Publications

Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey

Published in Computational Linguistics Journal, 2018

This article provides an extensive overview of the literature related to the phenomenon of non-nominal-antecedent anaphora (also known as abstract anaphora or discourse deixis).

Recommended citation: Varada Kolhatkar, Adam Roussel, Stefanie Dipper, and Heike Zinsmeister. 2018. Anaphora with non-nominal antecedents in computational linguistics: A survey. Computational Linguistics, 44(3). https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00327

Using New York Times Picks to Identify Constructive Comments

Published in Proceedings of NLP meets journalism workshop, 2017

In this paper we use New York Times Picks as training examples for constructiveness and build computational models to identify constructive comments in news comments.

Recommended citation: Varada Kolhatkar and Maite Taboada. 2017. Using New York Times Picks to Identify Constructive Comments. In Proceedings of NLP meets journalism workshop, Association for Computational Linguistics, Copenhagen, Denmark, pages 100-105. https://aclanthology.info/papers/W17-4218/w17-4218

Constructive Language in News Comments

Published in Proceedings of the First Workshop on Abusive Language Online, 2017

This paper is about identifying constructive comments in news comments.

Recommended citation: Constructive Language in News Comments. In Proceedings of the First Workshop on Abusive Language Online. Association for Computational Linguistics, Vancouver, BC, Canada, pages 11-17. http://aclweb.org/anthology/W17-3002

Resolving shell nouns

Published in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014

Recommended citation: Varada Kolhatkar and Graeme Hirst. 2014. Resolving shell nouns. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 499–510, Doha, Qatar, October. Association for Computational Linguistics. http://www.aclweb.org/anthology/D14-1056

Interpreting anaphoric shell nouns using antecedents of cataphoric shell nouns as training data

Published in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 2013

This paper is about interpreting hard cases of anaphoric shell nouns (e.g., this issue) using relatively easy cases of cataphora-like shell nouns (e.g., the issue whether X).

Recommended citation: Varada Kolhatkar, Heike Zinsmeister, and Graeme Hirst. 2013. Interpreting anaphoric shell nouns using antecedents of cataphoric shell nouns as training data. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 300–310, Seattle, Washington, USA, October. Association for Computational Linguistics. http://www.anthology.aclweb.org/D/D13/D13-1030.pdf

Annotating anaphoric shell nouns with their antecedents

Published in The 7th Linguistic Annotation Workshop and Interoperability with Discourse, 2013

This paper is about annotating complex anaphoric expressions such as this issue or this fact.

Recommended citation: Varada Kolhatkar, Heike Zinsmeister, and Graeme Hirst. 2013. Annotating anaphoric shell nouns with their antecedents. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 112–121, Sofia, Bulgaria, August. Association for Computational Linguistics. http://www.aclweb.org/anthology/W13-2314

Resolving this-issue anaphora

Published in In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2012

This paper is about resolving complex anaphora in the form of demonstratives followed by a noun phrase.

Recommended citation: Varada Kolhatkar and Graeme Hirst. (2009). Resolving "this-issue" anaphora. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. pages 1255 -- 1265, Jeju Island, Korea, July. Association for Computational Linguistics. http://www.aclweb.org/anthology/D12-1115

Wordnet::Senserelate:: Allwords: a broad coverage word sense tagger that maximizes semantic relatedness

Published in The Annual Conference of the North American chapter of the association for computational linguistics, 2009

This paper is about a method to identify meaning of words in a given context.

Recommended citation: Pedersen, Ted and Kolhatkar, Varada: WordNet:: SenseRelate:: AllWords - A Broad Coverage Word Sense Tagger that Maximizes Semantic Relatedness. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Demonstration Session, pp. 17–20 (2009) http://www.aclweb.org/anthology/N09-5005