Generating discourse structures for written texts

LeThanh, Huong; Abeysinghe, Geetha; Huyck, Christian R.

doi:10.3115/1220355.1220403

Cited by 40 publications

(47 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"but", "because", "after") and syntactic information (Le Thanh et al, 2004;Tofiloski et al, 2009 More recent discourse segmenters on the RST-DT are based on binary classifiers at the word level (Soricut and Marcu, 2003;Fisher and Roark, 2007;Joty et al, 2015), possibly using a neural network architecture (Subba and Di Eugenio, 2007). Joty et al (2015) also report results for the Instructional corpus (Subba and Di Eugenio, 2009) (F 1 80.9% on 10-fold).…”

Section: Related Workmentioning

confidence: 99%

Does syntax help discourse segmentation? Not so much

Braud¹,

Lacroix²,

Søgaard³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Discourse segmentation is the first step in building discourse parsers. Most work on discourse segmentation does not scale to real-world discourse parsing across languages, for two reasons: (i) models rely on constituent trees, and (ii) experiments have relied on gold standard identification of sentence and token boundaries. We therefore investigate to what extent constituents can be replaced with universal dependencies, or left out completely, as well as how state-of-the-art segmenters fare in the absence of sentence boundaries. Our results show that dependency information is less useful than expected, but we provide a fully scalable, robust model that only relies on part-of-speech information, and show that it performs well across languages in the absence of any gold-standard annotation.

show abstract

Section: Related Workmentioning

confidence: 99%

Does syntax help discourse segmentation? Not so much

Braud¹,

Lacroix²,

Søgaard³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…CKY and chart parsing) and various features (eg. length, position et al) for discourse parsing (Soricut and Marcu, 2003;Joty et al, 2012;Reitter, 2003;LeThanh et al, 2004;Baldridge and Lascarides, 2005;Subba and Di Eugenio, 2009;Sagae, 2009;Hernault et al, 2010b;Feng and Hirst, 2012). However, the existing approaches suffer from at least one of the following three problems.…”

Section: Introductionmentioning

confidence: 99%

Text-level Discourse Dependency Parsing

Wang

Cao

et al. 2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

126

View full text Add to dashboard Cite

Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). The state-of-the-art dependency parsing techniques, the Eisner algorithm and maximum spanning tree (MST) algorithm, are adopted to parse an optimal discourse dependency tree based on the arcfactored model and the large-margin learning techniques. Experiments show that our discourse dependency parsers achieve a competitive performance on text-level discourse parsing.

show abstract

“…Early approaches to discourse parsing (Marcu, 2000;LeThanh et al, 2004) have primarily focused on overt discourse markers (or cue words) and used a series of rules to derive the discourse tree structure. Soricut and Marcu (2003) employed a standard bottom-up chart parsing algorithm with syntactic and lexical features to conduct sentencelevel parsing.…”

Section: Related Workmentioning

confidence: 99%

Learning Contextually Informed Representations for Linear-Time Discourse Parsing

Liu¹,

Lapata²

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Recent advances in RST discourse parsing have focused on two modeling paradigms: (a) high order parsers which jointly predict the tree structure of the discourse and the relations it encodes; or (b) lineartime parsers which are efficient but mostly based on local features. In this work, we propose a linear-time parser with a novel way of representing discourse constituents based on neural networks which takes into account global contextual information and is able to capture long-distance dependencies. Experimental results show that our parser obtains state-of-the art performance on benchmark datasets, while being efficient (with time complexity linear in the number of sentences in the document) and requiring minimal feature engineering.

show abstract

Generating discourse structures for written texts

Cited by 40 publications

References 11 publications

Does syntax help discourse segmentation? Not so much

Does syntax help discourse segmentation? Not so much

Text-level Discourse Dependency Parsing

Learning Contextually Informed Representations for Linear-Time Discourse Parsing

Contact Info

Product

Resources

About