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)

This paper presents a simple and versatile tree-rewriting lexicalized grammar formalism, TAGLET, that provides an effective scaffold for introducing advanced topics in a survey course on natural language processing (NLP). Students who implement a strong competence TAGLET parser and generator simultaneously get experience with central computer science ideas and develop an effective starting point for their own subsequent projects in data-intensive and interactive NLP.

The computational program for theoretical neuroscience initiated by Marr and Poggio (1977) calls for a study of biological information processing on several distinct levels of abstraction. At each of these levels — computational (defining the problems and considering possible solutions), algorithmic (specifying the sequence of operations leading to a solution) and implementational — significant progress has been made in the understanding of cognition. In the past three decades, computational principles have been discovered that are common to a wide range of (...) functions in perception (vision, hearing, olfaction) and action (motor control). More recently, these principles have been applied to the analysis of cognitive tasks that require dealing with structured information, such as visual scene understanding and analogical reasoning. Insofar as language relies on cognition-general principles and mechanisms, it should be possible to capitalize on the recent advances in the computational study of cognition by extending its methods to linguistics. (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)

Communication and content presents a comprehensive and foundational account of meaning based on new versions of situation theory and game theory. The literal and implied meanings of an utterance are derived from first principles assuming little more than the partial rationality of interacting agents. New analyses of a number of diverse phenomena – a wide notion of ambiguity and content encompassing phonetics, syntax, semantics, pragmatics, and beyond, vagueness, convention and conventional meaning, indeterminacy, universality, the role of truth in communication, semantic (...) change, translation, Frege’s puzzle of informative identities – are developed. Communication, speaker meaning, and reference are defined. Frege’s context and compositional principles are generalized and reconciled in a fixed-point principle, and a detailed critique of Grice, several aspects of Lewis, and some aspects of the Romantic conception of meaning are offered. Connections with other branches of linguistics, especially psycholinguistics, sociolinguistics, historical linguistics, and natural language processing, are explored. -/- The book will be of interest to scholars in philosophy, linguistics, artificial intelligence, and cognitive science. It should also interest readers in related fields like literary and cultural theory and the social sciences. (shrink)

In the last two decades, WORDNET has evolved as the most comprehensive computational lexicon of general English. In this article, we discuss its potential for supporting the creation of an entirely new kind of information resource for public health, viz. MEDICAL WORDNET. This resource is not to be conceived merely as a lexical extension of the original WORDNET to medical terminology; indeed, there is already a considerable degree of overlap between WORDNET and the vocabulary of medicine. Instead, we propose a (...) new type of repository, consisting of three large collections of (1) medically relevant word forms, structured along the lines of the existing Princeton WORDNET; (2) medically validated propositions, referred to here as medical facts, which will constitute what we shall call MEDICAL FACTNET; and (3) propositions reflecting laypersons’ medical beliefs, which will constitute what we shall call the MEDICAL BELIEFNET. We introduce a methodology for setting up the MEDICAL WORDNET. We then turn to the discussion of research challenges that have to be met in order to build this new type of information resource. (shrink)

Progress in molecular biology has revealed profound relations between linguistic and genomic sciences, mainly through advances in bioinformatics. The structural symmetries between biochemical and verbal syntaxes raise the question of their origins: did they emerge independently, or did one arise from the other? Does the genetic code contain the traces of a protolanguage, a universal grammar whose gradual evolution and successive mutations progressively led to the polymorphism of natural languages? To explore this question, we review the isomorphism of the genetic (...) code and verbal codes from lexical, syntactic, semantic and pragmatic standpoints. We discuss the limits of these symmetries and their anthropomorphic connotations. We observe the gradual evolution of species and languages according to parallel mechanisms, and the genetic roots of the physiology of language. In conclusion, we hypothesize that human observers may not be projecting linguistic frameworks onto genomic structures. Rather, it could be their linguistic faculties that reflect the grammatical structure of genetic code. (shrink)

Traditional methods for deriving property-based representations of concepts from text have focused on either extracting only a subset of possible relation types, such as hyponymy/hypernymy (e.g., car is-a vehicle) or meronymy/metonymy (e.g., car has wheels), or unspecified relations (e.g., car—petrol). We propose a system for the challenging task of automatic, large-scale acquisition of unconstrained, human-like property norms from large text corpora, and discuss the theoretical implications of such a system. We employ syntactic, semantic, and encyclopedic information to guide our extraction, (...) yielding concept-relation-feature triples (e.g., car be fast, car require petrol, car cause pollution), which approximate property-based conceptual representations. Our novel method extracts candidate triples from parsed corpora (Wikipedia and the British National Corpus) using syntactically and grammatically motivated rules, then reweights triples with a linear combination of their frequency and four statistical metrics. We assess our system output in three ways: lexical comparison with norms derived from human-generated property norm data, direct evaluation by four human judges, and a semantic distance comparison with both WordNet similarity data and human-judged concept similarity ratings. Our system offers a viable and performant method of plausible triple extraction: Our lexical comparison shows comparable performance to the current state-of-the-art, while subsequent evaluations exhibit the human-like character of our generated properties. (shrink)

