Computational Modeling Of Language Research Articles

Language and other complex behaviors: Unifying characteristics, computational models, neural mechanisms

Similar to other complex behaviors, language is dynamic, social, multimodal, patterned, and purposive, its purpose being to promote desirable actions or thoughts in others and self (Edelman, 2017b). An analysis of the functional characteristics shared by complex sequential behaviors suggests that they all present a common overarching computational problem: dynamically controlled constrained navigation in concrete or abstract situation spaces. With this conceptual framework in mind, I compare and contrast computational models of language and evaluate their potential for explaining linguistic behavior and for elucidating the brain mechanisms that support it.

Reference Production as Search: The Impact of Domain Size on the Production of Distinguishing Descriptions.

When producing a description of a target referent in a visual context, speakers need to choose a set of properties that distinguish it from its distractors. Computational models of language production/generation usually model this as a search process and predict that the time taken will increase both with the number of distractors in a scene and with the number of properties required to distinguish the target. These predictions are reminiscent of classic findings in visual search; however, unlike models of reference production, visual search models also predict that search can become very efficient under certain conditions, something that reference production models do not consider. This paper investigates the predictions of these models empirically. In two experiments, we show that the time taken to plan a referring expression-as reflected by speech onset latencies-is influenced by distractor set size and by the number of properties required, but this crucially depends on the discriminability of the properties under consideration. We discuss the implications for current models of reference production and recent work on the role of salience in visual search.

Introduction to the Special Issue on Cross-Language Algorithms and Applications

With the increasingly global nature of our everyday interactions, the need for multilin- gual technologies to support efficient and effective information access and communication cannot be overemphasized. Computational modeling of language has been the focus of Natural Language Processing, a subdiscipline of Artificial Intelligence. One of the current challenges for this discipline is to design methodologies and algorithms that are cross- language in order to create multilingual technologies rapidly. The goal of this JAIR special issue on Cross-Language Algorithms and Applications (CLAA) is to present leading re- search in this area, with emphasis on developing unifying themes that could lead to the development of the science of multi- and cross-lingualism. In this introduction, we provide the reader with the motivation for this special issue and summarize the contributions of the papers that have been included. The selected papers cover a broad range of cross-lingual technologies including machine translation, domain and language adaptation for sentiment analysis, cross-language lexical resources, dependency parsing, information retrieval and knowledge representation. We anticipate that this special issue will serve as an invaluable resource for researchers interested in topics of cross-lingual natural language processing.

Inducing Implicit Arguments from Comparable Texts: A Framework and Its Applications

In this article, we investigate aspects of sentential meaning that are not expressed in local predicate–argument structures. In particular, we examine instances of semantic arguments that are only inferable from discourse context. The goal of this work is to automatically acquire and process such instances, which we also refer to as implicit arguments, to improve computational models of language. As contributions towards this goal, we establish an effective framework for the difficult task of inducing implicit arguments and their antecedents in discourse and empirically demonstrate the importance of modeling this phenomenon in discourse-level tasks. Our framework builds upon a novel projection approach that allows for the accurate detection of implicit arguments by aligning and comparing predicate–argument structures across pairs of comparable texts. As part of this framework, we develop a graph-based model for predicate alignment that significantly outperforms previous approaches. Based on such alignments, we show that implicit argument instances can be automatically induced and applied to improve a current model of linking implicit arguments in discourse. We further validate that decisions on argument realization, although being a subtle phenomenon most of the time, can considerably affect the perceived coherence of a text. Our experiments reveal that previous models of coherence are not able to predict this impact. Consequently, we develop a novel coherence model, which learns to accurately predict argument realization based on automatically aligned pairs of implicit and explicit arguments.

Ellipsis: computation of.

A computational account of ellipsis should specify not only how the meaning of an elliptical sentence is computed in context but also a description of what is being computed. Many proposals can be divided into two groups, as per whether they compute the meaning of an elliptical sentence based on the semantic or the syntactic parts of its context. A unifying theme of these proposals is that they are all based on the idea that the meaning of an elliptical sentence is determinable based on a structured representation which is transformationally related to its surface syntactic structure. WIREs Cogn Sci 2012, 3:411-418. doi: 10.1002/wcs.1168 For further resources related to this article, please visit the WIREs website.

