical environment and the goals and plans of communication partners. According to the theory, concepts that ground linguistic meaning are neither internal nor external to language users, but instead span the objective‐subjective boundary. To model the possible interactions between subject and object, the theory relies on the notion of perceived affordances: structured units of interaction that can be (...) used for prediction at multiple levels of abstraction. Language understanding is treated as a process of filtering perceived affordances. The theory accounts for many aspects of the situated nature of human language use and provides a unified solution to a number of demands on any theory of language understanding including conceptual combination, prototypicality effects, and the generative nature of lexical items.To support the theory, we describe an implemented system that understands verbal commands situated in a virtual gaming environment. The implementation uses probabilistic hierarchical plan recognition to generate perceived affordances. The system has been evaluated on its ability to correctly interpret free‐form spontaneous verbal commands recorded from unrehearsed game play between human players. The system is able to “step into the shoes” of human players and correctly respond to a broad range of verbal commands in which linguistic meaning depends on social and physical context. We quantitatively compare the system's predictions in response to direct player commands with the actions taken by human players and show generalization to unseen data across a range of situations and verbal constructions. (shrink)

In recent years the view that understanding a language requires knowing what its words and expressions mean has come under attack. One line of attack attempts to show that while knowledge can be undermined by Gettier-style counterexamples, language understanding cannot be. I consider this line of attack, particularly in the work of Pettit and Longworth, and show it to be unpersuasive. I stress, however, that maintaining a link between language understanding and knowledge does not (...) itself vindicate a cognitivist view of the former. (shrink)

The article argues that cognitive linguistic theory may prove an alternative to the Montague paradigm for designing natural language understanding systems. Within this framework it describes a system which models language understanding as a dialogical process between user and computer. The system operates with natural language texts as input and represent language meaning as entity-relationship diagrams.

Is language understanding a special case of social cognition? To help evaluate this view, we can formalize it as the rational speech-act theory: Listeners assume that speakers choose their utterances approximately optimally, and listeners interpret an utterance by using Bayesian inference to “invert” this model of the speaker. We apply this framework to model scalar implicature (“some” implies “not all,” and “N” implies “not more than N”). This model predicts an interaction between the speaker's knowledge state and the (...) listener's interpretation. We test these predictions in two experiments and find good fit between model predictions and human judgments. (shrink)

While cognitive linguists have been successful at providing accounts of the stable knowledge structures (conceptual metaphors) that give rise to figurative language, and the conceptual mechanisms that manipulate these knowledge structures (conceptual blending), relatively less effort has been thus far devoted to the nature of the linguistic mechanisms involved in figurative language understanding. This paper presents a theoretical account of figurative language understanding, examining metaphor and metonymy in particular. This account is situated within the Theory (...) of Lexical Concepts and Cognitive Models (LCCM Theory). LCCM Theory (Evans, Cognitive Linguistics 17: 491–534, 2006, How words mean: Lexical concepts, cognitive models and meaning construction, Oxford University Press, 2009b) is a cognitively realistic model of lexical representation and semantic compositionality, providing, it is argued, an account of figurative language which complements the ‘backstage’ cognition perspective of Conceptual Blending Theory. It also integrates the notion of conceptual metaphor within the account provided of figurative language understanding. The paper introduces the key mechanisms involved in figurative language understanding arising from language use. The paper also provides a programmatic account of how conceptual metaphors are integrated with linguistic knowledge in figurative language use. It is argued the present proposals flesh out a key aspect of the conceptual integration perspective promoted by Fauconnier and Turner, with which LCCM Theory is continuous. In part, the paper attempts to advance the prospect of a ‘joined up’ cognitive linguistic account of figurative language understanding. (shrink)

Several disciplines within the cognitive sciences have advanced the idea that people comprehend the actions of others, including the linguistic meanings they communicate, through embodied simulations where they imaginatively recreate the actions they observe or hear about. This claim has important consequences for theories of mind and meaning, such as that people’s use and interpretation of language emerges as a kind of bodily activity that is an essential part of ordinary cognition. Daniel Weiskopf presents several arguments against the idea (...) that experiential simulations play a major role in immediate language use and meaning. We offer several rebuttals to Weiskopf, in which we critique his interpretation of simulation theory, present additional psycholinguistic evidence supportive of the simulation perspective, and suggest that a more traditional theory of linguistic meaning and processing has little psychological and empirical validity.Keywords: Language; Comprehension; Embodied cognition; Embodied simulation; Linguistic meaning, Psycholinguistics. (shrink)

