Language understanding

The estimation of initial language models for new applications of spoken dialogue systems without large taskspecific training corpora is becoming an increasingly important issue. This paper investigates two different approaches in which the task-specific knowledge contained in the language understanding grammar is exploited in order to generate n-gram language models for the speech recognizer: The first uses class-based language models for which the word-classes are automatically derived from the grammar. In the second approach, language models are estimated on artificial corpora which have been created from the understanding grammar. The application of fill-up techniques allows the combination of the strengths of both approaches and leads to a language model which shows optimal performance regardless of the amount of training data available. Perplexities and word error rates are reported for two different domains.

Working memory (WM) plays a crucial role in learning a second language (L2). The ability to repeat words in an unknown language has been observed to predict success in learning that language. Conversely, decreased digit span and inability to repeat pseudowords have been related with failure in L2 acquisition. Not only digit span, but also ''word span'' and ''semantic span'' should be considered in WM analysis. In addition to the phonological system, a semantic system is proposed in the WM model for language. In bilinguals, brain activation patterns during WM tasks have been observed to be more complex when using a L2. Processing information in L2 is more demanding, and WM may be less efficient. It can be conjectured that language understanding defects in L2 are at least partially due to this decreased efficiency of WM in its phonological as well as in its semantic subsystem. Learning outcomes: The reader will be introduced to the basic assumptions of WM. It will be emphasized that WM is significantly involved in the ability to learn a L2. Cross-linguistic differences in digit span will be analyzed. It will be concluded that despite digit span and word span are affected by different variables, ''semantic span'' may be similar across languages. Words in a L2 function as low frequency words, and hence, semantic search takes longer and WM is less efficient. It will be concluded that in addition to the ''phonological system,'' the WM model should include a ''semantic system,'' involving a ''semantic store'' and a ''semantic search'' process. #

We describe a comprehensive framework for narrative understanding based on Episodic Logic (EL). This situational logic was developed and implemented as a semantic representation and commonsense knowledge representation that would serve the full range of interpretive and inferential needs of general NLU. The most distinctive feature of EL is its natural language-like expressiveness. It allows for generalized quantifiers, lambda abstraction,

Lip reading provides useful information in speech perception and language understanding, especially when the auditory speech is degraded. However, many current automatic lip reading systems impose some restrictions on users. In this paper, we present our research efforts in the Interactive System Laboratory, towards unrestricted lip reading. We first introduce a top–down approach to automatically track and extract lip regions. This technique makes it possible to acquire visual information in real-time without limiting the user's freedom of movement. We then discuss normalization algorithms to preprocess images for different lightning conditions (global illumination and side illumination). We also compare different visual preprocessing methods such as raw image, Linear Discriminant Analysis (LDA), and Principle Component Analysis (PCA). We demonstrate the feasibility of the proposed methods by the development of a modular system for flexible human–computer interaction via both vi...

The proper interpretation of prepositions is an important issue for automatic natu- ral language understanding. We present an approach towards PP interpretation as part of a natural language understanding system which has been successfully em- ployed in various NLP tasks for informa- tion retrieval and question answering. Our approach is based on the so-called Multi- Net paradigm, a knowledge representation

We report on a fuzzy logic-based language understanding system applied to speech recognition. This system acquires conceptual knowledge from corpus data and organizes such knowledge into fuzzy logic inference rules. The system parses speech recognition results into conceptual structures in a robust manner, and thus is able to tolerate noise caused by speech recognition errors. We discuss the fuzzy inference rule learning method and explain its organization. Experimental results that demonstrate the ability of the system to deal with complex speech input instances are reported

