The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper presents the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, topic identification and segmentation, question-answer pair identification, action item recognition, decision extraction, and summarization.

We address the problem of identifying words and phrases that accurately capture, or contribute to, the semantic gist of decisions made in multi-party human-human meetings. We first describe our approach to modelling decision discussions in spoken meetings and then compare two approaches to extracting information from these discussions. The first one uses an opendomain semantic parser that identifies candidate phrases for decision summaries and then employs machine learning techniques to select from those candidate phrases. The second one uses categorical and sequential classifiers that exploit simple syntactic and semantic features to identify words and phrases relevant for decision summarization.

The CALO Meeting Assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.

An ideal spoken dialogue system listens continually and determines which utterances were spoken to it, understands them and responds appropriately while ignoring the rest. This paper outlines a simple method for achieving this goal which involves trading a slightly higher false rejection rate of in domain utterances for a higher correct rejection rate of out of domain (OOD) utterances. The system recognizes semantic entities specified by a unification grammar which is specialized by explanation based learning (EBL), so that it only uses rules which are seen in the training data. The resulting grammar has probabilities assigned to each construct so that overgeneralizations are not a problem. The resulting system only recognizes utterances which reduce to a valid logical form which has meaning for the system and rejects the rest. A class N-gram grammar has been trained on the same training data. This system gives good recognition performance and offers good out of domain discrimination when combined with the semantic analysis. The resulting systems were tested on a space station robot dialogue speech database and a subset of the OGI conversational speech database. Both systems run in real time on a PC laptop and the present performance allows continuous listening with an acceptably low false acceptance rate. This type of open microphone system has been used in the Clarissa procedure reading and navigation spoken dialogue system which is being tested on the International Space Station

Current alternatives for language modeling are statistical techniques based on large amounts of training data, and hand-crafted context-free or finite-state grammars that are difficult to build and maintain. One way to address the problems of the grammar-based approach is to compile recognition grammars from grammars written in a more expressive formalism. While theoretically straight-forward, the compilation process can exceed memory and time bounds, and might not always result in accurate and efficient speech recognition. We will describe and evaluate two approaches to this compilation problem. We will also describe and evaluate additional techniques to reduce the structural ambiguity of the language model.

This paper presents a minimal enumerative approach to the problem of compiling typed unification grammars into CFG language models, a prototype implementation and results of experiments in which it was used to compile some non-trivial unification grammars. We argue that enumerative methods are considerably more useful than has been previously believed. Also, the simplicity of enumerative methods makes them a natural baseline against which to compare alternative approaches. 1.

We describe an efficient bottom-up parser that interleaves syntactic and semantic structure building. Two techniques are presented for reducing search by reducing local ambiguity: Limited left context constraints are used to reduce local syntactic ambiguity, and deferred sortal-constraint application is used to reduce local semantic ambiguity. We experimentally evaluate these techniques, and show dramatic reductions in both number of chart edges and total parsing time. The robust processing capabilities of the parser are demonstrated in its use in improving the accuracy of a speech recognizer.

Article Free Access Share on Gemini: a natural language system for spoken-language understanding Authors: John Dowding SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Jean Mark Gawron SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Doug Appelt SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , John Bear SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Lynn Cherny SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Robert Moore SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Douglas Moran SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile Authors Info & Claims ACL '93: Proceedings of the 31st annual meeting on Association for Computational LinguisticsJune 1993Pages 54–61https://doi.org/10.3115/981574.981582Published:22 June 1993Publication History 43citation1,076DownloadsMetricsTotal Citations43Total Downloads1,076Last 12 Months25Last 6 weeks7 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Publisher SiteeReaderPDF

We have analyzed 607 sentences of spontaneous human-computer speech data containing repairs, drawn from a total corpus of 10,718 sentences. We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources: pattern matching, syntactic and semantic analysis, and acoustics.

This paper describes the SDC PUNDIT, (Prolog UNDerstands Integrated Text), system for processing natural language messages.1 PUNDIT, written in Prolog, is a highly modular system consisting of distinct syntactic, semantic and pragmatics components.Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of EngLish, semantic verb decompositions, rules mapping between syntactic and semantic constituents, and a domain model.This paper discusses the communication between the syntactic, semantic and pragmatic modules that is necessary for making implicit linguistic information explicit.The key is letting syntax and semantics recognize missing linguistic entities as implicit entities, so that they can be labelled as such, and referenee resolution can be directed to find specific referents for the entities.In this way the task of making implicit linguistic information explicit becomes a subset of the tasks performed by reference resolution.The success of this approach is dependent on marking missing syntactic constituents as elided and missing semantic roles as ESSENTIAL so that reference resolution can know when to look for referents.