Quantifying Ellipsis In Dialogue: An Index of Mutual Understanding

1998

The area of ellipsis resolution and generation has long been neglected in work on natural language processing, and there are few examples of working systems or computational algorithms. However, the misuse or non-use of ellipsis in highly preferred contexts can make a dialogue difficult to understand similar to the way inappropriate referential expressions can impede comprehension. Furthermore, we think ellipsis has many more functions than are currently recognized, an idea discussed in our own contribution to this volume. We are grateful that the ESSLLI organizers have provided a forum for researchers to present new data and analyses.

Proceedings of the 5th Workshop on NLP and XML Multi-Dimensional Markup in Natural Language Processing - NLPXML '06, 2006

The ability to request clarification of utterances is a vital part of the communicative process. In this paper we discuss the range of possible forms for clarification requests, together with the range of readings they can convey. We present the results of corpus analysis which show a correlation between certain forms and possible readings, together with some indication of maximum likely distance between request and the utterance being clarified. We then explain the implications of these results for a possible HPSG analysis of clarification requests and for an ongoing implementation of a clarification-capable dialogue system. 1

Research on Language and Computation, 2007

What knowledge sources are necessary in the interpretation and generation of ellipsis? After a short background on earlier approaches we compare and discuss each of the four papers selected for this special issue, examining how they approach ellipsis generation or interpretation. We highlight areas where more research needs to be done: outlining how pragmatics affects ellipsis, empirical studies, and theoretical work on what the effect of ellipsis is in context.

1995

We discuss the treatment of ellipsis in a spoken languageroute planning enquiry service which uses theCore Language Engine (CLE) as its linguistic processor.We show how use of the CLE allows us to separatethe interpretation of ellipsis in a dialogue contextfrom the more general issue of dialogue managementin a dialogue context and, especially, to factor out thelinguistic influences on such interpretation and placethem where they belong - in the linguistic processor.The route planning...

2017

Dialogue act annotation aids understanding of interaction structure, and also in the design of artificial dialogue. While many dialogues can be described as task-based or instrumental, others are more interactional. These categories are not mutually exclusive; many service encounters include social talk. Much research on dialogue and particularly on description of dialogue acts for use in dialogue systems has focused on task-based dialogue. However, attention has been focusing on social aspects of spoken and text interaction, particularly in light of newer systems designed for domains such as companionship. In this paper we briefly describe social or casual talk, review how current dialogue annotation schemes, and particularly the ISO standard 24617-2 "Semantic annotation framework, Part 2: Dialogue acts", treat non-task elements of dialogue. We describe the collection and annotation using the ISO standard of a corpus of 193 text dialogues, report on a analysis of dialogue acts used in greeting, introductions and leave-taking, and propose new dialogue acts to provide coverage of these fundamental conversational sequences.

Language Resources and Evaluation, 2011

Verb Phrase Ellipsis (VPE) has been studied in great depth in theoretical linguistics, but empirical studies of VPE are rare. We extend the few previous corpus studies with an annotated corpus of VPE in all 25 sections of the Wall Street Journal corpus (WSJ) distributed with the Penn Treebank. We annotated the raw files using a stand-off annotation scheme that codes the auxiliary verb triggering the elided verb phrase, the start and end of the antecedent, the syntactic type of antecedent (VP, TV, NP, PP or AP), and the type of syntactic pattern between the source and target clauses of the VPE and its antecedent. We found 487 instances of VPE (including predicative ellipsis, antecedent-contained deletion, comparative constructions, and pseudo-gapping) plus 67 cases of related phenomena such as do so anaphora. Inter-annotator agreement was high, with a 0.97 average F-score for three annotators for one section of the WSJ. Our annotation is theory neutral, and has better coverage than earlier efforts that relied on automatic methods, e.g. simply searching the parsed version of the Penn Treebank for empty VP's achieves a high precision (0.95) but low recall (0.58) when compared with our manual annotation. The distribution of VPE source-target patterns deviates highly from the standard examples found in the theoretical linguistics literature on VPE, once more underlining the value of corpus studies. The resulting corpus will be useful for studying VPE phenomena as well as for evaluating natural language processing systems equipped with ellipsis resolution algorithms, and we propose evaluation measures for VPE detection and VPE antecedent selection. The stand-off annotation is freely available for research purposes.

2012

In this paper, we propose a new scheme for annotating response tokens (RTs) and their triggering expressions in Japanese multi-party conversations. In the proposed scheme, RTs are first identified and classified according to their forms, and then sub-classified according to their sequential positions in the discourse. To deeply study the contexts in which RTs are used, the scheme also provides procedures for annotating triggering expressions, which are considered to trigger the listener's production of RTs. RTs are classified according to whether or not there is a particular object or proposition in the speaker's turn for which the listener shows a positive or aligned stance. Triggering expressions are then identified in the speaker's turn; they include surprising facts and other newsworthy things, opinions and assessments, focus of a response to a question or repair initiation, keywords in narratives, and embedded propositions quoted from other's statement or thought, which are to be agreed upon, assessed, or noticed. As an illustrative application of our scheme, we present a preliminary analysis on the distribution of the latency of the listener's response to the triggering expression, showing how it differs according to RT's forms and positions.