The aim of the present study was to investigate idiom comprehension in school-age Italian children with different reading comprehension skills. According to our hypothesis, the level of a childÕs text comprehension skills should predict his/her ability to understand idiomatic meanings. Idiom comprehension in fact requires children to go beyond a simple word-by-word comprehension strategy and to integrate figurative meaning into contextual information. In a preliminary phase, we used a standardized battery of tests to assess the ability of second graders and fourth graders to comprehend written texts. Three groups were identified at each age level: good, medium, and poor comprehenders. Children were then presented with familiar idiomatic expressions which also have a literal meaning (e.g., ''break the ice''). Idioms were embedded in short stories: in Experiment 1 only the idiomatic interpretation was contextually appropriate, in Experiment 2 a literal reading of the string was also plausible in the context. A multiple-choice task was used in both experiments: children were asked to choose one answer among three corresponding to: (a) the idiomatic meaning; (b) the literal meaning; and (c) an interpretation contextually appropriate but not connected with the idiomatic or literal meaning of the idiom string. The results of both experiments showed that the ability to understand a text indeed predicted childrenÕs understanding of idioms in context. To verify whether possible improvements in childrenÕs comprehension skills might produce an increase in figurative language understanding, Experiment 3 was carried out. A group of poor comprehenders who participated in Experiments 1 and 2 was tested eight months later. The results of Experiment 3 showed that children whose general comprehension skills improved their performance on an idiom comprehension test.

The study of processes underlying the interpretation of language often produces evidence that they are complete and occur incrementally. However, computational linguistics has shown that interpretations are often effective even if they are underspecified. We present evidence that similar underspecified representations are used by humans during comprehension, drawing on a scattered and varied literature. We also show how linguistic properties of focus, subordination and focalization can control depth of processing, leading to underspecified representations. Modulation of degrees of specification might provide a way forward in the development of models of the processing underlying language understanding.

We present a natural-language customer service application for a telephone banking call center, developed as part of the AMITIÉS dialogue project (Automated Multilingual Interaction with Information and Services). Our dialogue system, based on empirical data gathered from real call-center conversations, features data-driven techniques that allow for spoken language understanding despite speech recognition errors, as well as mixed system/customer initiative and spontaneous conversation.

Simulating human language understanding on the computer is a great challenge. A way to approach it is to represent natural language meanings in logic, and to use logical provers to determine what does and does not follow from a text. What logic is best to use and how natural language meanings are best represented in it are far from trivial questions. This thesis focuses on semantic representation in deep parsing. It describes the Delilah parser and generator for Dutch, which computes semantic representations for sentences, discussing several issues and proposing some further improvements to the system. A style of logical form is developed that is optimized for inference in mainly two ways. One is the implementation of event semantics for verbs and nominalizations and with underlying states for intersective adjectives and their corresponding abstract nouns. This makes many entailments follow straightforwardly. The second is the introduction of Flat Logical Form, as an alternative to ...

and-conditions-of-access.pdf This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, redistribution , reselling , loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material.

The utility of formal theories of commonsense reasoning will depend both on their competency in solving problems and on their conceptual coverage. We argue that the problems of coverage and competency can be decoupled and solved with different methods for a given commonsense domain. We describe a methodology for identifying the coverage requirements of theories through the large-scale analysis of planning strategies, with further refinements made by collecting and categorizing instances of natural language expressions pertaining to the domain. We demonstrate the effectiveness of this methodology in identifying the representational coverage requirements of theories of the commonsense psychology of human memory. We then apply traditional methods of formalization to produce a formal first-order theory of commonsense memory with a high degree of competency and coverage.

Özet: Birden fazla anlama sahip herhangi bir sözcüğün tümce içerisindeki yeri önemli olmaksizin, hangi anlamda olduğu ile ilgili genellikle bir belirsizlik mevcuttur. Kişi, anlam belirsizliği olan bir tümceyi anladiği zaman belirsizliğe neden olan sözcüğün diğer anlamlarini elemiş, sadece bir anlamini göz önüne almiştir. İnsanoğlu anlama işlemini gerçekleştiren bilişsel bir sisteme sahip olduğu için, belirsizlik içeren bir tümcenin anlaşilmasi insan dil

This paper evaluates qualitatively the use of the MedLEE natural language processing system to code medical narratives directly into the SNOMED nomenclature, while retaining the MedLEE information model data structure. A gold standard is produced from narrative text manually coded in SNOMED. An automated parsing and SNOMED-coding of the narrative text is then automatically generated by MedLEE. By comparing MedLEE s output to that of the Gold Standard, the capacities of SNOMED and MedLEE to represent the clinical information are subsequently evaluated leading to qualitative observations on their respective strengths and constraints. In this study, MedLEE did code to SNOMED and captures the codes in a sub-structure amenable to interoperability with the description logic of SNOMED RT, showing an approach that augments and formalizes SNOMED s compositional representation methods to accurately capture information from clinical narratives.

