Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution

By Sam Wiseman, Alexander M. Rush, Stuart M. Shieber, Jason Aaron Edward Weston. 2015

168 citations recorded by the source corpus.

We introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representations, and we report the best overall score on the CoNLL 2012 English test set to date.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Gender Bias in Coreference Resolution (2018, background): “Neural The move to deep neural models led to more powerful antecedent scoring functions, and the subsequent learned feature combinations resulted in new state-of-the-art performance (Wiseman et al., 2015; Clark and Manning, 2016b).”
What Does BERT Look at? An Analysis of BERT’s Attention (2019, background): “We also show the performance of a recent neural coreference system from Wiseman et al. (2015).”
End-to-end Neural Coreference Resolution (2017, methodology): “We experimented with these cost-sensitive alternatives, including margin-based variants (Wiseman et al., 2015; Clark and Manning, 2016a), but a simple maximum-likelihood objective proved to be most effective.”
Deep Reinforcement Learning for Mention-Ranking Coreference Models (2016, methodology): “In this section we ﬁrst describe a heuristic loss function incorporating this idea from Wiseman et al. (2015).”
Higher-Order Coreference Resolution with Coarse-to-Fine Inference (2018, background): “, 2017) that our proposed model builds upon, there is a large body of literature on coreference resolvers that fundamentally rely on scoring span pairs (Ng and Cardie, 2002; Bengtson and Roth, 2008; Denis and Baldridge, 2008; Fernandes et al., 2012; Durrett and Klein, 2013; Wiseman et al., 2015; Cla”
Improving Entity Linking by Modeling Latent Relations between Mentions (2018, methodology): “This method is similar to the way some mention-ranking coreference models deal with non-anaphoric mentions (e.g. Wiseman et al. (2015)).”
CorefQA: Coreference Resolution as Query-based Span Prediction (2019, background): “…and Kuhn, 2014; Clark and Manning, 2015, 2016; Wiseman et al., 2016) that directly model the representation of real-world entities and (2) mention-ranking models (Durrett and Klein, 2013; Wiseman et al., 2015; Lee et al., 2017) that learn to select the antecedent of each anaphoric mention.”
Robustness in Coreference Resolution (2020, background): “Discourse-old mentions are commonly referred to as anaphoric mentions in the coreference resolution literature, e.g. Zhou & Kong (2009), Ng (2009), Wiseman et al. (2015), Lassalle & Denis (2015), inter alia.”
BERT for Coreference Resolution: Baselines and Analysis (2019, methodology): “(2018) belongs to this family of models (Ng and Cardie, 2002; Bengtson and Roth, 2008; Denis and Baldridge, 2008; Fernandes et al., 2012; Durrett and Klein, 2013; Wiseman et al., 2015; Clark and Manning, 2016; Lee et al., 2017).”
Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric (2016, methodology): “Table 4 shows the scores of the state-of-the-art coreference resolvers developed by Wiseman et al. (2015), Martschat and Strube (2015), and Peng et al. (2015).”
Using Coreference Links to Improve Spanish-to-English Machine Translation (2017, background): “Interpolation between the best and worse candidate is considered (Wiseman et al., 2015; Bengtson and Roth, 2008).”
Learning Global Features for Coreference Resolution (2016, methodology): “Features We use the raw B ASIC + feature sets described by Wiseman et al. (2015), with the following modiﬁcations: • We remove all features from φ p that concate-nate a feature of the antecedent with a feature of the current mention, such as bi-head features.”