A machine learning approach to pronoun resolution in spoken dialogue

Strube, Michael; Müller, Christoph

doi:10.3115/1075096.1075118

Cited by 67 publications

(64 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…their discourse entity elements are siblings. For the process of anaphora resolution each anaphora-candidate-pair is interpreted as a feature vector which is used for training a classifier (see also [41,46,58]). A detailed description of the candidate list creation process as well as of the XSLT processing script is given in [47].…”

Section: A Nte Cedent Candidate Listmentioning

confidence: 99%

“…in terms of sentences) and by collecting all discourse entities in this window [e.g. 52,41,46,58], Taking all preceding candidates into account works well for small texts, however for long texts this might lead to large candidate sets. The definition of an appropriate size of the search window is important inasmuch as a small window leads to errors due to the fact that the search window does not cover the correct antecedent at all and as a large window leads to large candidate sets which increases the possibility of preferring a wrong candidate over the correct one (for a discussion of the window size's impact on precision and recall values see [52]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Linguistic Annotation Models and Their Application in the Domain of Antecedent Detection

Witt

Stührenberg

Goecke

et al. 2011

Modeling, Learning, and Processing of Text Technological Data Structures

View full text Add to dashboard Cite

Abstract. Seamless integration of various, often heterogeneous linguistic resources in terms of their output formats and a combined analysis of the respective annotation layers are crucial tasks for linguistic research. After a decade of concentration on the development of formats to structure single annotations for specific linguistic issues, in the last years a variety of specifications to store multiple annotations over the same primary data has been developed. The paper focuses on the integration of the knowledge resource logical document structure information into a text document to enhance the task of automatic anaphora resolution both for the task of candidate detection and antecedent selection. The paper investigates data structures necessary for knowledge integration and retrieval. IntroductionAnaphora Resolution (AR) describes the process of identifying the correct antecedent for a given anaphoric element and, in general, consists of three steps: (1) identification of anaphoric elements, (2) creation of a candidate set for each anaphora and (3) detection of the correct antecedent from the candidate set. In this paper we will focus on the second and third step and we will investigate the question how to create an appropriate candidate set.In recent approaches that define anaphora resolution as a pairwise decision, the candidate set is created by choosing all candidates that precede a given anaphora

show abstract

Section: A Nte Cedent Candidate Listmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Integrated Linguistic Annotation Models and Their Application in the Domain of Antecedent Detection

Witt

Stührenberg

Goecke

et al. 2011

Modeling, Learning, and Processing of Text Technological Data Structures

View full text Add to dashboard Cite

show abstract

“…Coreference resolution is a central problem in Natural Language Processing with a broad range of applications such as summarization (Steinberger et al, 2007), textual entailment (Mirkin et al, 2010), information extraction (McCarthy and Lehnert, 1995), and dialogue systems (Strube and Müller, 2003). Traditionally, the resolution of noun phrases (NPs) has been the focus of coreference research .…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

2015

View full text Add to dashboard Cite

will take place in Denver on June 4 and 5 and is colocated with SemEval and NAACL. As in 2014 at COLING, also on this occasion *SEM and SemEval chose to coordinate their programs by featuring a joint invited talk. In this way, *SEM aims to bring together the ACL SIGLEX and ACL SIGSEM communities.The acceptance rate of *SEM 2015 was quite competitive: out of 98 submissions, we accepted 36 papers for an overall acceptance of 37%. The acceptance rate of long paper that were accepted for oral presentation (18 out of 62) is 29%. The papers cover a wide range of topics including distributional semantics; lexical semantics and lexical acquisition; formal and linguistic semantics; discourse semantics; lexical resources, linked data and ontologies; semantics for applications; and extra-propositional semantics: sentiment and figurative meaning.The *SEM 2015 program consists of oral presentations for selected long papers and a poster session for long and short papers.Day One, June 4th:• Joint *SEM SemEval keynote talk by Marco Baroni;• Oral presentation sessions on distributional semantics, lexical semantics, and extra-propositional semantics;• Poster session.Day Two, June 5th:• Keynote talk by Preslav Natkov;• Oral presentation sessions on semantics for applications, lexical resources and ontologies, formal semantics, and discourse semantics;• *SEM Best Paper Award.We cannot finish without saying that *SEM 2015 would not have been possible without the considerable efforts of our area chairs, their reviewers, and the computational semantics community in general.We hope you will enjoy *SEM 2015, Distributional semantic methods have some a priori appeal as models of human meaning acquisition, because they induce word representations from contextual distributions naturally occurring in corpus data without need for supervision. However, learning the meaning of a (concrete) word also involves establishing a link between the word and its typical visual referents, which is beyond the scope of classic, text-based distributional semantics. Since recently several proposals have been put forward about how to induce multimodal word representations from linguistic and visual contexts, it is natural to ask if this line of work, besides its practical implications, can help us to develop more realistic, grounded models of human word learning within the distributional semantics framework.In my talk, I will report about two studies in which we used multimodal distributional semantics (MDS) to simulate human word learning. In one study, we first measured the ability of subjects to link a nonce word to relevant linguistic and visual associates when prompted only by exposure to minimal corpus evidence about it. We then simulated the same task with an MDS model, finding its behavior remarkably similar to that of subjects. In the second study, we constructed a corpus in which child-directed speech is aligned with real-life pictures of the objects mentioned by care-givers. We then trained our MDS model on these data, and inspected the generaliza...

