In this paper we present a complete system for automatically generating natural language abstracts of meeting conversations. This system is comprised of components relating to interpretation of the meeting documents according to a meeting ontology, transformation or content selection from that source representation to a summary representation, and generation of new summary text. In a formative user study, we compare this approach to gold-standard human abstracts and extracts to gauge the usefulness of the different summary types for browsing meeting conversations. We find that our automatically generated summaries are ranked significantly higher than human-selected extracts on coherence and usability criteria. More generally, users demonstrate a strong preference for abstract-style summaries over extracts. 1

We address the challenge of automatically abstracting conversations such as face-to-face meetings and emails. We focus here on the stages of interpretation, where sentences are mapped to a conversation ontology, and transformation, where the summary content is selected. Our approach is fully developed and tested on meeting speech, and we subsequently explore its application to email conversations. 1

This paper is about interpreting human communication in meetings using audio, video and other signals. Automatic meeting recognition and understanding is extremely challenging, since communication in a meeting is spontaneous and conversational, and involves multiple speakers and multiple modalities. This leads to a number of significant research problems in signal processing, in speech recognition, and in discourse interpretation, taking account of both individual and group behaviours. Addressing these problems requires an interdisciplinary effort. In this paper, I discuss the capture and annotation of multimodal meeting recordings—resulting in the AMI meeting corpus—and how we have built on this to develop techniques and applications for the recognition and interpretation of meetings. 1

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.

Available online at www.sciencedirect.com Speech Communication xxx (2010) xxx–xxx www.elsevier.com/locate/specom 2 Long story short – Global unsupervised models for keyphrase 3 based meeting summarization

This paper presents an interactive interface to create visually structured summaries of human conversations via ontology mapping. We have built highly accurate classifiers for mapping the sentences of a conversation in an ontology, which includes nodes for the Dialog Acts (DA) properties such as decision and subjective, along with nodes for the conversation participants. In contrast with previous work, our classifiers do not rely on features specific to any particular conversational modality. We are currently developing an interactive interface that allows the user to generate visual structured summaries by searching a conversation for sentences according to the ontology mapping. Our first prototype comprises two panels. The right panel displays the ontology, while the left panel of the our prototype displays the whole conversation, where sentences are temporally ordered. Given the information displayed in the two panels, the user can generate visual, structured summaries by selecting nodes in the ontology. As a result, the sentences that were mapped in the selected nodes will be highlighted. Our initial prototype builds on a component of the GATE system, which was originally developed as a tool for text annotation.

In this paper we describe a complete abstractive summarizer for meeting conversations, and evaluate the usefulness of the automatically generated abstracts in a browsing task. We contrast these abstracts with extracts for use in a meeting browser and investigate the effects of manual versus ASR transcripts on both summary types. Index Terms: summarization, automatic speech recognition, abstraction, extraction, evaluation

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. Index Terms—Multiparty meetings processing, speech recognition, spoken language understanding. I.

This paper is about the recognition and interpretation of multiparty meetings captured as audio, video and other signals. This is a challenging task since the meetings consist of spontaneous and conversational interactions between a number of participants: it is a multimodal, multiparty, multistream problem. We discuss the capture and annotation of the AMI meeting corpus, the development of a meeting speech recognition system, and systems for the automatic segmentation, summarisation and social processing of meetings, together with some example applications based on these systems.

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. Index Terms— multiparty meetings processing, speech recognition, spoken language understanding I.