Showing papers on "Natural language published in 1994"

Reflective teaching in second language classrooms

Abstract: Introduction: Teacher Development Through Exploring Classroom Processes 1. Approaches to Classroom Investigation in Teaching 2. Exploring Teachers' Beliefs 3. Focus on the Learner 4. Teacher Decision Making 5. The Role of the Teacher 6. The Structure of a Language Lesson 7. Interaction in the Second Language Classroom 8. The Nature of Language Learning Activities 9. Language Use in the Classroom Epilogue References

Making it explicit : reasoning, representing, and discursive commitment

Abstract: What would something unlike us - a computer, for example - have to be able to do to qualify as a possible knower, like us? To answer this question at the very heart of our sense of ourselves, philosophers have long focused on intentionality and have looked to language as a key to this condition. "Making It Explicit" is an investigation into the nature of language - the social practices that distinguish us as rational, logical creatures - that revises the very terms of this inquiry. Where accounts of the relation between language and mind have traditionally rested on the concept of representation, this book sets out an alternate approach based on inference, and on a conception of certain kinds of implicit assessment that become explicit in language. "Making It Explicit" attempts to work out in detail a theory that renders linguistic "meaning" in terms of "use" - in short, to explain how semantic content can be conferred on expressions and attitudes that are suitably caught up in social practices. At the centre of this enterprise is a notion of discursive commitment. Being able to talk - and so in the fullest sense being able to think - is a matter of mastering the practices that govern such commitments, being able to keep track of one's own commitments and those of others. Assessing the pragmatic signficance of speech acts is a matter of explaining the explicit in terms of the implicit. As he traces the inferential structure of the social practices within which things can be made conceptually explicit, the author defines the distinctively expressive role of logical vocabulary. This expressive account of language, mind and logic is, finally, an account of who "we" are.

Time in language

Abstract: This book looks at the various ways in which time is reflected in natural language. All natural languages have developed a rich repetoire of devices to express time, but linguists have tended to concentrate on tense and aspect, rather than discourse principles. Klein considers the four main ways in which language expresses time - the verbal categories of tense and aspect; inherent lexical features of the verb; and various types of temporal adverbs. Klein looks at the interaction of these four devices and suggests new or partly new treatments of these devices to express temporality.

Actions and Events in Interval Temporal Logic

Abstract: We present a representation of events and action based on interval temporal logic that is significantly more expressive and more natural than most previous AI approaches. The representation is motivated by work in natural language semantics and discourse, temporal logic, and AI planning and plan recognition. The formal basis of the representation is presented in detail, from the axiomatization of time periods to the relationship between actions and events and their effects. The power of the representation is illustrated by applying it to the axiomatization and solution of several standard problems from the AI literature on action and change. An approach to the frame problem based on explanation closure is shown to be both powerful and natural when combined with our representational framework. We also discuss features of the logic that are beyond the scope of many traditional representations, and describe our approach to difficult problems such as external events and simultaneous actions.

A Language and Program for Complex Bayesian Modelling

Abstract: Gibbs sampling has enormous potential for analysing complex data sets However, routine use of Gibbs sampling has been hampered by the lack of general purpose software for its implementation Until now all applications have involved writing one-off computer code in low or intermediate level languages such as C or Fortran We describe some general purpose software that we are currently developing for implementing Gibbs sampling: BUGS (Bayesian inference using Gibbs sampling) The BUGS system comprises three components: first, a natural language for specifying complex models; second, an 'expert system' for deciding appropriate methods for obtaining samples required by the Gibbs sampler; third, a sampling module containing numerical routines to perform the sampling S objects are used for data input and output BUGS is written in Modula-2 and runs under both DOS and UNIX

Input, Interaction, and Second Language Production.

Abstract: The role of conversational interactions in the development of a second language has been central in the recent second language acquisition literature. While a great deal is now known about the way in which nonnative speakers interact with native speakers and other nonnative speakers, little is known about the lasting effects of these interactions on a nonnative's linguistic development. This paper specifically investigates the relationship among input, interaction, and second language production. Through data from native–nonnative speaker interactions in a direction-giving task, we show that both modified input and interaction affect task performance. However, only interaction has an effect on subsequent task performance.

Do Gestures Communicate? A Review

Abstract: (1994). Do Gestures Communicate? A Review. Research on Language and Social Interaction: Vol. 27, No. 3, pp. 175-200.

