Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules

Abstract

We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of deterministic, rule-based systems. Our sieve architecture applies a battery of deterministic coreference models one at a time from highest to lowest precision, where each model builds on the previous model's cluster output. The two stages of our sieve-based architecture, a mention detection stage that heavily favors recall, followed by coreference sieves that are precision-oriented, offer a powerful way to achieve both high precision and high recall. Further, our approach makes use of global information through an entity-centric model that encourages the sharing of features across all mentions that point to the same real-world entity. Despite its simplicity, our approach gives state-of-the-art performance on several corpora and genres, and has also been incorporated into hybrid state-of-the-art coreference systems for Chinese and Arabic. Our system thus offers a new paradigm for combining knowledge in rule-based systems that has implications throughout computational linguistics.

Different German and English Coreference Resolution Models for Multi-domain Content Curation Scenarios

“…Another system (Krug et al 2015) adapted the Stanford sieve approach (Lee et al 2013) for coreference resolution in the domain of German historic novels and evaluated it against a hand annotated corpus of 48 novel fragments with approximately 19,000 character references in total. An F1 score of 85.5 was achieved.…”

“…In this paper, we describe our forays into developing a German coreference resolution system. We attempt to adapt the Stanford CoreNLP (Manning et al 2014) Deterministic (rule-based) Coreference Resolution approach (Raghunathan et al 2010;Lee et al 2013) as well as the Stanford CoreNLP Mention Ranking (statistical) model (Clark and Manning 2015) to German. We also experiment with projection-based implementation, i.e., using Machine Translation and English coreference models to achieve German coreference resolution.…”

Constructing a Knowledge Base for Entertainment by Interlinking Multiple Data Sources

“…One is the pattern training based on seed data and training corpus; the other is the extraction work applying the patterns on sentences. Natural language processing technologies, such as named entity recognition [14], dependency parsing [15][16] [17], and co-reference resolution [18], are mandatory for this work. Finally, the extracted facts are transformed into triple format referencing to the designed ontology.…”

Proceedings of ACL 2017, System Demonstrations

“…The coreference resolution component in REACH adapts the algorithm of Lee et al (2013) to the biomedical domain, where it operates both over entity mentions (e.g., by resolving pronominal and nominal mentions such as "it" or "this protein" to the corresponding entity) and event mentions (e.g., "this interaction" is resolved to an actual event) .…”