Annotation for and Robust Parsing of Discourse Structure on Unrestricted Texts

Baldridge, Jason; Asher, Nicholas; Hunter, Julie

doi:10.1515/zfs.2007.018

Cited by 15 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of discourse structure, in particular rhetorical structure, on texts is now a well entrenched cottage industry in computational linguistics. Several discourse annotated corpora exist including the Penn Discourse Treebank (PDTB; Prasad et al, 2008) and the RST Discourse Treebank (RST-DT; Carlson et al, 2002)-the only large corpus with full discourse structure for texts-as well as smaller annotated corpora such as DISCOR (Baldridge et al, 2007) or ANNODIS (Afantenos et al, 2012). The STAC project (Hunter et al, 2015b; extends this work to dialogue annotation on a corpus of chats from an online version of the game Settlers of Catan.…”

Section: Introductionmentioning

confidence: 99%

Modelling Structures for Situated Discourse

Asher

Hunter

Thompson

2020

dad

Self Cite

View full text Add to dashboard Cite

This paper describes a corpus of situated multiparty chats developed for the STAC project (Strategic Conversation, ERC grant n. 269427). and annotated for discourse structure in the style of Segmented Discourse Representation Theory (SDRT; Asher & Lascarides,2003). The STAC corpus is not only a rich source of data on strategic conversation, but also the first corpus that we are aware of that provides discourse structures for multiparty dialogues situated within a virtual environment. The corpus was annotated in two stages: we initially annotated the chat moves only, but later decided to annotate interactions between the chat moves and non-linguistic events from the virtual environment. This two-step procedure has allowed us quantify various ways in which adding information from the nonlinguistic context affects dialogue structure. In this paper, we look at how annotations based only on linguistic information were preserved once the nonlinguistic context was factored in. We explain that while the preservation of relation instances is relatively high when we move from one corpus to the other, there is little preservation of higher order structures that capture "the main point" of a dialogue and distinguish it from peripheral information.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling Structures for Situated Discourse

Asher

Hunter

Thompson

2020

dad

Self Cite

View full text Add to dashboard Cite

show abstract

“…A more appropriate model would enforce global constraints on its predictions. In the simple+MST model, this is achieved by a minimum spanning tree (MST) decoding, which has first been applied for syntactic dependency parsing (McDonald et al, 2005a;McDonald et al, 2005b) and later for discourse parsing (Baldridge et al, 2007;Muller et al, 2012). First, we build a fullyconnected directed graph, with one node for each text segment.…”

Section: Learned Attachment With Mst Decodingmentioning

confidence: 99%

“…Finally, we compare our models to the well-known mstparser 4 , which was also used in the discourse parsing experiments of Baldridge et al (2007). The mstparser applies 1-best MIRA structured learning, a learning regime that we expect to be superior over the simple training in the previous models.…”

Section: Comparison: Mst Parsermentioning

confidence: 99%

Joint prediction in MST-style discourse parsing for argumentation mining

Peldszus

Stede

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

108

127

View full text Add to dashboard Cite

We introduce a new approach to argumentation mining that we applied to a parallel German/English corpus of short texts annotated with argumentation structure. We focus on structure prediction, which we break into a number of subtasks: relation identification, central claim identification, role classification, and function classification. Our new model jointly predicts different aspects of the structure by combining the different subtask predictions in the edge weights of an evidence graph; we then apply a standard MST decoding algorithm. This model not only outperforms two reasonable baselines and two datadriven models of global argument structure for the difficult subtask of relation identification, but also improves the results for central claim identification and function classification and it compares favorably to a complex mstparser pipeline.

show abstract

“…3 From model and raw data to annotation 3.1 DISCOR: a first experiment on discourse structure A first effort on the part of some of the authors of this paper to build a annotated corpus with rhetorical relations was an NSF funded project, DISCOR (Baldridge et al , 2007), carried out at the University of Texas at Austin. The project annotated 60 English texts from the MUC 6 and MUC 7 data sets, and so the texts were largely news stories.…”

Section: Recursive and Complete Discourse Structures For Text And Diamentioning

confidence: 99%