A Multi-Pass Sieve for Coreference Resolution

By Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan Thitte, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, Christopher D. Manning. 2010

460 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

Citations in the corpus

Toward Gender-Inclusive Coreference Resolution (2019, background): “…resolution systems on our ablated data: the AI2 system [AI2; Gardner et al. 2017], hugging face, which is a neural system based on spacy, and the Stanford deterministic [SfdD; Raghunathan et al. 2010], statistical [SfdS; Clark and Manning 2015] and neural [SfdN; Clark and Manning 2016] systems.”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, methodology): “ARIS applies the Stanford dependency parser, named entity recognizer and coreference resolution system to the problem text (de Marneffe et al., 2006; Finkel et al., 2005; Raghunathan et al., 2010).”
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods (2018, methodology): “In this section we evaluate of three representative systems: rule based, Rule , (Raghunathan et al., 2010), feature-rich, Feature , (Durrett and Klein, 2013), and end-to-end neural (the current state-of-the-art), E2E , (Lee et al., 2017).”
End-to-end Neural Coreference Resolution (2017, methodology): “However, the learning problem is challenging and, until very recently, handengineered systems built on top of automatically produced parse trees (Raghunathan et al., 2010) outperformed all learning approaches.”
Deep Reinforcement Learning for Mention-Ranking Coreference Models (2016, methodology): “Our experiments were run using predicted mentions from Stanford’s rule-based coreference system (Raghunathan et al., 2010).”
Assessing The Factual Accuracy of Generated Text (2019, neutral): “NER is followed by co-reference resolution4 [6, 11, 24, 25].”
A Constrained Latent Variable Model for Coreference Resolution (2013, methodology): “This capability is very desirable as shown by the success of the rule-based deterministic approach of Raghunathan et al. (2010) in the CoNLL shared task 2011 (Pradhan et al., 2011).”
CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes (2012, background): “These could be better at capturing the differences in gender and number signaled by certain morphemes than hand-crafted rules. chen built upon the sieve architecture proposed in Raghunathan et al. (2010) and added one more sieve — head match — for Chinese and modified two sieves.”
Entity Linking: Finding Extracted Entities in a Knowledge Base (2013, background): “This task has a long history in the NLP community [34] which still receives significant attention [37, 15, 43].”
Evaluation of named entity coreference (2019, methodology): “Systems We evaluate the Stanford coreference system, with its deterministic (Raghunathan et al., 2010; Lee et al., 2011; Recasens et al., 2013), statistical (Clark and Manning, 2015) and neural (Clark and Manning, 2016a,b) versions, and the neural end-to-end systems of (Lee et al., 2017) and (Lee…”
The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution (2018, methodology): “In this section, we compare the performance of ﬁve representative coreference systems on our task: Stanford’s rule-based system (Raghunathan et al., 2010) ( Rule ), Stanford’s statistical system (Clark and Manning, 2015) ( Stat ), Clark and Manning (2016)’s deep reinforcement learning system (…”
Image retrieval using scene graphs (2015, methodology): “To make use of such a description for image retrieval, we would need to resolve co-references in the text [53, 30, 39], perform relationship extraction to convert the unstructured text into structured tuples [47], and ground the entities of the tuples into regions of the image described by the text…”
Entity-Centric Coreference Resolution with Model Stacking (2015, methodology): “…incorporated successfully into entity-centric coreference systems that build up coreference clusters incrementally, using the information from the partially completed coreference chains produced so far to guide later decisions (Raghunathan et al., 2010; Stoyanov and Eisner, 2012; Ma et al., 2014).”
Improving Coreference Resolution by Learning Entity-Level Distributed Representations (2016, methodology): “Entity-level information has also been incorporated in coreference systems using joint inference (McCallum and Wellner, 2003; Poon and Domingos, 2008; Haghighi and Klein, 2010) and systems that build up coreference clusters incrementally (Luo et al., 2004; Yang et al., 2008; Raghunathan et al., 2010”
IXA pipeline: Efficient and Ready to Use Multilingual NLP tools (2014, result): “The results show a pattern which has also been shown in other results reported with other evaluation sets (Raghunathan et al., 2010), namely, the fact that a large part of the performance of the multi pass sieve system is based on a set of signiﬁcant sieves.”
Understandable Big Data: A survey (2015, background): “In this domain, improvements are not related to Big Data features and are mainly focused on enrichment and precision of new lexical and syntactic features and global inference [56,55,57].”