The essay deals with the mechanism of interpretation for legal metaphorical expressions. Firstly, it points out the perspective the cognitive approach induced about legal metaphors; then it suggests that this perspective gains in plausibility when a new bilateral model of language understanding is endorsed. A possible sketch of the meaning-making procedure for legal metaphors, compatible with this new model, is then proposed, and illustrated with some examples built on concepts belonging to the Italian Civil Code. The insights the (...) bilateral model of understanding provides are compared with the practice followed by legal communities for dealing with the metaphorical expressions they coin and use. (shrink)

An Example for Natural Language Understanding and the AI Problems it Raises I think this 1976 memorandum is of 1996 interest. The problems it raises haven't been solved or even substantially reformulated.

Meaning depends on context. This applies in obvious cases like deictics or sarcasm as well as more subtle situations like framing or persuasion. One key aspect of this is the identity of the participants in an interaction. Our interpretation of an utterance shifts based on a variety of factors, including personal history, background knowledge, and our relationship to the source. While obviously an incomplete model of individual differences, demographic factors provide a useful starting point and allow us to capture some (...) of this variance. However, the relevance of specific demographic factors varies between situations—where age might be the key factor in one context, ideology might dominate in another. To address this challenge, we introduce a method for combining demographics and context into situated demographic embeddings—mapping representations into a continuous geometric space appropriate for the given domain, showing the resulting representations to be functional and interpretable. We further demonstrate how to make use of related external data so as to apply this approach in low‐resource situations. Finally, we show how these representations can be incorporated into improve modeling of real‐world natural language understanding tasks, improving model performance and helping with issues of data sparsity. (shrink)

Many scholars often use the terms “metaphors,” “analogies,” and “models” interchangeably and inadvertently overlook the uniqueness of each word. According to recent cognitive studies, the three terms involve distinct cognitive processes using features from a familiar concept and applying them to an abstract, complicated concept. In the field of science and religion, there have been various objects or ideas used as metaphors, analogies, or models to describe the science–religion relationship. Although these heuristic tools provided some understanding of the complex (...) interaction, they failed to address the broad nature of science and religion as well as the multifarious relationship between the two in a sociocultural context. Unlike the previous candidates, the concept of language, including the notions of linguistic worldview, linguistic identity, dialects, power, and bilingualism, offers a unique and comprehensive window through which science, religion, and the relationship between the two are seen with clarity. (shrink)

This paper engages with Johaness Bronkhorst’s recognition of a “correspondence principle” as an underlying assumption of Nāgārjuna’s thought. Bronkhorst believes that this assumption was shared by most Indian thinkers of Nāgārjuna’s day, and that it stimulated a broad and fascinating attempt to cope with Nāgārjuna’s arguments so that the principle of correspondence may be maintained in light of his forceful critique of reality. For Bronkhorst, the principle refers to the relation between the words of a sentence and the realities they (...) are meant to convey. While I accept this basic intuition of correspondence, this paper argues that a finer understanding of the principle can be offered. In light of a set of verses from Nāgārjuna’s Śūnyatāsaptati (45–57), it is maintained that for Nāgārjuna, the deeper level of correspondence involves a structural identity he envisions between understanding and reality. Here Nāgārjuna claims that in order for things to exist, a conceptual definition of their nature must be available; in order for there to be a real world and reliable knowledge, a svabhāva of things must be perceived and accounted for. Svabhāva is thus reflected as a knowable essence. Thus, Nāgārjuna’s arguments attacks the accountability of both concepts and things, a position which leaves us with nothing more than mistaken forms of understanding as the reality of the empty. This markedly metaphysical approach is next analyzed in light of the debate Nāgārjuna conducts with a Nyāya interlocutor in his Vigrahavyāvartanī. The correspondence principle is here used to highlight the metaphysical aspect of the debate and to point out the ontological vision of Nāgārjuna’s theory of emptiness. In the analysis of the Vigrahavyāvartanī it becomes clear that the discussion revolves around a foundational metaphysical deliberation regarding the reality or unreality of svabhāva. In this dispute, Nāgārjuna fails to answer the most crucial point raised by his opponent—what is that he defines as empty? (shrink)