Effects of syllable structure in aphasic errors: Implications for a new model of speech production

Current models of word production assume that words are stored as linear sequences of phonemes which are structured into syllables only at the moment of production. This is because syllable structure is always recoverable from the sequence of phonemes. In contrast, we present theoretical and empirical evidence that syllable structure is lexically represented. Storing syllable structure would have the advantage of making representations more stable and resistant to damage. On the other hand, re-syllabifications affect only a minimal part of phonological representations and occur only in some languages and depending on speech register. Evidence for these claims comes from analyses of aphasic errors which not only respect phonotactic constraints, but also avoid transformations which move the syllabic structure of the word further away from the original structure, even when equating for segmental complexity. This is true across tasks, types of errors, and, crucially, types of patients. The same syllabic effects are shown by apraxic patients and by phonological patients who have more central difficulties in retrieving phonological representations. If syllable structure was only computed after phoneme retrieval, it would have no way to influence the errors of phonological patients. Our results have implications for psycholinguistic and computational models of language as well as for clinical and educational practices.

Special Issue on Language-Based Human Intelligence and Personalization

At the annual conference of the Japan Society for Artificial Intelligence (JSAI), a special survival session called "Challenge for Realizing Early Profits (CREP)" is organized to support and promote excellent ideas in new AI technologies expected to be realized and contributed to society within five years. Every year at the session, researchers propose their ideas and compete in being evaluated by conference participants. The Everyday Language Computing (ELC) project, started in 2000 at the Brain Science Institute, RIKEN, and ended in 2005, participated in the CREP program in 2001 to have their project evaluated by third parties and held an organized session every year in which those interested in language-based intelligence and personalization participate. They competed with other candidates, survived the session, and achieved the session's final goal to survive for five years. Papers in this special issue selected for presentation at the session include the following: The first article, "Everyday-Language Computing Project Overview," by Ichiro Kobayashi et al., gives an overview and the basic technologies of the ELC Project. The second to sixth papers are related to the ELC Project. The second article, "Computational Models of Language Within Context and Context-Sensitive Language Understanding," by Noriko Ito et al., proposes a new database, called the "semiotic base," that compiles linguistic resources with contextual information and an algorithm for achieving natural language understanding with the semiotic base. The third article, "Systemic-Functional Context-Sensitive Text Generation in the Framework of Everyday Language Computing," by Yusuke Takahashi et al., proposes an algorithm to generate texts with the semiotic base. The fourth article, "Natural Language-Mediated Software Agentification," by Michiaki Iwazume et al., proposes a method for agentifying and verbalizing existing software applications, together with a scheme for operating/running them. The fifth article, "Smart Help for Novice Users Based on Application Software Manuals," by Shino Iwashita et al., proposes a new framework for reusing electronic software manuals equipped with application software to provide tailor-made operation instructions to users. The sixth article, "Programming in Everyday Language: A Case for Email Management," by Toru Sugimoto et al., making a computer program written in natural language. Rhetorical structure analysis is used to translate the natural language command structure into the program structure. The seventh article, "Application of Paraphrasing to Programming with Linguistic Expressions," by Nozomu Kaneko et al., proposes a method for translating natural language commands into a computer program through a natural language paraphrasing mechanism. The eighth article, "A Human Interface Based on Linguistic Metaphor and Intention Reasoning," by Koichi Yamada et al., proposes a new human interface paradigm called Push Like Talking (PLT), which enables people to operate machines as they talk. The ninth article, "Automatic Metadata Annotation Based on User Preference Evaluation Patterns," by Mari Saito proposes effective automatic metadata annotation for content recommendations matched to user preference. The tenth article, "Dynamic Sense Representation Using Conceptual Fuzzy Sets," by Hiroshi Sekiya et al., proposes a method to represent word senses, which vary dynamically depending on context, using conceptual fuzzy sets. The eleventh article, "Common Sense from the Web? Naturalness of Everyday Knowledge Retrieved from WWW," by Rafal Rzepka et al., is a challenging work to acquire common-sense knowledge from information on the Web. The twelfth article, "Semantic Representation for Understanding Meaning Based on Correspondence Between Meanings," by Akira Takagi et al., proposes a new semantic representation to deal with Japanese language in natural language processing. I thank the reviewers and contributors for their time and effort in making this special issue possible, and I wish to thank the JACIII editorial board, especially Professors Kaoru Hirota and Toshio Fukuda, the Editors-in-Chief, for inviting me to serve as Guest Editor of this Journal. Thanks also go to Kazuki Ohmori and Kenta Uchino of Fuji Technology Press for their sincere support.

