OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing

Abstract

The OPT submission to the Shared Task of the 2016 Conference on Natural Language Learning (CoNLL) implements a 'classic' pipeline architecture, combining binary classification of (candidate) explicit connectives, heuristic rules for non-explicit discourse relations, ranking and 'editing' of syntactic constituents for argument identification, and an ensemble of classifiers to assign discourse senses. With an end-toend performance of 27.77 F 1 on the English 'blind' test data, our system advances the previous state of the art (Wang & Lan, 2015) by close to four F 1 points, with particularly good results for the argument identification sub-tasks.

Window-Based Neural Tagging for Shallow Discourse Argument Labeling

“…The task of shallow discourse parsing was initiated by the development of the second version of the Penn Discourse Treebank (PDTB2) (Prasad et al, 2008b) and further by the shared tasks at CoNLL 2015 and 2016 (Xue et al, 2015(Xue et al, , 2016. Successful systems at these competitions were those of Wang et al (2015); Wang and Lan (2016); Oepen et al (2016). They followed the pipeline model of (Lin et al, 2014), which consists of successive tasks of connective identification, argument labeling, and sense classification for both explicit and implicit relations.…”

CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing

“…an implicit discourse relation. It is possible that no discourse relation exists, but such cases are rare and most systems choose to ignore such a possibility (Oepen et al, 2016;Laali et al, 2016;Chandrasekar et al, 2016). The extraction of the arguments for explicit discourse relations is more involved as their distribution is more diverse.…”

Improving Discourse Relation Projection to Build Discourse Annotated Corpora

“…The CLaC parser has been trained on Section 02-20 of the PDTB and can disambiguate the usage of the 100 English DCs listed in the PDTB with an F1-score of 0.90 and label them with their PDTB relation with an F1-score of 0.76 when tested on the blind test set of the CoNLL 2016 shared task (Xue et al, 2016). This parser was used because its performance is very close to that of the state of the art (Oepen et al, 2016) (i.e. 0.91 and 0.77 respectively), but is more efficient at running time than Oepen et al (2016).…”

“…This parser was used because its performance is very close to that of the state of the art (Oepen et al, 2016) (i.e. 0.91 and 0.77 respectively), but is more efficient at running time than Oepen et al (2016). Note that since the CoNLL 2016 blind test set was extracted from Wikipedia and its domain and genre differ significantly from the PDTB, the 0.90 and 0.76 F1-scores of the CLaC parser can be considered as an estimation of its performance on texts with a different domain such as Europarl.…”