This paper addresses the problem of Computer-Aided Speech and Language Therapy (CASLT). The goal of the work described in the paper is to develop and evaluate a semi-automated system for providing interactive speech therapy to the increasing population of impaired individuals and help professional speech therapists. A discussion on the development and evaluation of a set of interactive therapy tools, along with the underlying speech technologies that support these tools is provided. The interactive tools are designed to facilitate the acquisition of language skills in the areas of basic phonatory skills, phonetic articulation and language understanding primarily for children with neuromuscular disorders like dysarthria. Human-machine interaction for all of these areas requires the existence of speech analysis, speech recognition, and speech verification algorithms that are robust with respect to the sources of speech variability that are characteristic of this population of speakers. The paper will present an experimental study that demonstrates the effectiveness of an interactive system for eliciting speech from a population of impaired children and young speakers ranging in age from 11 to 21 years. The performance of automatic speech recognition (ASR) systems and subword-based pronunciation verification (PV) on this domain are also presented. The results indicate that ASR and PV systems configured from speech utterances taken from the impaired speech domain can provide adequate performance, similar to the experts' agreement rate, for supporting the presented CASLT applications.

Özet: Birden fazla anlama sahip herhangi bir sözcüğün tümce içerisindeki yeri önemli olmaksızın, hangi anlamda olduğu ile ilgili genellikle bir belirsizlik mevcuttur. Kişi, anlam belirsizliği olan bir tümceyi anladığı zaman belirsizliğe neden olan sözcüğün diğer anlamlarını elemiş, sadece bir anlamını göz önüne almıştır. İnsanoğlu anlama işlemini gerçekleştiren bilişsel bir sisteme sahip olduğu için, belirsizlik içeren bir tümcenin anlaşılması insan dil anlama sisteminde olası anlam kümesi içinden uygun anlamın seçilmesidir. Bu belirsizlik durumunun sözcüğün uygulanma şekline göre uygun algoritmaların kullanılması ile çözümlenmesi doğal dil işlemleme alanındaki çalışmalarla başlamış, hesaplamalı dilbilim çalışmalarının yaygınlaşması ile daha da önem kazanmıştır. Sözcük anlamlarının belirginleştirilmesi çalışmaları, dilin doğasını inceleyen dilbilim çalışmaları, metin veya konuşmaların çevirisinin yapıldığı bilgisayarlı çeviri sistemleri, bilgi yönetimi teknolojisi olarak kullanılan bilgi geri getirimi ve çıkarımı, İnternet üzerinde arama motorlarının tasarımı gibi çok geniş uygulama alanına sahiptir.

Embodied theories of conceptual knowledge suggest that sensory-motor representations of actions similar to those involved in the performance of the action described are recruited during language comprehension. The extent of this recruitment, however, and the brain mechanisms supporting this process remain unknown. Using fMRI, we investigated these issues by examining how people understand sentences that convey three different degrees of physical effort and by comparing this process to action execution. To understand the effort implied by the stimulus sentences, object and action properties associated with nouns and verbs respectively needed to be integrated: pushing the piano implies more physical effort than pushing the chair. Results indicated that a pre-motor region, which was also active in action execution, was sensitive to the degree of effort implied by the language. Interestingly, the anterior inferior frontal gyrus, a region typically associated with semantic processing, was not active in action execution but was nevertheless modulated by the effort implied. Inter-region correlations also suggested that this region was strongly correlated with premotor and posterior temporal regions. Overall, results suggest that (a) language understanding elicits action representations retaining a degree of specificity that was previously unsuspected, including unique properties of interactions with objects, and (b) these representations, which result from integrating the words' semantic information, may be computed within a collaborative neural network that includes the anterior inferior frontal gyrus.