Everyday-Language Computing Project Overview

This paper explains an overview of everyday language computing (ELC) promoted by the Laboratory for Language-Based Intelligent Systems, Brain Science Institute, RIKEN from 2000 to 2005. The objective of ELC was to develop a language-based intelligent system. To do this, we constructed a computational model of language in context, called the Semiotic Base, and developed computational algorithms for text understanding and generation, which are basic information processing in the ELC framework. Based on these resources and algorithms, we constructed a computing environment in which language is used as an information medium to process information. To demonstrate its feasibility, we developed language-based applications such as a language-based wordprocessor, language-based programming, and “smart” help. We explain the basic principles of ELC, outline of its basic technologies, and discuss applications developed based on the ELC framework.

What can developmental disorders tell us about the neurocomputational constraints that shape development? The case of Williams syndrome

The uneven cognitive phenotype in the adult outcome of Williams syndrome has led some researchers to make strong claims about the modularity of the brain and the purported genetically determined, innate specification of cognitive modules. Such arguments have particularly been marshaled with respect to language. We challenge this direct generalization from adult phenotypic outcomes to genetic specification and consider instead how genetic disorders provide clues to the constraints on plasticity that shape the outcome of development. We specifically examine behavioral studies, brain imaging, and computational modeling of language in Williams syndrome but contend that our theoretical arguments apply equally to other cognitive domains and other developmental disorders. While acknowledging that selective deficits in normal adult patients might justify claims about cognitive modularity, we question whether similar, seemingly selective deficits found in genetic disorders can be used to argue that such cognitive modules are prespecified in infant brains. Cognitive modules are, in our view, the outcome of development, not its starting point. We note that most work on genetic disorders ignores one vital factor, the actual process of ontogenetic development, and argue that it is vital to view genetic disorders as proceeding under different neurocomputational constraints, not as demonstrations of static modularity.

The processing of verbs and nouns in neural networks: Insights from synthetic brain imaging

The paper presents a computational model of language in which linguistic abilities evolve in organisms that interact with an environment. Each individual’s behavior is controlled by a neural network and we study the consequences in the network’s internal functional organization of learning to process different classes of words. Agents are selected for reproduction according to their ability to manipulate objects and to understand nouns (objects’ names) and verbs (manipulation tasks). The weights of the agents’ neural networks are evolved using a genetic algorithm. Synthetic brain imaging techniques are then used to examine the functional organization of the neural networks. Results show that nouns produce more integrated neural activity in the sensory-processing hidden layer, while verbs produce more integrated synaptic activity in the layer where sensory information is integrated with proprioceptive input. Such findings are qualitatively compared with human brain imaging data that indicate that nouns activate more the posterior areas of the brain related to sensory and associative processing, while verbs activate more the anterior motor areas.

Hot topics in speech communication

In speech perception, the issues emphasized are related to long-term representation of speech units, language-specific differences in speech perception by infants and adults, and some new results from cochlear implant and other hearing research relating to the auditory coding of speech cues. New results on the question of prototypes for speech units and how speaker and contextual variability affect listeners’ behavior are reviewed. Next, there is a survey of recent findings on the effect of language background on infants’ and adults’ perception of speech. Finally, results from perceptual studies of cochlear implant patients involving systematically designed stimulus sets are summarized. In speech production, focus is on the applications of instrumentation, on numerical simulation, and on sensory feedback. There is discussion of measuring instruments that are beginning to provide data on motor compensation and coproduction, and sophisticated numerical simulations that are being developed to answer questions about vibratory mechanisms, air flow, and their relation to sound output. Finally, there is a discussion on the roles of receptor and auditory feedback on articulatory coordination and timing. In speech processing, stress is placed on the progress made in auditory representations, in computational models of language, and in statistical methods for text-to-speech synthesis. In auditory-based representations, 100- to 200-ms speech segments may serve as a basis for distance measures for speech coding that reflect perceptual acceptability of acoustic distortions, and as speech-recognition features that capture dynamic aspects of speech production. In spoken-language processing, the gap between stochastic models of speech (e.g., HMM’s and more traditional models of language structure (syntax) and content (semantics) is being bridged. Finally, text-to-speech synthesis is moving, albeit slowly, from hand-tuned to automatically trained systems.