Showing papers on "Utterance published in 2011"

Identifying Sarcasm in Twitter: A Closer Look

Abstract: Sarcasm transforms the polarity of an apparently positive or negative utterance into its opposite. We report on a method for constructing a corpus of sarcastic Twitter messages in which determination of the sarcasm of each message has been made by its author. We use this reliable corpus to compare sarcastic utterances in Twitter to utterances that express positive or negative attitudes without sarcasm. We investigate the impact of lexical and pragmatic factors on machine learning effectiveness for identifying sarcastic utterances and we compare the performance of machine learning techniques and human judges on this task. Perhaps unsurprisingly, neither the human judges nor the machine learning techniques perform very well.

Spoken Language Understanding: Systems for Extracting Semantic Information from Speech

Abstract: List of Contributors. Forward. Preface. 1 Introduction (Gokhan Tur and Renato De Mori). 1.1 A Brief History of Spoken Language Understanding. 1.2 Organization of the Book. PART 1 SPOKEN LANGUAGE UNDERSTANDING FOR HUMAN/MACHINE INTERACTIONS. 2 History of Knowledge and Processes for Spoken Language Understanding (Renato De Mori). 2.1 Introduction. 2.2 Meaning Representation and Sentence Interpretation. 2.3 Knowledge Fragments and Semantic Composition. 2.4 Probabilistic Interpretation in SLU Systems. 2.5 Interpretation with Partial Syntactic Analysis. 2.6 Classification Models for Interpretation. 2.7 Advanced Methods and Resources for Semantic Modeling and Interpretation. 2.8 Recent Systems. 2.9 Conclusions. References. 3 Semantic Frame-based Spoken Language Understanding (Ye-Yi Wang, Li Deng and Alex Acero). 3.1 Background. 3.2 Knowledge-based Solutions. 3.3 Data-driven Approaches. 3.4 Summary. References. 4 Intent Determination and Spoken Utterance Classification (Gokhan Tur and Li Deng). 4.1 Background. 4.2 Task Description. 4.3 Technical Challenges. 4.4 Benchmark Data Sets. 4.5 Evaluation Metrics. 4.6 Technical Approaches. 4.7 Discussion and Conclusions. References. 5 Voice Search (Ye-Yi Wang, Dong Yu, Yun-Cheng Ju and Alex Acero). 5.1 Background. 5.2 Technology Review. 5.3 Summary. References. 6 Spoken Question Answering (Sophie Rosset, Olivier Galibert and Lori Lamel). 6.1 Introduction. 6.2 Specific Aspects of Handling Speech in QA Systems. 6.3 QA Evaluation Campaigns. 6.4 Question-answering Systems. 6.5 Projects Integrating Spoken Requests and Question Answering. 6.6 Conclusions. References. 7 SLU in Commercial and Research Spoken Dialogue Systems (David Suendermann and Roberto Pieraccini). 7.1 Why Spoken Dialogue Systems (Do Not) Have to Understand. 7.2 Approaches to SLU for Dialogue Systems. 7.3 From Call Flow to POMDP: How Dialogue Management Integrates with SLU. 7.4 Benchmark Projects and Data Sets. 7.5 Time is Money: The Relationship between SLU and Overall Dialogue System Performance. 7.6 Conclusion. References. 8 Active Learning (Dilek Hakkani-Tur and Giuseppe Riccardi). 8.1 Introduction. 8.2 Motivation. 8.3 Learning Architectures. 8.4 Active Learning Methods. 8.5 Combining Active Learning with Semi-supervised Learning. 8.6 Applications. 8.7 Evaluation of Active Learning Methods. 8.8 Discussion and Conclusions. References. PART 2 SPOKEN LANGUAGE UNDERSTANDING FOR HUMAN/HUMAN CONVERSATIONS. 9 Human/Human Conversation Understanding (Gokhan Tur and Dilek Hakkani-Tur). 9.1 Background. 9.2 Human/Human Conversation Understanding Tasks. 9.3 Dialogue Act Segmentation and Tagging. 9.4 Action Item and Decision Detection. 9.5 Addressee Detection and Co-reference Resolution. 9.6 Hot Spot Detection. 9.7 Subjectivity, Sentiment, and Opinion Detection. 9.8 Speaker Role Detection. 9.9 Modeling Dominance. 9.10 Argument Diagramming. 9.11 Discussion and Conclusions. References. 10 Named Entity Recognition (Frederic Bechet). 10.1 Task Description. 10.2 Challenges Using Speech Input. 10.3 Benchmark Data Sets, Applications. 10.4 Evaluation Metrics. 10.5 Main Approaches for Extracting NEs from Text. 10.6 Comparative Methods for NER from Speech. 10.7 New Trends in NER from Speech. 10.8 Conclusions. References. 11 Topic Segmentation (Matthew Purver). 11.1 Task Description. 11.2 Basic Approaches, and the Challenge of Speech. 11.3 Applications and Benchmark Datasets. 11.4 Evaluation Metrics. 11.5 Technical Approaches. 11.6 New Trends and Future Directions. References. 12 Topic Identification (Timothy J. Hazen). 12.1 Task Description. 12.2 Challenges Using Speech Input. 12.3 Applications and Benchmark Tasks. 12.4 Evaluation Metrics. 12.5 Technical Approaches. 12.6 New Trends and Future Directions. References. 13 Speech Summarization (Yang Liu and Dilek Hakkani-Tur). 13.1 Task Description. 13.2 Challenges when Using Speech Input. 13.3 Data Sets. 13.4 Evaluation Metrics. 13.5 General Approaches. 13.6 More Discussions on Speech versus Text Summarization. 13.7 Conclusions. References. 14 Speech Analytics (I. Dan Melamed and Mazin Gilbert) 14.1 Introduction. 14.2 System Architecture. 14.3 Speech Transcription. 14.4 Text Feature Extraction. 14.5 Acoustic Feature Extraction. 14.6 Relational Feature Extraction. 14.7 DBMS. 14.8 Media Server and Player. 14.9 Trend Analysis. 14.10 Alerting System. 14.11 Conclusion. References. 15 Speech Retrieval (Ciprian Chelba, Timothy J. Hazen, Bhuvana Ramabhadran and Murat Saraclar). 15.1 Task Description. 15.2 Applications. 15.3 Challenges Using Speech Input. 15.4 Evaluation Metrics. 15.5 Benchmark Data Sets. 15.6 Approaches. 15.7 New Trends. 15.8 Discussion and Conclusions. References. Index.