Este artigo canta uma canção — uma canção criada ao unir o trabalho de quatro grandes nomes na história da lógica: Hans Reichenbach, Arthur Prior, Richard Montague, e Leon Henkin. Embora a obra dos primeiros três desses autores tenha sido previamente combinada, acrescentar as ideias de Leon Henkin é o acréscimo requerido para fazer com que essa combinação funcione no nível lógico. Mas o presente trabalho não se concentra nas tecnicalidades subjacentes (que podem ser encontradas em Areces, Blackburn, Huertas, e (...) Manzano [no prelo]), e sim nos instrumentos subjacentes e no modo como trabalham em conjunto. Esperamos que o leitor fique tentado a cantar junto. DOI:10.5007/1808-1711.2011v15n2p225. (shrink)

Abstract Since their inception, distributional models of semantics have been criticized as inadequate cognitive theories of human semantic learning and representation. A principal challenge is that the representations derived by distributional models are purely symbolic and are not grounded in perception and action; this challenge has led many to favor feature-based models of semantic representation. We argue that the amount of perceptual and other semantic information that can be learned from purely distributional statistics has been underappreciated. We compare the representations (...) of three feature-based and nine distributional models using a semantic clustering task. Several distributional models demonstrated semantic clustering comparable with clustering-based on feature-based representations. Furthermore, when trained on child-directed speech, the same distributional models perform as well as sensorimotor-based feature representations of children’s lexical semantic knowledge. These results suggest that, to a large extent, information relevant for extracting semantic categories is redundantly coded in perceptual and linguistic experience. Detailed analyses of the semantic clusters of the feature-based and distributional models also reveal that the models make use of complementary cues to semantic organization from the two data streams. Rather than conceptualizing feature-based and distributional models as competing theories, we argue that future focus should be on understanding the cognitive mechanisms humans use to integrate the two sources. (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.

The number of available legal documents has presented an enormous growth in recent years, and the digital processing of such materials is prompting the necessity of systems that support the automatic relevant information extraction. This work presents a system for ontology-based information extraction from natural language texts, able to identify a set of legal events. The system is based on an innovative methodology based on domain ontology of legal events and a set of linguistic rules, integrated through inference mechanism, resulting (...) in a flexible approach and scalable approach. A case study with the use of documents from the Superior Court in Brazil is related, with satisfactory results in precision and recall. (shrink)

Most areas of the cognitive and social sciences assume that knowledge representations are constructed and used during communication and that much of its content is social. Those of us who build computer models of comprehension and conversation are forced to be explicit about the nature of these knowledge representations and affiliated processes. There are some conditions when knowledge is not sufficiently social, and other conditions when knowledge is overly grounded in social mechanisms. The argument is advanced that constraints, coherence, and (...) precision are very much at the heart of an explanation of the nature and amount of social knowledge. Asocial content reigns supreme when the referential world knowledge is highly constrained, coherently structured, and precisely specified. The social context of knowledge construction becomes progressively more influential to the extent to that world knowledge is vague, open-ended, imprecise, underspecified, and fragmentary. (shrink)

The use of voluntary assisted dying as an end‐of‐life option has stimulated concerns and debates over the past decades. Although public attitudes towards voluntary assisted dying (including euthanasia and physician‐assisted suicide) are well researched, there has been relatively little study of the different reasons, normative reasoning and rhetorical strategies that people invoke in supporting or contesting voluntary assisted dying in everyday life. Using a mix of computational textual mining techniques, keyword study and qualitative thematic coding to analyse public submissions to (...) a parliamentary inquiry into voluntary assisted dying in Australia, this study critically examines the different reasons, normative reasoning and rhetorical strategies that people invoke in supporting or contesting voluntary assisted dying in everyday life. The analysis identified complex and potentially contradictory ethical principles being invoked on both sides of the debate. These findings deepen our understanding of the moral basis of public reasoning about end‐of‐life matters and will help to inform future discussions on policy and law reform. The findings underscore the importance of sound normative reasoning and the use of caution when interpreting opinion polls to inform policy. (shrink)

