Lexical Features in Coreference Resolution: To be Used With Caution

Moosavi, Nafise Sadat; Strube, Michael

doi:10.18653/v1/p17-2003

Cited by 24 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, models may learn to memorize artifact and biases rather than truly learning (Gururangan et al, 2018;Moosavi and Strube, 2017;Agrawal et al, 2016), e.g., from political individuals often leaning towards one side of the truth spectrum. Additionally, language models have been shown to implicitly store world knowledge (Roberts et al, 2020), which in principle could enhance the aforementioned biases.…”

Section: Related Workmentioning

confidence: 99%

Automatic Fake News Detection: Are Models Learning to Reason?

Hansen¹,

Hansen²,

Lima³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Most fact checking models for automatic fake news detection are based on reasoning: given a claim with associated evidence, the models aim to estimate the claim veracity based on the supporting or refuting content within the evidence. When these models perform well, it is generally assumed to be due to the models having learned to reason over the evidence with regards to the claim. In this paper, we investigate this assumption of reasoning, by exploring the relationship and importance of both claim and evidence. Surprisingly, we find on political fact checking datasets that most often the highest effectiveness is obtained by utilizing only the evidence, as the impact of including the claim is either negligible or harmful to the effectiveness. This highlights an important problem in what constitutes evidence in existing approaches for automatic fake news detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Fake News Detection: Are Models Learning to Reason?

Hansen¹,

Hansen²,

Lima³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…They model these properties as continuous scores associated to each mention and bucketized for evaluation. Lexical overlap has also been mentioned in Coreference Resolution (Moosavi and Strube, 2017) where coreferent mentions tend to co-occur in the test and train sets. In this line of works, the impact of lexical overlap is measured either by separating performance depending on the property of mentions (seen or unseen) or with outof-domain evaluation with a test set from a different dataset with lower lexical overlap with the train set.…”

Section: Related Workmentioning

confidence: 99%

Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction

Taillé¹,

Guigue²,

Scoutheeten³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

State-of-the-art NLP models can adopt shallow heuristics that limit their generalization capability (McCoy et al., 2019). Such heuristics include lexical overlap with the training set in Named-Entity Recognition (Taillé et al., 2020a) and Event or Type heuristics in Relation Extraction (Rosenman et al., 2020). In the more realistic end-to-end RE setting, we can expect yet another heuristic: the mere retention of training relation triples. In this paper we propose several experiments confirming that retention of known facts is a key factor of performance on standard benchmarks. Furthermore, one experiment suggests that a pipeline model able to use intermediate type representations is less prone to over-rely on retention.

show abstract

“…In general, coreference resolution methods are divided into rulebased methods, machine learning-based (statistical), and deep learning-based groups. In rule-based methods [21][22][23][24][25][26][27][28], a collection of rules are handwritten by experts. These rules are implemented in an orderly manner to specify co-referents in the text.…”

Section: Related Workmentioning

confidence: 99%

Coreference Resolution Using Neural MCDM and Fuzzy Weighting Technique

Hourali¹,

Zahedi²,

Fateh³

2020

IJCIS

View full text Add to dashboard Cite

Coreference resolution has been an active field of research in the past several decades and plays a vital role in many areas such as information extraction, document summarization, machine translation, and question answering systems. This paper presents a new coreference resolution approach by incorporating RoBERTa embedding with a neural multi-criteria decision making (MCDM) method. The proposed model does not use any syntactic and dependency parser. Mentions were extracted from the text with an unhand engineered mention detector and features were extracted from a deep neural network. Next, the problem is modeled in the form of effective parameters of the performance such as error rate reduction and enhances the F1 by Kohonen MCDM neural network. The weights assigned to the features represent their importance and suggests the best reference for a mention where such weights are computed using a fuzzy weighting method. Comparing to state-of-the-art coreference resolution models, the simulation results show significant improvements for the proposed approach on different datasets in terms of precision and recall and achieving marginal improvements on the following datasets: English CoNLL-2012 shared task (+3.1 F1), Yahoo's news site (+6.6 F1), and English Gigaword (+7.04).

show abstract

Lexical Features in Coreference Resolution: To be Used With Caution

Cited by 24 publications

References 11 publications

Automatic Fake News Detection: Are Models Learning to Reason?

Automatic Fake News Detection: Are Models Learning to Reason?

Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction

Coreference Resolution Using Neural MCDM and Fuzzy Weighting Technique

Contact Info

Product

Resources

About