Chameleons in Imagined Conversations: A New Approach to Understanding Coordination of Linguistic Style in Dialogs

Abstract: Conversational participants tend to immediately and unconsciously adapt to each other's language styles: a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their partner's immediately preceding utterance. This striking level of coordination is thought to have arisen as a way to achieve social goals, such as gaining approval or emphasizing difference in status. But has the adaptation mechanism become so deeply embedded in the language-generation process as to become a reflex? We argue that fictional dialogs offer a way to study this question, since authors create the conversations but don't receive the social benefits (rather, the imagined characters do). Indeed, we find significant coordination across many families of function words in our large movie-script corpus. We also report suggestive preliminary findings on the effects of gender and other features; e.g., surprisingly, for articles, on average, characters adapt more to females than to males.

EasyAlign: an automatic phonetic alignment tool under Praat

Abstract: We provide a user-friendly automatic phonetic alignment tool for continuous speech, named EasyAlign. It is developed as a plug-in of Praat, the popular speech analysis software, and it is freely available. Its main advantage is that one can easily align speech from an orthographic transcription. It requires a few minor manual steps and the result is a multi-level annotation within a TextGrid composed of phonetic, syllabic, lexical and utterance tiers. Evaluation showed that the performances of this HTK-based aligner compare to human alignment and to other existing alignment tools. It was originally fully available for French, English. Community’s interests for its extension to other languages helped to develop a straight-forward methodology to add languages. While Spanish and Taiwan Min were recently added, other languages are under development.

