A Paraphrase-Based Exploration of Cohesiveness Criteria

This paperproposesan empirical approachto the developmentof a computationalmodelfor assessingtexts accordingto cohesi veness.We arguethat the NLG technologiesfor the gener ation of structuralparaphrasescan be usedto efficiently createwhatwecall a cohesion-variantparallelcorpus,which wouldserve asa goodresourcefor empirical acquisitionof cohesi venesscriteria. We also presentour pilot case study, in which we took a particular type of paraphrasingthat separatesa relative clausefrom a sentence. We have so far createda cohesion-variant parallelcorpuscontaining499cohesi ve instancesand841incohesi ve instances. Basedon this corpus, we conducted a preliminary experimenton cohesion evaluation, obtaining encouragingresults.

[1]  Marilyn A. Walker,et al.  Japanese Discourse and the Process of Centering , 1994, Comput. Linguistics.

[2]  Leo Wanner,et al.  The HealthDoc Sentence Planner , 1996, INLG.

[3]  Kentaro Inui,et al.  Selective Sampling for Example-based Word Sense Disambiguation , 1998, CL.

[4]  Donia Scott,et al.  Book Reviews: Generating Referring Expressions , 1994, CL.

[5]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[6]  Scott Weinstein,et al.  Centering: A Framework for Modeling the Local Coherence of Discourse , 1995, CL.

[7]  K. Sakuma.  The structure of the Japanese language , 1951 .

[8]  Clarisse Sieckenius de Souza,et al.  Getting the message across in RST-based text generation , 1990 .

[9]  Manfred Stede,et al.  Discourse Marker Choice in Sentence Planning , 1998, INLG.

[10]  L SidnerCandace,et al.  Attention, intentions, and the structure of discourse , 1986 .

[11]  Eduard H. Hovy,et al.  Aggregation in Natural Language Generation , 1993, EWNLG.

[12]  Daniel Marcu,et al.  An Empirical Investigation of the Relation Between Discourse Structure and Co-Reference , 2000, COLING.

[13]  Daniel Marcu,et al.  From Local to Global Coherence: A Bottom-Up Approach to Text Planning , 1997, AAAI/IAAI.

[14]  Kentaro Inui,et al.  An environment for constructing nominal-paraphrase corpora , 2000 .

[15]  S. Oates.  State of the Art Report on Discourse Markers and Relations , 1999 .

[16]  Michael Halliday,et al.  An Introduction to Functional Grammar , 1985 .

[17]  Megumi Kameyama,et al.  A Property-Sharing Constraint in Centering , 1986, ACL.

[18]  Daniel Marcu,et al.  The Automatic Translation of Discourse Structures , 2000, ANLP.

[19]  James Shaw.  Clause Aggregation Using Linguistic Knowledge , 1998, INLG.

[20]  Inderjeet Mani,et al.  Improving Summaries by Revising Them , 1999, ACL.

[21]  Makoto Nagao,et al.  Building a Japanese parsed corpus while improving the parsing system , 1997 .

[22]  William C. Mann,et al.  RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION , 1987 .

[23]  Keith Vander Linden.  Generating Precondition Expressions in Instructional Text , 1994, ACL.