This essay considers what it means to understand natural language and whether a computer running an artificial-intelligence program designed to understand natural language does in fact do so. It is argued that a certain kind of semantics is needed to understand natural language, that this kind of semantics is mere symbol manipulation (i.e., syntax), and that, hence, it is available to AI systems. Recent arguments by Searle and Dretske to the effect that computers cannot understand natural (...) class='Hi'>language are discussed, and a prototype natural-language-understanding system is presented as an illustration. (shrink)

Our long-standing hypothesis has been that feedforward information flow is sufficient for speech perception, reading, and sentence (syntactic and semantic) processing more generally. We are encouraged by the target article's argument for the same hypothesis, but caution that more precise quantitative predictions will be necessary to advance the field.

Why is mutual understanding between two substantially different comprehensive language communities often problematic and even unattainable? To answer this question, the author first introduces a notion of presuppositional languages. Based on the semantic structure of a presuppositional language, the author identifies a significant condition necessary for effective understanding of a language: the interpreter is able to effectively understand a language only if he/she is able to recognize and comprehend its metaphysical presuppositions. The essential role (...) of the knowledge of metaphysical presuppositions in understanding is further strengthened by developing a truth-value conditional theory of understanding. It is concluded that if the interpreter approaches an incompatible alien language from the standpoint of the interpreter's own language by projecting the metaphysical presuppositions of his/her own language upon the alien language, then the mutual understanding between the two language communities is doomed to failure. (shrink)

The notion of modularity, introduced by Noam Chomsky and developed with special emphasis on perceptual and linguistic processes by Jerry Fodor in his important book The Modularity of Mind, has provided a significant stimulus to research in cognitive science. This book presents essays in which a diverse group of philosophers, linguists, psycholinguists, and neuroscientists - including both proponents and critics of the modularity hypothesis - address general questions and specific problems related to modularity. Jay L. Garfield is Associate Professor of (...) Philosophy in the School of Communications and Cognitive Science at Hampshire College. (shrink)

A classic problem in cognitive science concerns how listeners perceive and understand speech as comprised of discrete words. We propose a Syllable Inference account of spoken word recognition and segmentation, under which alternative hierarchical models of syllables, words, and phonemes are dynamically posited from cues that include current and past speech rate, with a goal of maximal prediction of sensory input. Three experiments using the Visual World eye‐tracking paradigm provide evidence supporting our proposal.

Stephen Laurence and Eric Margolis have recently argued that certain kinds of regress arguments against the language of thought (LOT) hypothesis as an account of how we understand natural languages have been answered incorrectly or inadequately by supporters of LOT ('Regress arguments against the language of thought', Analysis, 57 (1), 60-6, J 97). They argue further that this does not undermine the LOT hypothesis, since the main sources of support for LOT are (or might be) independent of it (...) providing an account of how we understand natural language. In my paper I seek to refute both these claims, and reinstate the putative explanation of natural language understanding as a necessarily central part of the support for LOT. The main argument exploits the fact that Laurence and Margolis give too little weight to the ideas (a) that LOT might be innate (b) that for LOT supporters a semantic theory must apply to in-the-head tokens, not linguistic utterances. (shrink)

I advocate a theory of syntactic semantics as a way of understanding how computers can think (and how the Chinese-Room-Argument objection to the Turing Test can be overcome): (1) Semantics, considered as the study of relations between symbols and meanings, can be turned into syntax – a study of relations among symbols (including meanings) – and hence syntax (i.e., symbol manipulation) can suffice for the semantical enterprise (contra Searle). (2) Semantics, considered as the process of understanding one domain (...) (by modeling it) in terms of another, can be viewed recursively: The base case of semantic understanding –understanding a domain in terms of itself – is syntactic understanding. (3) An internal (or narrow ), first-person point of view makes an external (or wide ), third-person point of view otiose for purposes of understanding cognition. (shrink)