Adaptive Statistical Language Modeling; A Maximum Entropy Approach

Abstract: : Language modeling is the attempt to characterize, capture and exploit regularities in natural language In statistical language modeling, large amounts of text are used to automatically determine the model's parameters Language modeling is useful in automatic speech recognition, machine translation, and any other application that processes natural language with incomplete knowledge In this thesis, I view language as an information source which emits a stream of symbols from a finite alphabet (the vocabulary) The goal of language modeling is then to identify and exploit sources of information in the language stream, so as to minimize its perceived entropy Most existing statistical language models exploit the immediate past only To extract information from further back in the document's history, I use trigger pairs as the basic information bearing elements This allows the model to adapt its expectations to the topic of discourse Next, statistical evidence from many sources must be combined Traditionally, linear interpolation and its variants have been used, but these are shown here to be seriously deficient Instead, I apply the principle of Maximum Entropy (ME) Each information source gives rise to a set of constraints, to be imposed on the combined estimate The intersection of these constraints is the set of probability functions which are consistent with all the information sources The function with the highest entropy within that set is the NE solution Language modeling, Adaptive language modeling, Statistical language modeling, Maximum entropy, Speech recognition

Multimodal natural language interface for cross-application tasks

Abstract: A multimodal natural language interface interprets user requests combining natural language input from the user with information selected from a current application and sends the request in the proper form to an appropriate auxiliary application for processing. The multimodal natural language interface enables users to combine natural language (spoken, typed or handwritten) input selected by any standard means from an application the user is running (the current application) to perform a task in another application (the auxiliary application) without either leaving the current application, opening new windows, etc., or determining in advance of running the current application what actions are to be done in the auxiliary application. The multimodal natural language interface carries out the following functions: (1) parsing of the combined multimodal input; (2) semantic interpretation (i.e., determination of the request implicit in the pars); (3) dialog providing feedback to the user indicating the systems understanding of the input and interacting with the user to clarify the request (e.g., missing information and ambiguities); (4) determination of which application should process the request and application program interface (API) code generation; and (5) presentation of a response as may be applicable. Functions (1) to (3) are carried out by the natural language processor, function (4) is carried out by the application manager, and function (5) is carried out by the response generator.

Teachers language use in university foreign language classrooms: a qualitative analysis of english and target language alternation

Abstract: In making the unavailable available, the teacher's role is one of facilitating the active use of the target language in the classroom, presenting the best possible model of the language, providing feedback, guidance, and reinforcement, and making available target-language data in terms of "comprehensible input," that is, the natural unconstrained use of the target language in the classroom (p. 8). (italics added)

Reexamining the Critical Period Hypothesis

Abstract: This study concerns the ability of adults to achieve nativelike competence in second language when the acquisition context lacks formal instruction and, therefore, more closely resembles the environment for first language acquisition. The study presents the results of extensive testing of an adult who has apparently acquired native proficiency in Egyptian Arabic (EA) in an untutored setting. The goal is to determine to what extent her linguistic competence matches that of native speakers. Measures employed to assess her level of achievement are a speech production task, a grammaticality judgment task, a translation task, an anaphoric interpretation task, and an accent recognition task. Results are compared to those of native speakers as well as to those of a proficient learner of EA with extensive formal instruction. The results lead the authors to reexamine the critical period hypothesis while addressing the role of talent in adult language learning. The study concludes with an evaluation of our subject's language learning history to discover what factors differentiate her from less successful naturalistic adult acquirers.

Integrating Grammar Instruction and Communicative Language Use Through Grammar Consciousness-Raising Tasks

Abstract: Grammar consciousness-raising tasks combine the development of knowledge about problematic L2 grammatical features with the provision for meaning-focused use of the target language. However, for this task type to be pedagogically useful in ESL/EFL classrooms, it must be shown that task performance is as effective as a teacher-fronted grammar lesson in promoting gains in knowledge of the target structure and is comparable to performance of regular communicative tasks in terms of opportunities for communicative language exchange. This article reports an investigation of three grammar consciousness-raising tasks dealing with word order. The results indicate that the tasks successfully promoted both proficiency gains and L2 negotiated interaction in the participants, with negotiation quantity being determined by the combination of task features present rather than by the nature of the task content. Thus, grammar consciousness-raising tasks can be recommended as one way to integrate formal instruction within a communicative framework.

Recent improvements in the CMU spoken language understanding system

Abstract: We have been developing a spoken language system to recognize and understand spontaneous speech. It is difficult for such systems to achieve good coverage of the lexicon and grammar that subjects might use because spontaneous speech often contains disfluencies and ungrammatical constructions. Our goal is to respond appropriately to input, even though coverage is not complete. The natural language component of our system is oriented toward the extraction of information relevant to a task, and seeks to directly optimize the correctness of the extracted information (and therefore the system response). We use a flexible frame-based parser, which parses as much of the input as possible. This approach leads both to high accuracy and robustness. We have implemented a version of this system for the Air Travel Information Service (ATIS) task, which is being used by several ARPA-funded sites to develop and evaluate speech understanding systems. Users are asked to perform a task that requires getting information from an Air Travel database. In this paper, we describe recent improvements in our system resulting from our efforts to improve the coverage given a limited amount of training data. These improvements address a number of problems including generating an adequate lexicon and grammar for the recognizer, generating and generalizing an appropriate grammar for the parser, and dealing with ambiguous parses.