Discourse representation theory

Abstract: Discourse Representation Theory, or DRT, is one of a number of theories of dynamic semantics, which have come upon the scene in the course of the past twenty years. The central concern of these theories is to account for the context dependence of meaning. It is a ubiquitous feature of natural languages that utterances are interpretable only when the interpreter takes account of the contexts in which they are made – utterance meaning depends on context. Moreover, the interaction between context and utterance is reciprocal.

Word-level correction of speech input

Abstract: A computer-implemented method comprising: providing a transcription of an utterance for presentation in an area of a display of a computing device; receiving a user selection of at least one word of the transcription of the utterance; in response to receiving the user selection of the at least one word of the transcription of the utterance, presenting at the display of the computing device one or more of: (i) one or more alternate words for the user-selected at least one word of the transcription of the utterance and (ii) a remove control to remove the user-selected at least one word of the transcription of the utterance from the transcription of the utterance; receiving a user selection of the remove control or an alternate word from among the one or more alternate words; and updating the transcription of the utterance presented in the area of the display of the computing device based at least on the user selection. A system and computer program are also described.

Enhanced speech-to-speech translation system and methods

Abstract: A speech translation system and methods for cross-lingual communication that enable users to improve and modify content and usage of the system and easily abort or reset translation. The system includes a speech recognition module configured for accepting an utterance, a machine translation module, an interface configured to communicate the utterance and proposed translation, a correction module and an abort action unit that removes any hypotheses or partial hypotheses and terminates translation. The system also includes modules for storing favorites, changing language mode, automatically identifying language, providing language drills, viewing third party information relevant to conversation, among other things.

Belief tracking and action selection in spoken dialog systems

Abstract: An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.

Quantity implicatures, exhaustive interpretation, and rational conversation

Abstract: Quantity implicatures are inferences triggered by an utterance based on what other utterances a speaker could have made instead. Using ideas and formalisms from game theory, I demonstrate that these inferences can be explained in a strictly Gricean sense as *rational behavior*. To this end, I offer a procedure for constructing the context of utterance insofar as it is relevant for quantity reasoning as a game between speaker and hearer. I then give a new solution concept that improves on classical equilibrium approaches in that it uniquely selects the desired "empirically correct" play in these interpretation games by a chain of back-and-forth reasoning about players' behavior. To make this formal approach more accessible to a wider audience, I give a simple algorithm with the help of which the model's solution can be computed without having to do heavy calculations of probabilities, expected utilities and the like. This rationalistic approach subsumes and improves on recent exhaustivity-based approaches. It makes correct and uniform predictions for quantity implicatures of various epistemic varieties, free choice readings of disjunctions, as well as a phenomenon tightly related to the latter, namely so-called "simplification of disjunctive antecedents". doi:10.3765/sp.4.1 BibTeX info

The relation between teacher input and lexical growth of preschoolers.

Abstract: The present study examined the growth of receptive lexical skills in preschoolers over an academic year in relation to teacher speech. The participating students were English language learners and their monolingual English-speaking peers from the same classrooms. The measures of teacher input included indicators of the amount of speech (total number of words), lexical richness (number of different word types), and structural complexity (number of words per utterance). These measures were based on a speech sample collected during a classroom observation. For English language learners, vocabulary growth was positively related to the total number of words produced by the teacher, but negatively related to the number of words per utterance. For monolingual speakers, vocabulary growth was positively related to the number of word types produced by the teacher. The findings underscore the importance of considering different aspects of verbal input for understanding individual variability in language growth of preschool students.

System and method for machine-mediated human-human conversation

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing speech. A system configured to practice the method monitors user utterances to generate a conversation context. Then the system receives a current user utterance independent of non-natural language input intended to trigger speech processing. The system compares the current user utterance to the conversation context to generate a context similarity score, and if the context similarity score is above a threshold, incorporates the current user utterance into the conversation context. If the context similarity score is below the threshold, the system discards the current user utterance. The system can compare the current user utterance to the conversation context based on an n-gram distribution, a perplexity score, and a perplexity threshold. Alternately, the system can use a task model to compare the current user utterance to the conversation context.

What's wrong with ‘the student experience’?