A proposal is made concerning the introduction of the notions of cause and reason into a natural language understanding system. Its hypothesis is that one should prefer rational explanations of actions when dealing with human, or human‐like, agents, if one can find them in what one is analyzing, but that in other, nonhuman, cases one should prefer causal explanations. The reader is reminded of the existing state of the preference semantics system, and then are described the changes that (...) would have to be made to incorporate the above proposal and to find examples to test it. Finally, it is argued that there is no reason to think that a more complex taxonomy of causes (beyond the opposition of causes and reasons) is required, at least not if, as here. one seeks a procedural distinction corresponding to any taxonomic distinction among inference rules. (shrink)

The papers in this volume represent the views of a range of experts in a variety of language-related disciplines on the role which context plays in language learning and language understanding. The authors provide various theoretical constructs which help impose order on the apparent chaos of contextual factors which may have an influence on the production and comprehension of speech events. They focus on a variety of types of context, including the context established by different speech (...) communities, interpersonal contexts, the classroom context, and the context provided by the linguistic code itself. The papers illustrate how the treatment of context varies across the disciplines of linguistics, historical stylistics, applied linguistics, and psycholinguistics. Each paper is prefaced by an editorial introduction to help the reader trace out common themes and points of conflict. (shrink)

Summary Pluralism and monism are the two current views concerning scientific research and language understanding. Between them there is a third, intermediate, view. We take a procedural methodology of science as exemplified in the work of L. Tondl, and procedural linguistics , as exemplified in the work of B. Harrison, to be representative of this third possibility. Procedures are cognitive, linguistic, and physical processes which, through their hierarchical interconnections can generate fruitful mechanisms . These mechanisms are sensitive to (...) context and operate in heuristic and algorithmic ways. Their similar logical structure points towards a profound unified basis for scientific and linguistic activities, thus providing an interesting bridge between what is achieved by a little child talking to his parents, and a creative scientist struggling to interpret the results of his experiments. (shrink)

This paper is concerned with those elements of planning knowledge that are common to both understanding someone else's plan and creating a plan for one's own use. This planning knowledge can be divided into two bodies: Knowledge about the world, and knowledge about the planning process itself. Our interest here is primarily with the latter corpus. The central thesis is that much of the knowledge about the planning process itself can be formulated in terms of higher‐level goals and plans (...) called meta‐goals and meta‐plans. These entities can then be used by the same understanding and planning mechanisms that process ordinary goals and plans. However, the meta‐planning knowledge now enables these mechanisms to handle much more complicated situations in a uniform manner.Systems based on meta‐planning would have a number of advantages over existing problem solving and understanding systems. The same knowledge could be shared by both a planner and understander, and both would be able to handle complex situations elegantly. In addition, in planning, the use of meta‐planning has several advantages over more traditional methods involving constraints or critics. Meta‐planning allows the full power of a problem solver to be applied to situations that are generally amenable only to special purpose processing. In addition, meta‐planning facilitates the representation of some situations that are difficult to express otherwise. We have begun to introduce meta‐planning knowledge into two systems: PAM, a story understanding program, and PANDORA, a problem solving and plannin̈g system. (shrink)

This book is a guide to understanding and applying the essential, heretofore elusive notion of context in language study and pedagogy: Éva Illés offers a new, critical, systematic theoretical framework, then applies that framework to practical interactions and issues in communicative language teaching rooted in English as a Lingua Franca. By linking theory and practice for research and teaching around the world, this book brings a new awareness of how context can be conceptualized and related to (...) class='Hi'>language pedagogy to advanced students, teachers, teacher educators, and researchers of language teaching, applied linguistics, and pragmatics. (shrink)

If we had to indicate in few words the main features of this introductory text to linguistic pragmatics we should maybe begin pointing out the clarity in the exposition. Taking into account its shortness and its pleasant style, we must acknowledge that this book is an excellent introduction to pragmatics. Reading it one not only can make an approach to the central topics and problems in this field, but also can form a clear idea on the wide and varied scope (...) of the discipline. The domain of pragmatics is defined by Green as an intersection of fields within and outside of cognitive science, such as linguistics, cognitive psychology, cultural anthropology and philosophy, and also sociology and rhetoric. But as she remarks. (shrink)

��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)

Philosophical Investigations, Volume 45, Issue 4, Page 490-511, October 2022.