Reviewing automatic language identification

Abstract: The Oregon Graduate Institute Multi-language Telephone Speech Corpus (OGI-TS) was designed specifically for language identification research. It currently consists of spontaneous and fixed-vocabulary utterances in 11 languages: English, Farsi, French, German, Hindi, Japanese, Korean, Mandarin, Spanish, Tamil, and Vietnamese. These utterances were produced by 90 native speakers in each language over real telephone lines. Language identification is related to speaker-independent speech recognition and speaker identification in several interesting ways. It is therefore not surprising that many of the recent developments in language identification can be related to developments in those two fields. We review some of the more important recent approaches to language identification against the background of successes in speaker and speech recognition. In particular, we demonstrate how approaches to language identification based on acoustic modeling and language modeling, respectively, are similar to algorithms used in speaker-independent continuous speech recognition. Thereafter, prosodic and duration-based information sources are studied. We then review an approach to language identification that draws heavily on speaker identification. Finally, the performance of some representative algorithms is reported. >

Natural language parsing as statistical pattern recognition

Abstract: Traditional natural language parsers are based on rewrite rule systems developed in an arduous, time-consuming manner by grammarians. A majority of the grammarian's efforts are devoted to the disambiguation process, first hypothesizing rules which dictate constituent categories and relationships among words in ambiguous sentences, and then seeking exceptions and corrections to these rules. In this work, I propose an automatic method for acquiring a statistical parser from a set of parsed sentences which takes advantage of some initial linguistic input, but avoids the pitfalls of the iterative and seemingly endless grammar development process. Based on distributionally-derived and linguistically-based features of language, this parser acquires a set of statistical decision trees which assign a probability distribution on the space of parse trees given the input sentence. These decision trees take advantage of significant amount of contextual information, potentially including all of the lexical information in the sentence, to produce highly accurate statistical models of the disambiguation process. By basing the disambiguation criteria selection on entropy reduction rather than human intuition, this parser development method is able to consider more sentences than a human grammarian can when making individual disambiguation rules. In experiments between a parser, acquired using this statistical framework, and a grammarian's rule-based parser, developed over a ten-year period, both using the same training material and test sentences, the decision tree parser significantly outperformed the grammar-based parser on the accuracy measure which the grammarian was trying to maximize, achieving an accuracy of 78% compared to the grammar-based parser's 69%.

Toward systems that understand spoken language

Abstract: MIT's Voyager system is an attempt to explore issues related to a fully interactive spoken-language system and natural language understanding. The system helps users get from one location to another within a specific geographical area, and can provide information about certain objects in the area. The current version of Voyager focuses on the city of Cambridge, Massachusetts, between MIT and Harvard University. Voyager's domain knowledge (or backend) is an enhanced version of an existing direction assistance program (J.R. Davis and T.F. Trobaugh, 1987). The map database includes the locations of various classes of objects (streets, buildings, rivers) and their properties (address, phone number, etc.). To retrieve information, the Summit speech recognition system converts the user's speech signal into a set of word hypotheses, the Tina natural language system interacts with Summit to obtain a word string and a linguistic interpretation of the utterance, and an interface between the two subsystems converts Tina's semantic representation into the appropriate function calls to the back-end. Voyager then responds with a map, highlighting the objects of interest, plus an textual and spoken answer. The current implementation has a vocabulary of about 350 words and can deal with various types of queries, such as the location of objects, simple properties of objects, how to get from one place to another, and the distance and travel time between objects. >

GEMINI: A Natural Language System for Spoken-Language Understanding

Abstract: Gemini is a natural language understanding system developed for spoken language applications. The paper describes the architecture of Gemini, paying particular attention to resolving the tension between robustness and overgeneration. Gemini features a broad-coverage unification-based grammar of English, fully interleaved syntactic and semantic processing in an all-paths, bottom-up parser, and an utterance-level parser to find interpretations of sentences that might not be analyzable as complete sentences. Gemini also includes novel components for recognizing and correcting grammatical disfluencies, and for doing parse preferences. This paper presents a component-by-component view of Gemini, providing detailed relevant measurements of size, efficiency, and performance.

Plan-based integration of natural language and graphics generation

Abstract: Multimodal interfaces combining natural language and graphics take advantage of both the individual strength of each communication mode and the fact that several modes can be employed in parallel. The central claim of this paper is that the generation of a multimodal presentation can be considered as an incremental planning process that aims to achieve a given communicative goal. We describe the multimodal presentation system WIP which allows the generation of alternate presentations of the same content taking into account various contextual factors. We discuss how the plan-based approach to presentation design can be exploited so that graphics generation influences the production of text and vice versa. We show that well-known concepts from the area of natural language processing like speech acts, anaphora, and rhetorical relations take on an extended meaning in the context of multimodal communication. Finally, we discuss two detailed examples illustrating and reinforcing our theoretical claims.

