| measure(ment),17-4-P03-1031,bq | <term> dialogue </term> progresses , the <term> | discourse | understanding accuracy </term> can be improved | #4209 By holding multiple candidates for understanding results and resolving the ambiguity as the dialogue progresses, thediscourse understanding accuracy can be improved. |
| other,12-3-H92-1045,bq | completion , we observed a very strong <term> | discourse | </term> effect . That is , if a <term> polysemous | #19224 As this work was nearing completion, we observed a very strongdiscourse effect. |
| other,12-3-N04-1024,bq | semantic similarity measures </term> and <term> | discourse | structure </term> . A <term> support vector | #6702 This system identifies features of sentences based on semantic similarity measures anddiscourse structure. |
| other,13-10-J86-3001,bq | processing of <term> utterances </term> in a <term> | discourse | </term> . <term> Discourse processing </term> | #14324 This theory provides a framework for describing the processing of utterances in adiscourse. |
| other,14-12-J86-3001,bq | </term> the role of information from the <term> | discourse | </term> and from the <term> participants </term> | #14382 This processing description specifies in these recognition tasks the role of information from thediscourse and from the participants' knowledge of the domain. |
| other,14-7-J86-3001,bq | provide an adequate explanation of such <term> | discourse | phenomena </term> as <term> cue phrases </term> | #14252 The distinction among these components is essential to provide an adequate explanation of suchdiscourse phenomena as cue phrases, referring expressions, and interruptions. |
| other,15-1-N04-1024,bq | <term> writing </term> with <term> essay-based | discourse | elements </term> ( e.g. , <term> thesis statements | #6661 CriterionSM Online Essay Evaluation Service includes a capability that labels sentences in student writing with essay-based discourse elements (e.g., thesis statements). |
| other,16-5-J86-3001,bq | the <term> participants </term> as the <term> | discourse | </term> unfolds . The <term> attentional state | #14210 The attentional state is an abstraction of the focus of attention of the participants as thediscourse unfolds. |
| other,17-4-H92-1045,bq | two or more times in a <term> well-written | discourse | </term> , it is extremely likely that they | #19245 That is, if a polysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. |
| other,20-1-J86-3001,bq | </term> and <term> processing </term> in <term> | discourse | </term> . In this theory , <term> discourse | #14100 In this paper we explore a new theory of discourse structure that stresses the role of purpose and processing indiscourse. |
| other,20-11-J86-3001,bq | <term> intentions </term> expressed in the <term> | discourse | </term> and the relationships among <term> | #14346 Discourse processing requires recognizing how the utterances of the discourse aggregate into segments, recognizing the intentions expressed in thediscourse and the relationships among intentions, and tracking the discourse through the operation of the mechanisms associated with attentional state. |
| other,20-2-C88-2130,bq | descriptions , using <term> organizational and | discourse | strategies </term> derived through analysis | #15488 The model is embodied in a program, APT, that can reproduce segments of actual tape-recorded descriptions, using organizational and discourse strategies derived through analysis of our corpus. |
| other,20-3-C04-1128,bq | upon <term> lexical similarity </term> of <term> | discourse | segments </term> for <term> question-answer | #6302 We show that various features based on the structure of email-threads can be used to improve upon lexical similarity ofdiscourse segments for question-answer pairing. |
| other,20-5-H92-1045,bq | share <term> sense </term> in the same <term> | discourse | </term> is extremely strong ( 98 % ) . This | #19280 This paper describes an experiment which confirmed this hypothesis and found that the tendency to share sense in the samediscourse is extremely strong (98%). |
| other,20-7-H92-1045,bq | </term> that did not make use of the <term> | discourse | constraint </term> . This paper describes | #19330 In addition, it could also be used to help evaluate disambiguation algorithms that did not make use of thediscourse constraint. |
| other,21-1-C88-2130,bq | apartment or house , a much-studied <term> | discourse | task </term> first characterized linguistically | #15455 We have developed a computational model of the process of describing the layout of an apartment or house, a much-studieddiscourse task first characterized linguistically by Linde (1974). |
| other,22-4-N04-1024,bq | question </term> and relatedness between <term> | discourse | elements </term> . <term> Intra-sentential | #6727 A support vector machine uses these features to capture breakdowns in coherence due to relatedness to the essay question and relatedness betweendiscourse elements. |
| other,23-6-J86-3001,bq | that are salient at each point of the <term> | discourse | </term> . The distinction among these components | #14236 The attentional state, being dynamic, records the objects, properties, and relations that are salient at each point of thediscourse. |
| other,3-1-C92-1052,bq | are ever introduced . In this paper <term> | discourse | segments </term> are defined and a method | #17754 In this paperdiscourse segments are defined and a method for discourse segmentation primarily based on abduction of temporal relations between segments is proposed. |
| other,3-9-J86-3001,bq | discourses </term> . Various properties of <term> | discourse | </term> are described , and explanations | #14290 Various properties ofdiscourse are described, and explanations for the behaviour of cue phrases, referring expressions, and interruptions are explored. |
