Filters








882 Hits in 4.0 sec

Unsupervised topic modelling for multi-party spoken discourse

Matthew Purver, Thomas L. Griffiths, Konrad P. Körding, Joshua B. Tenenbaum
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
We present a method for unsupervised topic modelling which adapts methods used in document classification (Blei et al., 2003; Griffiths and Steyvers, 2004) to unsegmented multi-party discourse transcripts  ...  We show how Bayesian inference in this generative model can be used to simultaneously address the problems of topic segmentation and topic identification: automatically segmenting multi-party meetings  ...  We thank Elizabeth Shriberg and Andreas Stolcke for providing automatic speech recognition data for the ICSI corpus and for their helpful advice; John Niekrasz and Alex Gruenstein for help with the NOMOS  ... 
doi:10.3115/1220175.1220178 dblp:conf/acl/PurverKGT06 fatcat:c6mz3duajjfqzc6fxktorrtkga

Unsupervised topic modeling for leader detection in spoken discourse

Raia Hadsell, Zsolt Kira, Wen Wang, Kristin Precoda
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper, we describe a method for leader detection in multiparty spoken discourse that relies on unsupervised topic modeling to segment the discourse automatically.  ...  Latent Dirichlet allocation is applied to sliding temporal windows of utterances, resulting in a topic model which captures the fluid transitions from topic to topic which occur in multi-party discourse  ...  SUMMARY In this paper, we hypothesized that topics shifts occurring during multi-party spoken discourse could lend important clues towards leader detection.  ... 
doi:10.1109/icassp.2012.6289071 dblp:conf/icassp/HadsellKWP12 fatcat:cxtzyx3x35fhrdi2wo43lwuyru

A Hybrid Framework for Topic Structure using Laughter Occurrences [article]

Sucheta Ghosh
2019 arXiv   pre-print
In this work we combine both paralinguistic and linguistic knowledge into a hybrid framework through a multi-level hierarchy. Thus it outputs the discourse-level topic structures.  ...  This training-free topic structuring approach can be applicable to online understanding of spoken dialogs.  ...  Afsaneh Asaei for all help.  ... 
arXiv:2001.00573v1 fatcat:txwdn6surbaslb6mmhfn5cz3u4

Unsupervised Topic Segmentation of Meetings with BERT Embeddings [article]

Alessandro Solbiati, Kevin Heffernan, Georgios Damaskinos, Shivani Poddar, Shubham Modi, Jacques Cali
2021 arXiv   pre-print
Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks.  ...  We introduce an unsupervised approach based on BERT embeddings that achieves a 15.5% reduction in error rate over existing unsupervised approaches applied to two popular datasets for meeting transcripts  ...  Discourse seg- mantic information from speech, pages 291–317. mentation of multi-party conversation.  ... 
arXiv:2106.12978v1 fatcat:dfyx4w7gobcfflh5sjfvgaus3u

Topic Segmentation [chapter]

Matthew Purver
2011 Spoken Language Understanding  
This chapter discusses the task of topic segmentation: automatically dividing single long recordings or transcripts into shorter, topically coherent segments.  ...  We then explain the most influential approaches -generative and discriminative, supervised and unsupervised -and discuss their application in particular domains.  ...  While the distinction between two-party and multi-party dialogue can be very useful in some contexts, we intend the term dialogue to cover both here.  ... 
doi:10.1002/9781119992691.ch11 fatcat:lvloaozyaraupna4fmy4kfhd3i

Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings [article]

Lu Wang, Claire Cardie
2016 arXiv   pre-print
Concretely, a series of unsupervised topic models is explored and experimental results show that fine-grained topic models, which discover topics at the utterance-level rather than the document-level,  ...  We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify "summary-worthy" words.  ...  content models for multi-document summarization.  ... 
arXiv:1606.07829v1 fatcat:drbyg72pfvbgxnetlgudyzfbre

MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations [article]

Dian Yu, Zhou Yu
2019 arXiv   pre-print
Dialog act prediction is an essential language comprehension task for both dialog system building and discourse analysis.  ...  To show the applicability of the scheme, we leverage transfer learning methods to train a multi-label dialog act prediction model and reach an F1 score of 0.79.  ...  However, the scheme is designed for modeling conversation topics instead of training dialog act predictors.  ... 
arXiv:1908.10023v1 fatcat:cfoqi6hsp5cbjhtxyabxvzaewm

Human/Human Conversation Understanding [chapter]

Gokhan Tur, Dilek Hakkani-Tür
2011 Spoken Language Understanding  
In this chapter we focus on two-party and multi-party human/human conversation understanding approaches, mainly focusing on discourse modeling, speech act modeling, and argument diagramming.  ...  newer area for spoken language processing.  ...  To process spoken multi-party conversations, similar approaches were employed but with mixed results.  ... 
doi:10.1002/9781119992691.ch9 fatcat:2quzefll5re2lp2ytbasw6nthu

