Sense Prediction for Explicit Discourse Relations with BERT

2021 ◽  
pp. 835-842
Author(s):  
Jií Mírovský ◽  
Lucie Poláková
2017 ◽  
Vol 8 (2) ◽  
pp. 225-248
Author(s):  
Lucie Poláková ◽  
Jiˇrí Mírovský ◽  
Pavlína Synková

Describing implicit phenomena in discourse is known to be a problematic task, from both theoretical and empirical perspectives. The present article contributes to this topic by a novel comparative analysis of two prominent annotation approaches to discourse relations (coherence relations) that were carried out on the same texts. We compare the annotation of implicit relations in the Penn Discourse Treebank 2.0, i.e. discourse relations not signaled by an explicit discourse connective, to the recently released analysis of signals of rhetorical relations in the RST Signalling Corpus (RST-SC). The intersection of corresponding pairs of relations is rather a small one, but it shows a clear tendency: unlike the overall signal distribution in the RST-SC, more than half of the signals in the studied intersection are of semantic type, formed mostly by loosely defined lexical chains. Our data transformation allows for a simultaneous depiction and detailed study of the two resources.


2014 ◽  
Vol 40 (4) ◽  
pp. 921-950 ◽  
Author(s):  
Rashmi Prasad ◽  
Bonnie Webber ◽  
Aravind Joshi

The Penn Discourse Treebank (PDTB) was released to the public in 2008. It remains the largest manually annotated corpus of discourse relations to date. Its focus on discourse relations that are either lexically-grounded in explicit discourse connectives or associated with sentential adjacency has not only facilitated its use in language technology and psycholinguistics but also has spawned the annotation of comparable corpora in other languages and genres. Given this situation, this paper has four aims: (1) to provide a comprehensive introduction to the PDTB for those who are unfamiliar with it; (2) to correct some wrong (or perhaps inadvertent) assumptions about the PDTB and its annotation that may have weakened previous results or the performance of decision procedures induced from the data; (3) to explain variations seen in the annotation of comparable resources in other languages and genres, which should allow developers of future comparable resources to recognize whether the variations are relevant to them; and (4) to enumerate and explain relationships between PDTB annotation and complementary annotation of other linguistic phenomena. The paper draws on work done by ourselves and others since the corpus was released.


2014 ◽  
Vol 31 ◽  
pp. 13-25
Author(s):  
Enrico Boone

This paper is concerned with the correct characterization of the licensing condition on clausal ellipsis and how it relates to the distribution of ellipsis. I argue, essentially following López (2000), that ellipsis is licensed when the ellipsis clause bears a relation to an antecedent in the discourse component. A relation between two discourse units can be established in two ways: (1) Either there holds a direct relation between the two discourse units or (2) there holds an anaphoric relation mediated by a discourse anaphor. In this paper, I show how this two-way distinction in setting up discourse relations accounts for the two-way split we find in the distribution of ellipsis.


PLoS ONE ◽  
2018 ◽  
Vol 13 (10) ◽  
pp. e0206057
Author(s):  
Gregor Weiss ◽  
Marko Bajec
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document