Doherty and Perner (Metalinguistic awareness and theory of mind: just two words for the same thing? Cognitive Development, 13 (1998), 279±305) report that children's understanding of synonyms and false belief is dependent on an understanding of the representational mind. Experiment 1 extends this finding by examining children's understanding of homonyms. Children aged 3 and 4 years were asked to judge whether a puppet correctly selected the second member of a homonym pair. Performance on this task was strongly associated with performance on the false belief task even after chronological and verbal mental age had been accounted for. Experiment 2 incorporated two new tasks: a synonyms task and an adjectives task. Understanding of synonyms and homonyms significantly predicted performance on the false belief task. However, once chronological age was accounted for, only performance on the homonyms task did so. The difficulty experienced on the homonyms task was not due to a reluctance to acknowledge that the puppet can point to a different picture when the the same word label is used twice. Children had no difficulty on the adjectives task when the puppet had to point to a different picture described using the same adjective. The suggestion that the understanding of synonyms, homonyms and false belief are related by a common insight into the representational mind is therefore not supported.

Özet: Birden fazla anlama sahip herhangi bir sözcüğün tümce içerisindeki yeri önemli olmaksızın, hangi anlamda olduğu ile ilgili genellikle bir belirsizlik mevcuttur. Kişi, anlam belirsizliği olan bir tümceyi anladığı zaman belirsizliğe neden olan sözcüğün diğer anlamlarını elemiş, sadece bir anlamını göz önüne almıştır. İnsanoğlu anlama işlemini gerçekleştiren bilişsel bir sisteme sahip olduğu için, belirsizlik içeren bir tümcenin anlaşılması insan dil anlama sisteminde olası anlam kümesi içinden uygun anlamın seçilmesidir. Bu belirsizlik durumunun sözcüğün uygulanma şekline göre uygun algoritmaların kullanılması ile çözümlenmesi doğal dil işlemleme alanındaki çalışmalarla başlamış, hesaplamalı dilbilim çalışmalarının yaygınlaşması ile daha da önem kazanmıştır. Sözcük anlamlarının belirginleştirilmesi çalışmaları, dilin doğasını inceleyen dilbilim çalışmaları, metin veya konuşmaların çevirisinin yapıldığı bilgisayarlı çeviri sistemleri, bilgi yönetimi teknolojisi olarak kullanılan bilgi geri getirimi ve çıkarımı, İnternet üzerinde arama motorlarının tasarımı gibi çok geniş uygulama alanına sahiptir.

This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs are noise-tolerant, and facilitate the training of M+. 1

One of the most important methods by which human beings learn is by reading. While in its full generality, the reading task is still too difficult a capability to be implemented in a computer, significant (if partial) approaches to the task are now feasible. Our goal in this ...

We introduce the second of 2 special issues of Ecological Psychology that present papers from a conference, “Grounding Language in Perception and (Inter)action,” held at Gordon College in June 2009. The articles in this issue situate the study of language use in two kinds of context that are central to an understanding of “languaging” activities in the social settings in which they occur. The first is the context of dynamical systems theory. Wallot and Van Orden show how a dynamical systems approach can illuminate language use as the intentional and creative activity that it is. Cowley and Thibault illustrate the distributed language approach. Cowley follows Gibson (1979/1986) in comparing language understanding to picture perception. Thibault illustrates the wholly embedded nature of language use in an evocative example of 2 boys offering a description of aliens they have learned about in a story. All of the contributors emphasize language as embodied social action deeply embedded in the social contexts of talking. The articles in this issue and its predecessor, Ecological Psychology 22(4), offer valuable insights for development of an ecological theory of language use.

One of the most important methods by which human beings learn is by reading. While in its full generality, the reading task is still too difficult a capability to be implemented in a computer, significant (if partial) approaches to the task are now feasible. Our goal in this ...

Digital video is rapidly becoming an important source for information, entertainment and a host of multimedia applications. With the size of these collections growing to thousands of hours, technology is needed to effectively browse segments in a short time without losing the content of the video. We propose a method to extract the significant audio and video information and create a "skim" video which represents a short synopsis of the original. The extraction of significant information, such as specific objects, audio keywords and relevant video structure, is made possible through the integration of techniques in image and language understanding. The resulting skim is much smaller, and retains the essential content of the original segment. 0

