CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing

Xue, Nianwen; Ng, Hwee Tou; Pradhan, S. Sandeep; Rutherford, Attapol T.; Webber, Bonnie; Wang, Chuan; Wang, Hongmin

doi:10.18653/v1/k16-2001

Cited by 95 publications

(90 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also experimented with pre-trained dependency-based word embeddings (Levy and Goldberg, 2014), but this yielded slightly worse results on the Dev set. (Wang and Lan, 2015) and CoNLL 2016 Shared Task best systems in Explicit (Jain, 2016) and Non-Explicit (Rutherford and Xue, 2016). F-Score is presented.…”

Section: Further Experiments On Non-explicit Relationsmentioning

confidence: 99%

Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Mihaylov

Frank

2016

Proceedings of the CoNLL-16 Shared Task

View full text Add to dashboard Cite

This paper describes our system for the CoNLL 2016 Shared Task's supplementary task on Discourse Relation Sense Classification. Our official submission employs a Logistic Regression classifier with several cross-argument similarity features based on word embeddings and performs with overall F-scores of 64.13 for the Dev set, 63.31 for the Test set and 54.69 for the Blind set, ranking first in the Overall ranking for the task. We compare the feature-based Logistic Regression classifier to different Convolutional Neural Network architectures. After the official submission we enriched our model for Non-Explicit relations by including similarities of explicit connectives with the relation arguments, and part of speech similarities based on modal verbs. This improved our Non-Explicit result by 1.46 points on the Dev set and by 0.36 points on the Blind set.

show abstract

Section: Further Experiments On Non-explicit Relationsmentioning

confidence: 99%

Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Mihaylov

Frank

2016

Proceedings of the CoNLL-16 Shared Task

View full text Add to dashboard Cite

show abstract

“…For example, Pitler et al (2009) report improvements in implicit relation sense classification with a sequence model. And more re-cent systems, including the best systems (Wang and Lan, 2015;Oepen et al, 2016) at the recent CONLL shared tasks on PDTB-style shallow discourse parsing (Xue et al, 2015(Xue et al, , 2016, while not using a sequence model, still incorporate features about neighboring relations. Such systems have many applications, including summarization (Louis et al, 2010), information extraction (Huang and Riloff, 2012), question answering (Blair-Goldensohn, 2007), opinion analysis (Somasundaran et al, 2008), and argumentation (Zhang et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Towards Full Text Shallow Discourse Relation Annotation: Experiments with Cross-Paragraph Implicit Relations in the PDTB

Prasad

Forbes-Riley

Lee

2017

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

Full text discourse parsing relies on texts comprehensively annotated with discourse relations. To this end, we address a significant gap in the inter-sentential discourse relations annotated in the Penn Discourse Treebank (PDTB), namely the class of cross-paragraph implicit relations, which account for 30% of inter-sentential relations in the corpus. We present our annotation study to explore the incidence rate of adjacent vs. non-adjacent implicit relations in cross-paragraph contexts, and the relative degree of difficulty in annotating them. Our experiments show a high incidence of non-adjacent relations that are difficult to annotate reliably, suggesting the practicality of backing off from their annotation to reduce noise for corpusbased studies. Our resulting guidelines follow the PDTB adjacency constraint for implicits while employing an underspecified representation of non-adjacent implicits, and yield 62% inter-annotator agreement on this task.

show abstract

“…Recent years have seen more and more works on this topic, including two CoNNL shared tasks Xue et al, 2016). The community most often uses the Penn Discourse Treebank (PDTB) (Prasad et al, 2008) as a resource, and has adopted the usual split into training and test data as used for other tasks such as parsing.…”

Section: Introductionmentioning

confidence: 99%

Do We Need Cross Validation for Discourse Relation Classification?

Wei¹,

Demberg

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 2

View full text Add to dashboard Cite

The task of implicit discourse relation classification has received increased attention in recent years, including two CoNNL shared tasks on the topic. Existing machine learning models for the task train on sections 2-21 of the PDTB and test on section 23, which includes a total of 761 implicit discourse relations. In this paper, we'd like to make a methodological point, arguing that the standard test set is too small to draw conclusions about whether the inclusion of certain features constitute a genuine improvement, or whether one got lucky with some properties of the test set, and argue for the adoption of cross validation for the discourse relation classification task by the community.

show abstract

CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing

Abstract: The CoNLL-2016 Shared Task is the second edition of the CoNLL-2015 Shared Task, now on Multilingual Shallow discourse parsing. Similar to the 2015 task, the goal of the shared task

Cited by 95 publications

References 33 publications

Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Towards Full Text Shallow Discourse Relation Annotation: Experiments with Cross-Paragraph Implicit Relations in the PDTB

Do We Need Cross Validation for Discourse Relation Classification?

Contact Info

Product

Resources

About