Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

  title={Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference},
  author={William B. Held and Dan Iter and Dan Jurafsky},
Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full n^2 pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory… 

Figures and Tables from this paper

Incorporating Centering Theory into Neural Coreference Resolution

This paper proposes to incorporate centering transitions derived from centering theory in the form of a graph into a neural coreference model, and improves the performance over the SOTA baselines.



Cross-Document Event Coreference Resolution Beyond Corpus-Tailored Systems

This work defines a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus and the Football Coreference Corpus, and compares a corpus-independent, feature-based system against a recent neural system developed for ECB+.

New Insights into Cross-Document Event Coreference: Systematic Comparison and a Simplified Approach

This study provides the first cross-validated evaluation on the ECB+ dataset; the first explicit evaluation of the pairwise event coreference classification step; and the first quantification of the effect of document clustering on system performance.

"Bag of Events" Approach to Event Coreference Resolution. Supervised Classification of Event Templates

We propose a new robust two-step approach to cross-textual event coreference resolution on news articles. The approach makes explicit use of event and discourse structure thereby compensating for

Breaking the Subtopic Barrier in Cross-Document Event Coreference Resolution

This work presents the first scalable approach for annotating cross-subtopic event coreference links, a highly valuable but rarely occurring type of cross-document link, and proposes crowdsourcing annotation on sentence level to achieve scalability.

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings

EPASE recognizes deep paraphrase relations in an event-specific context of sentences and can cover event paraphrases of more situations, bringing about a better generalization and the embeddings of argument roles are encoded into event embedding without relying on a fixed number and type of arguments, which results in the better scalability of EPASE.

End-to-end Neural Coreference Resolution

This work introduces the first end-to-end coreference resolution model, trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions.

Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling

This work proposes a pragmatic evaluation methodology which assumes access to only raw text -- rather than assuming gold mentions, disregards singleton prediction, and addresses typical targeted settings in CD coreference resolution.

Joint Entity and Event Coreference Resolution across Documents

A novel coreference resolution system that models entities and events jointly that handles nominal and verbal events as well as entities, and the joint formulation allows information from event coreference to help entity coreference, and vice versa.

Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events

We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as

Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization

This work proposes a neural network architecture with novel Clustering-Oriented Regularization (CORE) terms in the objective function that encourages the model to create embeddings of event mentions that are amenable to clustering.