This paper has two aims: (1) to generalize a computational account of discourse processing called CENTERING and apply it to discourse processing in Japanese, and (2) to provide some insights on the effect of syntactic factors in Japanese on discourse interpretation. We argue that while discourse interpretation is an inferential process, the syntactic cues constrain this process, and demonstrate this argument with respect to the interpretation of ZEROS, unexpressed arguments of the verb, in Japanese. The syntactic cues in Japanese discourse that we investigate are the morphological markers for grammatical TOPIC, the post-position wa, as well as those for grammatical functions such as SUBJECT, ga, OBJECT, o and OBJECT2, ni. In addition, we investigate the role of speakers' EMPATHY, which is the perspective from which an event is described. This is morphologically indicated through the use of verbal compounding, i.e. the auxiliary use of verbs such as kureta, kita. Our results are based on a survey of native speakers of their interpretation of short discourses, consisting of minimal pairs, varied by one of the above factors. We demonstrate that these syntactic cues do indeed affect the interpretation of ZEROS, but that having previously been the TOPIC and being realized as a ZERO also contribute to an entity being interpreted as the TOPIC. We propose a new notion of TOPIC AMBIGUITY, and show that CENTERING provides constraints on when a ZERO can be interpreted as the TOPIC.

This paper has three aims: (1) to generalize a compulational account of the discourse process called CENTERING, (2) to apply this account to discourse processing in Japanese so that it can be used in computational systems for machine translation or language understanding, and (3) to provide some insights on the effect of syntactic factors in Japanese on discourse interpretation. We argue that while discourse interpretation is an inferential process, syntactic cues constrain this process; we demonstrate this argument with respect to the interpretation of ZEROS, unexpressed arguments of the verb, in Japanese. The syntactic cues in Japanese discourse that we investigate are the morphological markers for grammatical TOPIC, the postposition wa, as well as those for grammatical functions such as SUBJECT, ga, OBJECT, o and OBJECT2, ni. In addition, we investigate the role of speaker's EMPATHY, which is the viewpoint from which an event is described. This is syntactically indicated thro...

We do things in the world by exploiting our knowledge of what causes what. But in trying to reason formally about causality, there is a difficulty: to reason with certainty we need complete knowledge of all the relevant events and circumstances, whereas in everyday reasoning tasks we need a more serviceable but looser notion that does not make such demands on our knowledge. In this work the notion of "causal complex" is introduced for a complete set of events and conditions necessary for the causal consequent to occur, and the term "cause" is used for the makeshift, nonmonotonic notion we require for everyday tasks such as planning and language understanding. Like all interesting concepts, neither of these can be defined with necessary and sufficient conditions, but they can be more or less tightly constrained by necessary conditions or sufficient conditions. The issue of how to distinguish between what is in a causal complex from what is outside it is discussed, and within a causal complex, how to distinugish the eventualities that deserve to be called "causes" from those that do not, in particular circumstances. One particular modal, the word "would", is examined from the standpoint of its underlying causal content, as a linguistic motivation for this enterprise.

While it has recently become possible to build spoken dialogue systems that interact with users in real-time in a range of domains, systems that support conversational natural language are still subject to a large number of spoken language understanding (SLU) errors. Endowing such systems with the ability to reliably distinguish SLU errors from correctly understood utterances might allow them to correct some errors automatically or to interact with users to repair them, thereby improving the system's overall performance. We report experiments on learning to automatically distinguish SLU errors in 11,787 spoken utterances collected in a field trial of AT&T's How May I Help You system interacting with live customer traffic. We apply the automatic classifier RIPPER (Cohen 96) to train an SLU classifier using features that are automatically obtainable in real-time. The classifer achieves 86% accuracy on this task, an improvement of 23% over the majority class baseline. We show that the most important features are those that the natural language understanding module can compute, suggesting that integrating the trained classifier into the NLU module of the How May I Help You system should be straightforward. ¡ The phone numbers, card numbers, and pin numbers in the sample dialogues are artificial.

Intelligent tasks, such as visual perception, auditory perception, and language understanding require the construction of good internal representations of the world (or "features"), which must be invariant to irrelevant variations of the input while, preserving relevant information. A major question for Machine Learning is how to learn such good features automatically. Convolutional Networks (ConvNets) are a biologicallyinspired trainable architecture that can learn invariant features. Each stage in a ConvNets is composed of a filter bank, some non-linearities, and feature pooling layers. With multiple stages, a ConvNet can learn multi-level hierarchies of features. While ConvNets have been successfully deployed in many commercial applications from OCR to video surveillance, they require large amounts of labeled training samples. We describe new unsupervised learning algorithms, and new non-linear stages that allow ConvNets to be trained with very few labeled samples. Applications to visual object recognition and vision navigation for off-road mobile robots are described.

