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

By Heeyoung Lee, Angel X. Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky. International Conference on Computational Logic, 2013

481 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/f3cd7890d3ad50cd1947d099bbd16f6da3b33a78

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

Citations in the corpus

IXA pipeline: Efficient and Ready to Use Multilingual NLP tools (2014, methodology): “This is illustrated by the evaluation results of the CoNLL 2011 Coreference Evaluation task (Lee et al., 2011; Lee et al., 2013), in which the Stanford’s system obtained the best results.”
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution (2019, background): “Due to its importance, pronoun resolution has seen a series of different approaches, such as rule-based systems (Lee et al., 2013) and end-to-end-trained neural models (Lee et al.”
Generating Coherent Event Schemas at Scale (2013, methodology): “We use the Stanford Co-reference system (Lee et al., 2013)6 to detect co-referring mentions.”
Argumentation Mining in User-Generated Web Discourse (2016, methodology): “– Binary features from Stanford Coreference Chain Resolver (Lee et al. 2013), e.”
Resolving Gendered Ambiguous Pronouns with BERT (2019, unknown): “They run 4 state-of-the-art coreference resolution models (Lee et al., 2013; Clark and Manning, 2015; Wiseman et al., 2016; Lee et al., 2017) on the OntoNotes and GAP datasets reporting F1 scores separately for masculine and feminine pronoun-named entity pairs (metrics M and F in the paper).”
Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, background): “A document graph consists of nodes that represent words and edges that represent various dependencies such as linear context (adjacent words), syntactic dependencies, and discourse relations (Lee et al., 2013; Xue et al., 2015).”
Design Challenges for Entity Linking (2015, methodology): “To this end, V INCULUM applies a coreference resolution system ( e.g. Lee et al. (2013)) to cluster coreferent mentions.”
Key Female Characters in Film Have More to Talk About Besides Men: Automating the Bechdel Test (2015, methodology): “We used Stanford’s named entity coreference resolution system (Lee et al., 2013) for finding coreferences.”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, background): “For example, the Stanford state-ofthe-art system [25] fails to link ‘Mohandas Gandhi’ to ‘Mahatma Gandhi’, and ‘Mrs.”
Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution (2015, methodology): “Both of these works are taken to contrast with the more popular approach of doing an initial non-anaphoric pruning step (Ng and Cardie, 2002; Rahman and Ng, 2009; Recasens et al., 2013; Lee et al., 2013).”
The GUM corpus: creating multilayer resources in the classroom (2016, methodology): “These features coincide in part with the features used deterministically by Lee et al. (2013), and also with those used to predict given status by Ritz (2010) (specifically grammatical function, proper noun inclusion and definiteness), but some of them are novel (rhetorical relations, interactions…”
Robustness in Coreference Resolution (2020, methodology): “As an example, in Moosavi & Strube (2014), we convert all entity-based features of Lee et al. (2013) to their corresponding pairwise features and yet we obtain on-par performance with that of Lee et al. (2013). The entity-based model of Clark & Manning (2016a) compared to their mention-ranking model”
Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves (2013, methodology): “NEC O extends the Stanford’s sieve-based model, in which a high recall mention detection phase is followed by a sequence of cluster merging operations ordered by decreasing precision (Raghunathan et al., 2010; Lee et al., 2013).”
Machine Comprehension with Syntax, Frames, and Semantics (2015, methodology): “We use the Stanford rule-based system for coreference resolution (Lee et al., 2013).”
Dense Event Ordering with a Multi-Pass Architecture (2014, background): “The top performer in CoNLL-2011 shared task was one such system (Lee et al., 2013).”
What Are You Talking About? Text-to-Image Coreference (2014, methodology): “Table 4 shows the accuracy of the Stanford’s coreference system [15] and our approach.”
Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval (2015, methodology): “Our pronoun resolver has an accuracy of 88.5% which is signiﬁcantly higher than the accuracy of 52.8% achieved by the coreference system of Lee et al. (2013).”