Abstract: Speaking about ‘the student experience’ has become common-place in higher education and the phrase has acquired the aura of a sacred utterance in UK higher education policy over the last decade. A critical discourse analysis of selected higher education policy texts reveals what ‘the student experience’ has come to signify, and how it structures relations between students and academics, institutions and academics, and higher education institutions and government. ‘The student experience’ homogenises students and deprives them of agency at the same time as apparently giving them ‘voice’. This paper examines the dominance and sacralisation of the discourse of ‘the student experience’ and questions its positioning as a means of discriminating between the value of different experiences of education.

Speech recognition dependent on text message content

Abstract: A method of automatic speech recognition. An utterance is received from a user in reply to a text message, via a microphone that converts the reply utterance into a speech signal. The speech signal is processed using at least one processor to extract acoustic data from the speech signal. An acoustic model is identified from a plurality of acoustic models to decode the acoustic data, and using a conversational context associated with the text message. The acoustic data is decoded using the identified acoustic model to produce a plurality of hypotheses for the reply utterance.

System and method for advanced turn-taking for interactive spoken dialog systems

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for advanced turn-taking in an interactive spoken dialog system A system configured according to this disclosure can incrementally process speech prior to completion of the speech utterance, and can communicate partial speech recognition results upon finding particular conditions A first condition which, if found, allows the system to communicate partial speech recognition results, is that the most recent word found in the partial results is statistically likely to be the termination of the utterance, also known as a terminal node A second condition is the determination that all search paths within a speech lattice converge to a common node, also known as a pinch node, before branching out again Upon finding either condition, the system can communicate the partial speech recognition results Stability and correctness probabilities can also determine which partial results are communicated

Isolated words enhance statistical language learning in infancy

Abstract: Infants are adept at tracking statistical regularities to identify word boundaries in pause-free speech. However, researchers have questioned the relevance of statistical learning mechanisms to language acquisition, since previous studies have used simplified artificial languages that ignore the variability of real language input. The experiments reported here embraced a key dimension of variability in infant-directed speech. English-learning infants (8–10 months) listened briefly to natural Italian speech that contained either fluent speech only or a combination of fluent speech and single-word utterances. Listening times revealed successful learning of the statistical properties of target words only when words appeared both in fluent speech and in isolation; brief exposure to fluent speech alone was not sufficient to facilitate detection of the words’ statistical properties. This investigation suggests that statistical learning mechanisms actually benefit from variability in utterance length, and provides the first evidence that isolated words and longer utterances act in concert to support infant word segmentation.

Imperatives: Meaning and Illocutionary Force

Abstract: Certain types of utterances, by virtue of being made, bring about obligations on their speakers or addressees. An utterance of a performatively used necessity modal brings about an obligation for the addressee (Kamp 1973). Explicitly performative utterances constituting promises or orders do the same for the speaker and addressee, respectively (Searle 1964; Alston 2000; Truckenbrodt 2009). It would seem that in the same fashion an utterance of an imperative creates an obligation for the addressee, a view explicitly espoused by Lewis (1969).

The syntacticization of discourse

Abstract: The goal of this paper is to explore the viability of a syntactic analysis of a range of empirical data that have so far received scarce attention in the syntactic literature, namely pragmatic markers which appear either on the left or the right edge of the utterance, as those illustrated in (1), from Romanian (R) and West Flemish (WF), and whose distribution will also be shown to interact with that of vocatives:

Terminology and Notation in Written Representations of Conversations with Augmentative and Alternative Communication

Abstract: There is a need for a continuous discussion about what terms one should use within the field of augmentative and alternative communication. When talking and thinking about people in their role as users of alternative communication forms, the terms should reflect their communicative ways and means, their achievements and what they are doing, rather than focus on what they cannot do. There are rather few articles analyzing utterance construction and dialogue processes involving children and adults using manual and graphic communication systems. The aim of this paper was to contribute to reviving the discussion of terminology and to more analyses of signing and aided communication and an increase in the use of conversation excerpts in the AAC Journal and elsewhere.

Incrementality and intention-recognition in utterance processing.