show abstract

“…Coreference resolution is an active NLP research area, with its own track at most NLP conferences and several shared tasks such as the CoNLL or SemEval shared tasks (Pradhan et al, 2012;Recasens et al, 2010) there exist a few systems for pronoun resolution in transcripts of spoken text (Strube and Müller, 2003;Tetreault and Allen, 2004). It has been shown that there are differences between written and spoken text that lead to a drop in performance when coreference resolution systems developed for written text are applied on spoken text (Amoia et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Workshop on Speech-Centric Natural Language Processing

Ruiz¹,

Bangalore²

2017

View full text Add to dashboard Cite

The purpose of this workshop was to unite the automatic speech recognition (ASR) and natural language processing (NLP) communities to discuss new frameworks for exploiting the rich information present in the speech signal to improve the capabilities of natural language processing applications. Our community objective is to revisit the conventional NLP problems with a focus on incorporating the richness of spoken language, as well as to encourage research contributions that promote cross-fertilization between statistical methods for ASR and NLP.Our inaugural workshop was held at EMNLP to encourage participation amongst the NLP community to consider and discuss the challenges of combining speech recognition with conventional NLP research, as well as to appreciate the recent successes in this exciting field. The authors in these proceedings have combined ASR and NLP in works that address part-of-speech tagging, constituency parsing and dependency parsing on speech, information extraction and spoken term detection, dialog state tracking and speech translation, as well as two research assessments that evaluate the fluency and adequacy of English speakers and the role of speech silence in conversational dialogs.The invited talk was given by Gabriel Skantze, entitled "Modelling turn-taking in spoken interaction."Our workshop also contained an open round-table discussion about the current state of speech-centric NLP and some of the research and pragmatic issues that raise a barrier of entry for the larger research community.We would like to thank the members of the Program Committee for their reviews, as well as our panelists who led our round- AbstractSilence is an integral part of the most frequent turn-taking phenomena in spoken conversations. Silence is sized and placed within the conversation flow and it is coordinated by the speakers along with the other speech acts. The objective of this analytical study is twofold: to explore the functions of silence with duration of one second and above, towards information flow in a dyadic conversation utilizing the sequences of dialog acts present in the turns surrounding the silence itself; and to design a feature space useful for clustering the silences using a hierarchical concept formation algorithm. The resulting clusters are manually grouped into functional categories based on their similarities. It is observed that the silence plays an important role in response preparation, also can indicate speakers' hesitation or indecisiveness. It is also observed that sometimes long silences can be used deliberately to get a forced response from another speaker thus making silence a multi-functional and an important catalyst towards information flow.

show abstract

A machine learning approach to pronoun resolution in spoken dialogue

Cited by 67 publications

References 17 publications

Integrated Linguistic Annotation Models and Their Application in the Domain of Antecedent Detection

Integrated Linguistic Annotation Models and Their Application in the Domain of Antecedent Detection

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

Proceedings of the Workshop on Speech-Centric Natural Language Processing

Contact Info

Product

Resources

About