To acquire one’s native phonological system, language-specific phonological categories and relationships must be extracted from the input. The acquisition of the categories and relationships has each in its own right been the focus of intense research. However, it is remarkable that research on the acquisition of categories and the relations between them has proceeded, for the most part, independently of one another. We argue that this has led to the implicit view that phonological acquisition is a “two-stage” process: Phonetic categories (...) are first acquired and then subsequently mapped onto abstract phoneme categories. We present simulations that suggest two problems with this view: First, the learner might mistake the phoneme-level categories for phonetic-level categories and thus be unable to learn the relationships between phonetic-level categories; on the other hand, the learner might construct inaccurate phonetic-level representations that prevent it from finding regular relations among them. We suggest an alternative conception of the phonological acquisition problem that sidesteps this apparent inevitability and acquires phonemic categories in a single stage. Using acoustic data from Inuktitut, we show that this model reliably converges on a set of phoneme-level categories and phonetic-level relations among subcategories, without making use of a lexicon. (shrink)

This is a report on the Doctoral Consortium co-located with the 17th International Conference on Artificial Intelligence and Law in Montreal.

The rapid development of natural language processing in the last three decades has drastically changed the way professional translators do their work. Nowadays most of them use computer-assisted translation or translation memory tools whose evolution has been overshadowed by the much more sensational development of machine translation systems, with which TM tools are sometimes confused. These two language technologies now interact in mutually enhancing ways, and their increasing role in human translation has become a subject of behavioral studies. Philosophers and (...) linguists, however, have been slow in coming to grips with these important developments. The present paper seeks to fill in this lacuna. I focus on the semantic aspects of the highly distributed human–computer interaction in the CAT process which presents an interesting case of an extended cognitive system involving a human translator, a TM tool, an MT engine, and sometimes other human translators or editors. Considered as a whole, such a system is engaged in representing the linguistic meaning of the source document in the target language. But the roles played by its various components, natural as well as artificial, are far from trivial, and the division of linguistic labor between them throws new light on the familiar notions that were initially inspired by rather different phenomena in the philosophy of language, mind, and cognitive science. (shrink)

This study realizes belief/reliability change of a judge in a legal judgment by dynamic epistemic logic. A key feature of DEL is that possibilities in an agent’s belief can be represented by a Kripke model. This study addresses two difficulties in applying DEL to a legal case. First, since there are several methods for constructing a Kripke model, our question is how we can construct the model from a legal case. Second, since this study employs several dynamic operators, our question (...) is how we can decide which operators are to be applied for belief/reliability change of a judge. In order to solve these difficulties, we have implemented a computer system which provides two functions. First, the system can generate a Kripke model from a legal case. Second, the system provides an inconsistency solving algorithm which can automatically perform several operations in order to reduce the effort needed to decide which operators are to be applied. By our implementation, the above questions can be adequately solved. With our analysis method, six legal cases are analyzed to demonstrate our implementation. (shrink)

Cause-related marketing has risen to become a popular strategy to increase business value through profit-motivated giving. Despite the growing number of articles published in the last decade, no comprehensive analysis of the most discussed constructs of cause-related marketing is available. This paper uses an advanced Text Mining methodology to conduct a comprehensive analysis of 246 articles published in 40 different journals between 1988 and 2013 on the subject of cause-related marketing. Text Mining also allows quantitative analyses to be performed on (...) the literature. For instance, it is shown that the most prominent long-term topics discussed since 1988 on the subject are “brand-cause fit”, “law and Ethics”, and “corporate and social identification”, while the most actively discussed topic presently is “sectors raising social taboos and moral debates”. The paper has two goals: first, it introduces the technique of CTM to the Marketing area, illustrating how Text Mining may guide, simplify, and enhance review processes while providing objective building blocks to be used in a review; second, it applies CTM to the C-RM field, uncovering and summarizing the most discussed topics. Mining text, however, is not aimed at replacing all subjective decisions that must be taken as part of literature review methodologies. (shrink)

The sounds that make up spoken words are heard in a series and must be mapped rapidly onto words in memory because their elements, unlike those of visual words, cannot simultaneously exist or persist in time. Although theories agree that the dynamics of spoken word recognition are important, they differ in how they treat the nature of the competitor set—precisely which words are activated as an auditory word form unfolds in real time. This study used eye tracking to measure the (...) impact over time of word frequency and 2 partially overlapping competitor set definitions: onset density and neighborhood density. Time course measures revealed early and continuous effects of frequency (facilitatory) and on set based similarity (inhibitory). Neighborhood density appears to have early facilitatory effects and late inhibitory effects. The late inhibitory effects are due to differences in the temporal distribution of similarity within neighborhoods. The early facilitatory effects are due to subphonemic cues that inform the listener about word length before the entire word is heard. The results support a new conception of lexical competition neighborhoods in which recognition occurs against a background of activated competitors that changes over time based on fine-grained goodness-of-fit and competition dynamics. (shrink)