{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T10:47:37Z","timestamp":1772362057876,"version":"3.50.1"},"reference-count":50,"publisher":"Cambridge University Press (CUP)","issue":"2","license":[{"start":{"date-parts":[[2012,11,6]],"date-time":"2012-11-06T00:00:00Z","timestamp":1352160000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2014,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Since the release of the large discourse-level annotation of the Penn Discourse Treebank (PDTB), research work has been carried out on certain subtasks of this annotation, such as disambiguating discourse connectives and classifying Explicit or Implicit relations. We see a need to construct a full parser on top of these subtasks and propose a way to evaluate the parser. In this work, we have designed and developed an end-to-end discourse parser-to-parse free texts in the PDTB style in a fully data-driven approach. The parser consists of multiple components joined in a sequential pipeline architecture, which includes a connective classifier, argument labeler, explicit classifier, non-explicit classifier, and attribution span labeler. Our trained parser first identifies all discourse and non-discourse relations, locates and labels their arguments, and then classifies the sense of the relation between each pair of arguments. For the identified relations, the parser also determines the attribution spans, if any, associated with them. We introduce novel approaches to locate and label arguments, and to identify attribution spans. We also significantly improve on the current state-of-the-art connective classifier. We propose and present a comprehensive evaluation from both component-wise and error-cascading perspectives, in which we illustrate how each component performs in isolation, as well as how the pipeline performs with errors propagated forward. The parser gives an overall system <jats:italic>F<\/jats:italic><jats:sub>1<\/jats:sub> score of 46.80 percent for partial matching utilizing gold standard parses, and 38.18 percent with full automation.<\/jats:p>","DOI":"10.1017\/s1351324912000307","type":"journal-article","created":{"date-parts":[[2012,11,6]],"date-time":"2012-11-06T06:04:19Z","timestamp":1352181859000},"page":"151-184","source":"Crossref","is-referenced-by-count":63,"title":["A PDTB-styled end-to-end discourse parser"],"prefix":"10.1017","volume":"20","author":[{"given":"ZIHENG","family":"LIN","sequence":"first","affiliation":[]},{"given":"HWEE TOU","family":"NG","sequence":"additional","affiliation":[]},{"given":"MIN-YEN","family":"KAN","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2012,11,6]]},"reference":[{"key":"S1351324912000307_ref41","first-page":"566","volume-title":"Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2009)","author":"Subba","year":"2009"},{"key":"S1351324912000307_ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0378-2166(88)90050-1"},{"key":"S1351324912000307_ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2008.50"},{"key":"S1351324912000307_ref36","volume-title":"Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008)","author":"Prasad","year":"2008"},{"key":"S1351324912000307_ref22","unstructured":"Lin Z. , Ng H. T. , and Kan M.-Y. 2010. A PDTB-styled end-to-end discourse parser. Technical Report TRB8\/10, School of Computing, National University of Singapore (August)."},{"key":"S1351324912000307_ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00986208"},{"key":"S1351324912000307_ref35","doi-asserted-by":"crossref","first-page":"413","DOI":"10.3115\/980431.980576","volume-title":"Proceedings of the 10th International Conference on Computational Linguistics (COLING 1984)","author":"Polanyi","year":"1984"},{"key":"S1351324912000307_ref15","volume-title":"Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004)","author":"Huong","year":"2004"},{"key":"S1351324912000307_ref21","first-page":"1006","volume-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012)","author":"Lin","year":"2012"},{"key":"S1351324912000307_ref12","volume-title":"Cohesion in English","author":"Halliday","year":"1976"},{"key":"S1351324912000307_ref16","unstructured":"Knott A. 1996. A Data-Driven Methodology for Motivating a Set of Coherence Relations. PhD thesis, Department of Artificial Intelligence, University of Edinburgh, Edinburgh, UK."},{"key":"S1351324912000307_ref19","volume-title":"Proceedings of the 5th International Workshop on Treebanks and Linguistic Theories","author":"Lee","year":"2006"},{"key":"S1351324912000307_ref10","first-page":"175","article-title":"Attention, intentions, and the structure of discourse","volume":"12","author":"Grosz","year":"1986","journal-title":"Computational Linguistics"},{"key":"S1351324912000307_ref4","first-page":"1","volume-title":"Proceedings of the Second SIGdial Workshop on Discourse and Dialogue","author":"Carlson","year":"2001"},{"key":"S1351324912000307_ref3","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.34.1.1"},{"key":"S1351324912000307_ref1","volume-title":"Logics of