This paper has three aims: (1) to generalize a computational account of the discourse process called {\sc centering}, (2) to apply this account to discourse processing in Japanese so that it can be used in computational systems for machine translation or language understanding, and (3) to provide some insights on the effect of syntactic factors in Japanese on discourse interpretation. We argue that while discourse interpretation is an inferential process, syntactic cues constrain this process, and demonstrate this argument with respect to the interpretation of {\sc zeros}, unexpressed arguments of the verb, in Japanese. The syntactic cues in Japanese discourse that we investigate are the morphological markers for grammatical {\sc topic}, the postposition {\it wa}, as well as those for grammatical functions such as {\sc subject}, {\em ga}, {\sc object}, {\em o} and {\sc object2}, {\em ni}. In addition, we investigate the role of speaker's {\sc empathy}, which is the viewpoint from which an event is described. This is syntactically indicated through the use of verbal compounding, i.e. the auxiliary use of verbs such as {\it kureta, kita}. Our results are based on a survey of native speakers of their interpretation of short discourses, consisting of minimal pairs, varied by one of the above factors. We demonstrate that these syntactic cues do indeed affect the interpretation of {\sc zeros}, but that having previously been the {\sc topic} and being realized as a {\sc zero} also contributes to the salience of a discourse entity. We propose a discourse rule of {\sc zero topic assignment}, and show that {\sc centering} provides constraints on when a {\sc zero} can be interpreted as the {\sc zero topic}.

This paper has two aims: (1) to generalize a computational account of discourse processing called CENTERING and apply it to discourse processing in Japanese, and (2) to provide some insights on the effect of syntactic factors in Japanese on discourse interpretation. We argue that while discourse interpretation is an inferential process, the syntactic cues constrain this process, and demonstrate this argument with respect to the interpretation of ZEROS, unexpressed arguments of the verb, in Japanese. The syntactic cues in Japanese discourse that we investigate are the morphological markers for grammatical TOPIC, the post-position wa, as well as those for grammatical functions such as SUBJECT, ga, OBJECT, o and OBJECT2, ni. In addition, we investigate the role of speakers' EMPATHY, which is the perspective from which an event is described. This is morphologically indicated through the use of verbal compounding, i.e. the auxiliary use of verbs such as kureta, kita. Our results are based on a survey of native speakers of their interpretation of short discourses, consisting of minimal pairs, varied by one of the above factors. We demonstrate that these syntactic cues do indeed affect the interpretation of ZEROS, but that having previously been the TOPIC and being realized as a ZERO also contribute to an entity being interpreted as the TOPIC. We propose a new notion of TOPIC AMBIGUITY, and show that CENTERING provides constraints on when a ZERO can be interpreted as the TOPIC.

This study investigates the relationship of theory of mind and inhibitory control in three samples from Europe, Africa and Latin America differing in relevant socioeconomic and psychological background. The relationship between false belief understanding and inhibitory control was tested using samples of 3-to 5-year-old preschoolers from Germany (N = 116), Costa Rica (N = 82) and Cameroon (N = 116). Inhibitory control and theory of mind were examined using test batteries. Age, gender, siblings, language understanding and mother's education were controlled. Results of regression analyses controlling for moderating effects of culture show a culture-independent relation between conflict inhibition and false belief understanding while delay inhibition is not a significant predictor for false belief understanding across cultures. Conflict inhibition is discussed as a universal developmental prerequisite for the development of theory of mind in the preschool years.

We introduce the second of 2 special issues of Ecological Psychology that present papers from a conference, “Grounding Language in Perception and (Inter)action,” held at Gordon College in June 2009. The articles in this issue situate the study of language use in two kinds of context that are central to an understanding of “languaging” activities in the social settings in which they occur. The first is the context of dynamical systems theory. Wallot and Van Orden show how a dynamical systems approach can illuminate language use as the intentional and creative activity that it is. Cowley and Thibault illustrate the distributed language approach. Cowley follows Gibson (1979/1986) in comparing language understanding to picture perception. Thibault illustrates the wholly embedded nature of language use in an evocative example of 2 boys offering a description of aliens they have learned about in a story. All of the contributors emphasize language as embodied social action deeply embedded ...