Keyphrase Extraction from Document Using RAKE and TextRank Algorithms

J.S. Baruni, Dr. J.G.R . Sathiaseelan
2020 International journal of computer science and mobile computing  
In this paper, to overcome this challenge, Automatic Keyphrase Extraction algorithm has been used to extract a Keyphrase efficiently that reduces the scope for human errors and saves time.  ...  Fig 1 . 1 Phrase Detection pipeline Fig 2 . 2 Sample Abstract to Extract Keyphrase A DEEP SEQUENTIAL MODEL FOR DISCOURSE PARSING ON MULTI-PARTY DIALOGUES Table 1 . 1 Extracted Keyphrase with scores  ...  This paper presents a deep sequential model for parsing discourse dependency structures of multiparty dialogues.  ... 
doi:10.47760/ijcsmc.2020.v09i09.009 fatcat:u5ytkygoqfgo7kp3ovwtaf6jqa

A Survey on Dialogue Summarization: Recent Advances and New Frontiers [article]

Xiachong Feng, Xiaocheng Feng, Bing Qin
2022 arXiv   pre-print
Furthermore, we discuss some future directions, including faithfulness, multi-modal, multi-domain and multi-lingual dialogue summarization, and give our thoughts respectively.  ...  However, there still remains a lack of a comprehensive survey for this task. To this end, we take the first step and present a thorough review of this research field carefully and widely.  ...  We would also like to thank Shiyue Zhang for her feedback on email summarization and Libo Qin for his helpful discussion.  ... 
arXiv:2107.03175v2 fatcat:qghkke4harac3otuvccbuw5pca

The CALO meeting speech recognition and understanding system

G. Tur, A. Stolcke, L. Voss, J. Dowding, B. Favre, R. Fernandez, M. Frampton, M. Frandsen, C. Frederickson, M. Graciarena, D. Hakkani-Tur, D. Kintzing (+9 others)
2008 2008 IEEE Spoken Language Technology Workshop  
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  ...  CONCLUSIONS We have presented a system for automatic processing of tasks involving multi-party meetings.  ...  We have also demonstrated the use of unsupervised adaptation methods for better recognition [3] .  ... 
doi:10.1109/slt.2008.4777842 dblp:conf/slt/TurSVDFFFFFGHKLMNPPRSTVY08 fatcat:ultv5i5cnjd5zhg7msra5ztnxy

Unsupervised Speaker Tracking In A Speech Recognition Module For Multi-Party Human-Computer Dialogue

Corneliu Burileanu, Jean Caelen, Vladimir Popescu
2008 Zenodo  
Hence, the choice of at most four dialogue partners seems appropriate for spontaneous spoken multi-party dialogue situations.  ...  and, moreover, multi-party human-computer dialogue corpora are not available, for the time being, in Romanian language.  ... 
doi:10.5281/zenodo.40863 fatcat:xo5dciagdvaatmck7wl3hgzqli

Discovering Latent Structure in Task-Oriented Dialogues

Ke Zhai, Jason D Williams
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Our methods synthesize hidden Markov models (for underlying state) and topic models (to connect words to states).  ...  We propose three new unsupervised models to discover latent structures in task-oriented dialogues.  ...  We are also grateful to Alan Ritter and Bill Dolan for their helpful discussions; and Kai (Anthony) Lui for providing TechSupport dataset.  ... 
doi:10.3115/v1/p14-1004 dblp:conf/acl/ZhaiW14 fatcat:a5ln3tbwnrck5mtcb6w7shkazm

Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information

Farah Benamara, Diana Inkpen, Maite Taboada
2018 Computational Linguistics  
This special issue contributes to a deeper understanding of the role of these interactions to process social media data from a new perspective in discourse interpretation.  ...  traditional text mining tools is clearly sub-optimal, as, typically, these tools take into account neither the interactive dimension nor the particular nature of this data, which shares properties with both spoken  ...  Acknowledgments We would like to thank all the authors who submitted articles and all the reviewers for their time and effort.  ... 
doi:10.1162/coli_a_00333 fatcat:mbpjsq3ltfdtnfbmldxlt7wzci

Focused Meeting Summarization via Unsupervised Relation Extraction [article]

Lu Wang, Claire Cardie
2016 arXiv   pre-print
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction.  ...  We evaluate the approach on a decision summarization task and show that it outperforms unsupervised utterance-level extractive summarization baselines as well as an existing generic relation-extraction-based  ...  We evaluate our approach on the AMI meeting corpus (Carletta et al., 2005) that consists of 140 multi-party meetings with a wide range of annotations.  ... 
arXiv:1606.07849v1 fatcat:7jezbomsnzfwnb7o26zndfhg6e
« Previous Showing results 1 — 15 out of 882 results