Coreference Semantics from Web Features

By Mohit Bansal, Daniel Klein. 2012

49 citations recorded by the source corpus.

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

WinoGrande (2019, methodology): “ooks for evidence for each answer candidate from the search result snippets. This IR-oriented approach comes from a line of work in coreference resolution (Kobdani et al. 2011; Ratinov and Roth 2012; Bansal and Klein 2012; Zheng et al. 2013; Peng, Khashabi, and Roth 2015). Ensemble Neural LMs Trinh ”
Toward Gender-Inclusive Coreference Resolution (2019, methodology): “The earliest example we know of that uses such knowledge sources is the end-to-end machine learning approach of Daumé III and Marcu [2005], which found substantial benefit by using mined mappings between names and professions to help resolve named entities like “Bill Clinton” to nominals like “presi”
Easy Victories and Uphill Battles in Coreference Resolution (2013, background): “However, while extremely high-precision approaches with carefully engineered features have been shown to be successful (Rahman and Ng, 2011a; Bansal and Klein, 2012; Recasens et al., 2013a), we conclude that capturing semantics in a data-driven, shallow manner”
Solving Hard Coreference Problems (2019, background): “A lot of recent work has attempted to utilize similar types of resources to improve coreference resolution (Rahman and Ng, 2011a; Ratinov and Roth, 2012; Bansal and Klein, 2012; Rahman and Ng, 2012).”
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks (2018, methodology): “(Bansal and Klein 2012), we randomly split the training into a 70/30 ratio to form a validation set).”
Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle* (2021, background): “…which found substantial beneﬁt by using mined mappings between names and professions to help resolve named entities like “Bill Clinton” to nominals like “president” (later examples include that of Rahman and Ng (2011) and Bansal and Klein (2012), who found less beneﬁt from a similar approach).”
A Knowledge Hunting Framework for Common Sense Reasoning (2018, methodology): “Other systems (Kobdani et al., 2011; Ratinov and Roth, 2012; Bansal and Klein, 2012; Zheng et al., 2013; Peng et al., 2015; Sharma et al., 2015) rely on similar techniques, i.”
A Constrained Latent Variable Model for Coreference Resolution (2013, background): “Finally, some research (Ratinov and Roth, 2012; Bansal and Klein, 2012; Rahman and Ng, 2011a) has tried to integrate world knowledge from web-based statistics or knowledge bases into a coreference system.”
Understandable Big Data: A survey (2015, background): “g: Denonym, Word inclusion in [57], Speaker identification in [55], Web features like General co-occurrence, Hearst co-occurrence, Entity-based context, Pronoun context in [58], etc.”
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules (2013, unknown): “Unsupervised or semi-supervised approaches to semantics such as Yang and Su (2007), Kobdani et al. (2011b), Uryupina et al. (2011b), Bansal and Klein (2012), or Recasens, Can, and Jurafsky (2013) may point the way forward.”
An Adversarial Winograd Schema Challenge at Scale (2019, background): “approach comes from an important line of work in coreference resolution (Kobdani et al., 2011; Ratinov and Roth, 2012; Bansal and Klein, 2012; Zheng et al., 2013; Peng et al., 2015; Sharma et al., 2015).”
Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves (2013, unknown): “Bansal and Klein (2012) use statistical analysis of Web n-gram features including lexical relations.”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, methodology): “We use the train/test split from Stoyanov et al. (2009), Haghighi and Klein (2010), and Bansal and Klein (2012).”