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

This is my translation of Gadamer's 1990 lecture "The Diversity of Languages and Understanding of the World." "In his lecture, Gadamer presents his views of language and world in a distinctively hermeneutical key. For example, he emphasizes language as that which 'belongs to conversation.' That is, language as conversation helps to bring about understanding and involves the play of dialogical exchange. 'Language is not proposition and judgment; rather, it is what it is, only when (...) it is question and answer.' Language involves another; it is on-the-way [unterwegs] to another. In fact, when addressing his question—what does world mean—Gadamer clarifies that humans and world are intimately connected; the world is that in which we are 'in the midst' and 'understanding is understanding oneself in the world.' But we are also in-the-world with others, and understanding ourselves in the world, means to understand ourselves with others. Gadamer goes so far as to say that our self-understanding as achieved in relation to others, as well as our understanding of others, should be taken in a moral and political sense. That is, the other is not there as merely a means to our ends or to exploit. Rather, 'the other indicates a principal limit to our self-love and self-centeredness. This is a general moral problem. It is also a political problem.' He goes on to emphasize the difficult task of achieving genuine solidarity with those from different cultures. Such a task requires language as conversation, the back-and-forth of dialogical exchange in which we come to understand the other and the other comes to understand us. Again and again, Gadamer underscores the task that each of has in light of our pluralistic world “to learn to bridge and reconcile the distances and differences between us and that means that we respect, look after, care for the other, and give one other a new hearing.” In contrast with the story of the Tower of Babel in which the people sought a pseudo-unity or 'oneness' driven by a will to dominate, Gadamer embraces both cultural and linguistic diversity and warns against reducing these multiple horizons 'by any special contrivance of unity [Einheitsmechanik].' He encourages us to seek out the open spaces that arise in our interactions with one another, to resist the levelling of language that information technology tends toward, and to 'cultivate language in its most distinctive possibilities.' In our present age of disinformation warfare, which threatens democracies worldwide and is a direct challenge to truth and the possibility of a meaningful dialogue with others, we would do well to linger with Gadamer’s hermeneutical and ethical insights and contemplate how we might bring these insights to bear on the global and political crises that we face today—Russia’s war of aggression against Ukraine, our climate catastrophe, and ever new forms of technical sophistry and disinformation that seek to erode our trust in truth, reality, and language itself.". (shrink)

A significant discrepancy in Wittgenstein's studies is whether Philosophical Investigations contains any trace of positive philosophy, notwithstanding the author's apparent anti-theoretic position. This study argues that the so-called ‘Chapter on philosophy’ in the Investigations §§89–133 contains negative and positive vocabulary and the use of various voices through which Wittgenstein employs his primary method of language-games, thus providing a surveyable understanding of several philosophical concepts, such as knowledge and time. His positive philosophy aims to reorient our attention from (...) class='Hi'>understanding the theories on these concepts to understanding the concepts themselves, regardless of any theorisation. (shrink)

Understanding is a ‘language event’ founded upon a ‘silent agreement’ between participants in a conversation. This silent agreement, built up of conversational aspects held in common, is what makes social solidarity possible and shows that the methods of science are an inappropriate starting point for our self-understanding. However, with the advent of industrial technical civilization, the question arises whether understanding has come under the control of a centrally steered communication system where language is a consciously (...) wielded instrument of politics with a corresponding loss of free insight and critical judgement. Only via a hermeneutic logic of words, which begins from recognition that words get their meaning from the open space of living conversation, can critical judgement be defended in the face of the authority of science and technology. (shrink)

A new comprehensive framework for narrative understanding has been developed. Its centerpiece is a new situational logic calledEpisodic Logic, a knowledge and semantic representation well-adapted to the interpretive and inferential needs of general NLU. The most distinctive features of EL is its natural language-like expressiveness. It allows for generalized quantifiers, lambda abstraction, sentence and predicate modifiers, sentence and predicate reification, intensional predicates, unreliable generalizations, and perhaps most importantly, explicit situational variables linked to arbitrary formulas that describe them. These (...) allow episodes to be explicitly related in terms of part-whole, temporal and causal relations. Episodic logical form is easily computed from surface syntax and lends itself to effective inference. (shrink)