Reframing the Debate: The Roles of Native Languages in English‐Only Programs for Language Minority Students

Abstract: The use of languages other than English in schooling is a subject of great controversy in the U.S., pitting those who hold assimilationist views (favoring English-only) against those who hold cultural pluralist view (favoring inclusion of the native language) (Secada & Lightfoot, 1993). A study of nine exemplary K-12 programs for language minority students in which English was the primary language of instruction showed that the incorporation of students' native languages in instruction need not be an all-or-nothing phenomenon. The use of the native language appears so compelling that it emerges even when policies and assumptions mitigate against it. Teachers who are monolingual English speakers or who do not speak the languages of all their students can incorporate students' native languages into instruction in many ways to serve a variety of educationally desirable functions. This article explores the complexities of the uses of students' native languages in schooling, describes and illustrates various ways these languages were used in the English-based but multilingual programs, and argues that programs for language minority students should be reconceptualized to move beyond the emotional and politically heated debate that opposes English-only instruction to native language instruction. We have been trapped in the past in an endless and often fruitless debate over the best language of instruction. I hope that this reauthorization [of federal education programs for English L2 students] can rise above this tired issue, so that we can turn our attention to more substantive problems—how to provide language minority students with an equal opportunity to learn challenging content and high level skills. (Hakuta, 1993)

Classes d'objets et description des verbes

Abstract: G. Gross : Classes d'objet et description des verbes ; This article aims at clarifying the concept of « object classes » in natural languages and its usefulness in describing verbal predicates. Syntactic features such as human, concrete, abstract are not accurate enough to account for the polysemy of the operators. Object classes can be put to other uses, some of which are outlined here.

A Grammar of Supyire

Abstract: The series builds an extensive collection of high quality descriptions of languages around the world. Each volume offers a comprehensive grammatical description of a single language together with fully analyzed sample texts and, if appropriate, a word list and other relevant information which is available on the language in question. There are no restrictions as to language family or area, and although special attention is paid to hitherto undescribed languages, new and valuable treatments of better known languages are also included. No theoretical model is imposed on the authors; the only criterion is a high standard of scientific quality.

The Speech-Language Interface in the Spoken Language Translator.

Abstract: The Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system translates air travel (ATIS) queries from spoken English to spoken Swedish and to French. It is constructed, with as few modifications as possible, from existing pieces of speech and language processing software. The speech recognizer and language understander are connected by a fairly conventional pipelined N-best interface. This paper focuses on the ways in which the language processor makes intelligent use of the sentence hypotheses delivered by the recognizer. These ways include (1) producing modified hypotheses to reflect the possible presence of repairs in the uttered word sequence; (2) fast parsing with a version of the grammar automatically specialized to the more frequent constructions in the training corpus; and (3) allowing syntactic and semantic factors to interact with acoustic ones in the choice of a meaning structure for translation, so that the acoustically preferred hypothesis is not always selected even if it is within linguistic coverage.

Automatic language identification of telephone speech messages using phoneme recognition and N-gram modeling

Abstract: The paper compares the performance of four approaches to automatic language identification (LID) of telephone speech messages: Gaussian mixture model classification (GMM), language-independent phoneme recognition followed by language-dependent language modeling (PRLM), parallel PRLM (PRLM-P), and language-dependent parallel phoneme recognition (PPR). These approaches span a wide range of training requirements and levels of recognition complexity. All approaches were tested on the development test subset of the OGI multi-language telephone speech corpus. Generally, system performance was directly related to system complexity, with PRLM-P and PPR performing best. On 45 second test utterances, average two language, closed-set, forced-choice classification performance reached 94.5% correct. The best 10 language, closed-set, forced-choice performance was 79.2% correct. >

Natural language vs. Boolean query evaluation: a comparison of retrieval performance

Abstract: The results of experiments comparing the relative performance of natural language and Boolean query formulations are presented. The experiments show that on average a current generation natural language system provides better retrieval performance than expert searchers using a Boolean retrieval system when searching full-text legal materials. Methodological issues are reviewed and the effect of database size on query formulation strategy is discussed.

Language identification using phone-based acoustic likelihoods

Abstract: Applies the technique of phone-based acoustic likelihoods to the problem of language identification. The basic idea is to process the unknown speech signal by language-specific phone model sets in parallel, and to hypothesize the language associated with the model set having the highest likelihood. Using laboratory quality speech the language can be identified as French or English with better than 99% accuracy with only as little as 2 seconds of speech. On spontaneous telephone speech from the OGI corpus, the language can be identified as French or English with 82% accuracy with 10 seconds of speech. The 10 language identification rate using the OGI corpus is 59.7% with 10 seconds of signal. >