Anaphora Resolution with the ARRAU Corpus

Poesio, Massimo; Grishina, Yulia; Kolhatkar, Varada; Moosavi, Nafise Sadat; Roesiger, Ina; Roussel, Adam; Simonjetz, Fabian; Uma, Alexandra; Uryupina, Olga; Yu, Juntao; Zinsmeister, Heike

doi:10.18653/v1/w18-0702

Cited by 52 publications

(67 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional coreference datasets Unlike traditional coreference annotations in datasets like those of Pradhan et al (2007), Ghaddar and Langlais (2016), Chen et al (2018) and Poesio et al (2018), which aim to obtain complete coref-erence clusters, our questions require understanding coreference between only a few spans. While this means that the notion of coreference captured by our dataset is less comprehensive, it is also less conservative and allows questions about coreference relations that are not marked in OntoNotes annotations.…”

Section: Related Workmentioning

confidence: 99%

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Dasigi¹,

Liu²,

Marasović³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

106

View full text Add to dashboard Cite

Machine comprehension of texts longer than a single sentence often requires coreference resolution. However, most current reading comprehension benchmarks do not contain complex coreferential phenomena and hence fail to evaluate the ability of models to resolve coreference. We present a new crowdsourced dataset containing more than 24K span-selection questions that require resolving coreference among entities in over 4.7K English paragraphs from Wikipedia. Obtaining questions focused on such phenomena is challenging, because it is hard to avoid lexical cues that shortcut complex reasoning. We deal with this issue by using a strong baseline model as an adversary in the crowdsourcing loop, which helps crowdworkers avoid writing questions with exploitable surface cues. We show that state-of-the-art reading comprehension models perform significantly worse than humans on this benchmark-the best model performance is 70.5 F 1 , while the estimated human performance is 93.4 F 1 .1 Links to dataset, code, models, and leaderboard available at https://allennlp.org/quoref.

show abstract

Section: Related Workmentioning

confidence: 99%

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Dasigi¹,

Liu²,

Marasović³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

106

View full text Add to dashboard Cite

show abstract

“…The second release of the ARRAU corpus, first published in Poesio and Artstein (2008), was used as the data basis for the shared task. It is a multi-domain corpus that aims at "providing much needed data for the next generation of coreference/anaphora resolution systems" (Uryupina et al, to appear).…”

Section: The Arrau Corpusmentioning

confidence: 99%

“…The first shared task on bridging resolution, co-located with the workshop on computational models of reference, anaphora and coreference (CRAC), deals with the task of bridging anaphora resolution in the RST domain of the ARRAU corpus (Poesio and Artstein, 2008). The dataset used in the shared task is part of the second release of the ARRAU corpus (Uryupina et al, to appear).…”

Section: Introductionmentioning

confidence: 99%

Rule- and Learning-based Methods for Bridging Resolution in the ARRAU Corpus

Roesiger¹

2018

Proceedings of the First Workshop on Computational Models Of Reference, Anaphora and Coreference

Self Cite

View full text Add to dashboard Cite

We present two systems for bridging resolution, which we submitted to the CRAC shared task on bridging anaphora resolution in the ARRAU corpus (track 2): a rulebased approach following Hou et al. (2014) and a learning-based approach.The reimplementation of Hou et al. (2014) achieves very poor performance when being applied to ARRAU. We found that the reason for this lies in the different bridging annotations: whereas the rule-based system suggests many referential bridging pairs, ARRAU contains mostly lexical bridging. We describe the differences between these two types of bridging and adapt the rule-based approach to be able to handle lexical bridging. The modified rule-based approach achieves reasonable performance on all (sub-)tasks and outperforms a simple learningbased approach.

show abstract

“…Recent related literature distinguishes between the following most common types of bridging relations: part-whole, set membership and generalized possession (Poesio et al, 2004), (Poesio and Artstein, 2008), (Hinrichs et al, 2005). In addition to these, in the Prague Dependency Treebank, contrast was annotated as a bridging relation as well (Nedoluzhko et al, 2009).…”

Section: Previous Annotation Effortsmentioning

confidence: 99%

Experiments on bridging across languages and genres

Grishina

2016

Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016)

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce a typology of bridging relations applicable to multiple languages and genres. After discussing our annotation guidelines, we describe annotation experiments on the German part of our parallel coreference corpus and show that our interannotator agreement results are reliable, considering both antecedent selection and relation assignment. In order to validate our theoretical model on other languages, we manually transfer German annotations to the English and Russian sides of the corpus and briefly discuss first results that suggest the promise of our approach. Furthermore, for the complete exploration of extended coreference relations, we exploit an existing near-identity scheme to augment our annotations with near-identity links, and we report on the results.

show abstract

Anaphora Resolution with the ARRAU Corpus

Cited by 52 publications

References 27 publications

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Rule- and Learning-based Methods for Bridging Resolution in the ARRAU Corpus

Experiments on bridging across languages and genres

Contact Info

Product

Resources

About