A recently emerging view sees language understanding as closely linked to sensory and motor processes. The present study investigates this issue by examining the influence of processing action verbs and concrete nouns on the execution of a reaching movement. Fine-grained analyses of movement kinematics revealed that relative to nouns, processing action verbs significantly affect overt motor performance. Within 200 ms following onset, processing action verbs interferes with a concurrent reaching movement. By contrast, the same words assist reaching movement when processed prior to movement onset. The cross-talk between language processes and overt motor behavior provides unambiguous evidence that action words and motor action share common cortical representations and could thus suggest that cortical motor regions are indeed involved in action word retrieval.

We describe the rst sentence understanding system that is completely based on learned methods both for understanding individual sentences, and determinig their meaning in the context of preceding sentences. We describe the models used for each of three stages in the understanding: semantic parsing, semantic classication, and discourse modeling. When we ran this system on the last test (December, 1994) of the ARPA Air Travel Information System (ATIS) task, we achieved 14.5% error rate. The error rate for those sentences that are context-independent (class A) was 9.5%.

Many intelligent agents need knowledge and information to support their reasoning and problem solving. The World Wide Web is a vast, open, accessible and free source of knowledge, but virtually all of it is encoded as natural language text–a form difficult for most agents to directly understand. We describe initial work on adapting a mature language understanding agent to process Web text and publish its output in the Semantic Web language OWL. This approach adds knowledge on the Web in a form designed for agents ...

This paper addresses the problem of Computer-Aided Speech and Language Therapy (CASLT). The goal of the work described in the paper is to develop and evaluate a semi-automated system for providing interactive speech therapy to the increasing population of impaired individuals and help professional speech therapists. A discussion on the development and evaluation of a set of interactive therapy tools, along with the underlying speech technologies that support these tools is provided. The interactive tools are designed to facilitate the acquisition of language skills in the areas of basic phonatory skills, phonetic articulation and language understanding primarily for children with neuromuscular disorders like dysarthria. Human-machine interaction for all of these areas requires the existence of speech analysis, speech recognition, and speech verification algorithms that are robust with respect to the sources of speech variability that are characteristic of this population of speakers. The paper will present an experimental study that demonstrates the effectiveness of an interactive system for eliciting speech from a population of impaired children and young speakers ranging in age from 11 to 21 years. The performance of automatic speech recognition (ASR) systems and subword-based pronunciation verification (PV) on this domain are also presented. The results indicate that ASR and PV systems configured from speech utterances taken from the impaired speech domain can provide adequate performance, similar to the experts' agreement rate, for supporting the presented CASLT applications.

Although people with autism spectrum disorders (ASD) often have severe problems with pragmatic aspects of language, little is known about their pragmatic reasoning. We carried out a behavioral study on highfunctioning adults with autistic disorder (n = 11) and Asperger syndrome (n = 17) and matched controls (n = 28) to investigate whether they are capable of deriving scalar implicatures, which are generally considered to be pragmatic inferences. Participants were presented with underinformative sentences like ''Some sparrows are birds''. This sentence is logically true, but pragmatically inappropriate if the scalar implicature ''Not all sparrows are birds'' is derived. The present findings indicate that the combined ASD group was just as likely as controls to derive scalar implicatures, yet there was a difference between participants with autistic disorder and Asperger syndrome, suggesting a potential differentiation between these disorders in pragmatic reasoning. Moreover, our results suggest that verbal intelligence is a constraint for task performance in autistic disorder but not in Asperger syndrome.

The Air Travel Information System (ATIS) domain serves as the common task for DARPA spoken language system research and development. The approaches and results possible in this rapidly growing area are structured by available corpora, annotations of that data, and evaluation methods. Coordination of this crucial infrastructure is the charter of the Multi-Site ATIS Data COllection Working group (MAD-COW). We focus here on selection of training and test data, evaluation of language understanding, and the continuing search for evaluation methods that will correlate well with expected performance of the technology in applications.