Abstract: Ever since dialogue modelling first developed relative to br oadly Gricean assumptions about utterance interpretation (Clark, 1996), it has remained an open question whether the full complexity of higher-order intention computation is made use of in everyday conversation. In this paper we examine the phenomenon of split utterances, from the perspective of Dynamic Syntax, to further probe the necessity of full intention recognition/formation in c ommunication: we do so by exploring the extent to which the interactive coordination of dialogue exchange can be seen as emergent from low-level mechanisms of language processing, without needing representation by interlocutors of each other’s mental states, or fully developed intentions a s regards messages to be conveyed. We thus illustrate how many dialogue phenomena can be seen as direct consequences of the grammar architecture, as long as this is presented within an incremental, goal-directed/predictivemodel.

Integrated local and cloud based speech recognition

Abstract: A system for integrating local speech recognition with cloud-based speech recognition in order to provide an efficient natural user interface is described In some embodiments, a computing device determines a direction associated with a particular person within an environment and generates an audio recording associated with the direction The computing device then performs local speech recognition on the audio recording in order to detect a first utterance spoken by the particular person and to detect one or more keywords within the first utterance The first utterance may be detected by applying voice activity detection techniques to the audio recording The first utterance and the one or more keywords are subsequently transferred to a server which may identify speech sounds within the first utterance associated with the one or more keywords and adapt one or more speech recognition techniques based on the identified speech sounds

Post-focus compression: cross-linguistic distribution and historical origin

Abstract: One of the most important acoustic correlates of prosodic focus is post-focus compression (PFC) — the reduction of pitch range and amplitude of all post-focus components in an utterance PFC has been found in many Indo-European, Altaic languages, and interestingly, also in Mandarin Chinese Meanwhile, there have also been reports that many other languages do not have PFC, or lack any clear prosodic marking of focus This paper presents a brief review of the current state of the art in the investigation of PFC, and discusses a number of hypotheses in regard to this typological division among the world languages In particular, the idea is explored that the distribution of PFC is related to the historical development of the world languages

Incremental interpretation and prediction of utterance meaning for interactive dialogue

Abstract: We present techniques for the incremental interpretation and prediction of utterance meaning in dialogue systems. These techniques open possibilities for systems to initiate responsive overlap behaviors during user speech, such as interrupting, acknowledging, or completing a user's utterance while it is still in progress. In an implemented system, we show that relatively high accuracy can be achieved in understanding of spontaneous utterances before utterances are completed. Further, we present a method for determining when a system has reached a point of maximal understanding of an ongoing user utterance, and show that this determination can be made with high precision. Finally, we discuss a prototype implementation that shows how systems can use these abilities to strategically initiate system completions of user utterances. More broadly, this framework facilitates the implementation of a range of overlap behaviors that are common in human dialogue, but have been largely absent in dialogue systems.

On the Nature of "Laughables": Laughter as a Response to Overdone Figurative Phrases

Abstract: In this article I explore the relationship between laugh responses and the turns which they orient to. I consider whether it is possible to identify properties of the prior turns that the recipient may be orienting to in laughing. Thus, I begin by briefly exploring the relationship between laughter and humour in interaction. But I point to some of the difficulties in identifying what it is that makes some discourse humorous, and I argue that laughter is not simply a reaction to the perception of humour. Laughter should be considered as an action in its own right, the occurrence of which may have nothing to do with the presence of humour. Consequently, I consider the notion of the “laughable” and whilst I agree that “(v)irtually any utterance or action could draw laughter, under the right (or wrong) circumstances” (Glenn 2003: 49), I argue it is often possible to identify recurrent properties of turns treated as laughables. These properties concern the design, action and the sequential position of the turns. Thus, it seems that speakers draw from a range of resources in constructing laughables. I illustrate this by exploring a collection of instances of figurative phrases followed by laugh responses from telephone calls. I argue that in responding with laughter, recipients may orient to a cluster of properties in the prior turn. However, because laughter is an action with its own sequential implications, rather than simply a response to a prior turn, whether a recipient orients to a prior candidate laughable by laughing will depend on the nature of his or her contribution to the action sequence.