Conversation","author":"Asher","year":"2003"},{"key":"S1351324912000307_ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(98)00023-X"},{"key":"S1351324912000307_ref6","first-page":"665","volume-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009)","author":"duVerle","year":"2009"},{"key":"S1351324912000307_ref9","first-page":"1071","volume-title":"Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011)","author":"Ghosh","year":"2011"},{"key":"S1351324912000307_ref30","volume-title":"The Penn Discourse Treebank 2.0 Annotation Manual","year":"2007"},{"key":"S1351324912000307_ref40","first-page":"149","volume-title":"Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2003)","author":"Soricut","year":"2003"},{"key":"S1351324912000307_ref47","first-page":"92","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL 2007)","author":"Wellner","year":"2007"},{"key":"S1351324912000307_ref26","first-page":"313","article-title":"Building a large annotated corpus of English: the Penn Treebank","volume":"19","author":"Marcus","year":"1993","journal-title":"Computational Linguistics"},{"key":"S1351324912000307_ref25","unstructured":"Marcu D. 1997. The Rhetorical Parsing, Summarization, and Generation of Natural Language Texts. PhD thesis, University of Toronto, Ontario, Canada."},{"key":"S1351324912000307_ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024137719751"},{"key":"S1351324912000307_ref38","doi-asserted-by":"publisher","DOI":"10.3115\/991719.991756"},{"key":"S1351324912000307_ref46","unstructured":"Wellner B. 2009. Sequence Models and Ranking Methods for Discourse Parsing. Ph.D. thesis, Brandeis University, Waltham, MA, USA."},{"key":"S1351324912000307_ref11","first-page":"203","article-title":"Centering: a framework for modeling the local coherence of discourse","volume":"21","author":"Grosz","year":"1995","journal-title":"Computational Linguistics"},{"key":"S1351324912000307_ref45","first-page":"86","volume-title":"COLING-ACL Workshop on Discourse Relations and Discourse Markers","author":"Webber","year":"1998"},{"key":"S1351324912000307_ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1706543.1706560"},{"key":"S1351324912000307_ref27","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"S1351324912000307_ref23","first-page":"997","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT 2011)","author":"Lin","year":"2011"},{"key":"S1351324912000307_ref33","volume-title":"Proceedings of the 22nd International Conference on Computational Linguistics (COLING 2008)","author":"Pitler","year":"2008"},{"key":"S1351324912000307_ref20","first-page":"343","volume-title":"Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP 2009)","author":"Lin","year":"2009"},{"key":"S1351324912000307_ref31","first-page":"683","volume-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009)","author":"Pitler","year":"2009"},{"key":"S1351324912000307_ref29","volume-title":"Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC 2004)","author":"Miltsakaki","year":"2004"},{"key":"S1351324912000307_ref37","first-page":"2076","volume-title":"Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC-2010)","author":"Prasad","year":"2010"},{"key":"S1351324912000307_ref43","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2805_6"},{"key":"S1351324912000307_ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1608829.1608834"},{"key":"S1351324912000307_ref42","first-page":"710","volume-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010)","author":"Wang","year":"2010"},{"key":"S1351324912000307_ref44","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324911000337"},{"key":"S1351324912000307_ref48","doi-asserted-by":"crossref","first-page":"117","DOI":"10.3115\/1654595.1654618","volume-title":"Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue","author":"Wellner","year":"2006"},{"key":"S1351324912000307_ref49","first-page":"249","volume-title":"Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004)","author":"Wolf","year":"2005"},{"key":"S1351324912000307_ref28","volume-title":"Proceedings of the Fourth Workshop on Treebanks and Linguistic Theories (TLT2005)","author":"Miltsakaki","year":"2005"},{"key":"S1351324912000307_ref50","first-page":"1507","volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010)","author":"Zhou","year":"2010"},{"key":"S1351324912000307_ref14","volume-title":"CSLI Lecture Notes Number 21","author":"Hobbs","year":"1990"},{"key":"S1351324912000307_ref39","first-page":"57","volume-title":"Proceedings of the Recent Advances in Natural Language Processing (RANLP 2005)","author":"Skadhauge","year":"2005"},{"key":"S1351324912000307_ref24","doi-asserted-by":"publisher","DOI":"10.1515\/text.1.1988.8.3.243"},{"key":"S1351324912000307_ref13","unstructured":"Hobbs Jerry R. 1985. On the coherence and structure of discourse. Technical Report CSLI-85-37, Center for the Study of Language and Information, Stanford University, Stanford, CA, USA."},{"key":"S1351324912000307_ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1667583.1667589"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324912000307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,22]],"date-time":"2019-04-22T17:40:12Z","timestamp":1555954812000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324912000307\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,6]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["S1351324912000307"],"URL":"https:\/\/doi.org\/10.1017\/s1351324912000307","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11,6]]}}}