Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution

By Simone Paolo Ponzetto, Michael Strube. North American Chapter of the Association for Computational Linguistics, 2006

307 citations recorded by the source corpus.

In this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6d375f8b45d8e5e961875bf74a89f32394759b89

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

CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes (2011, background): “Given that WordNet is a static ontology and as such has limitation on coverage, more recently, there have been successful attempts to utilize information from much larger, collaboratively built resources such as Wikipedia (Ponzetto and Strube, 2006).”
Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task (2011, methodology): “…new sieves that exploit semantics from WordNet, Wikipedia infoboxes, and Freebase records, drawing on previous coreference work using these databases (Ng & Cardie, 2002; Daum´e & Marcu, 2005; Ponzetto & Strube, 2006; Ng, 2007; Yang & Su, 2007; Bengston & Roth, 2008; Huang et al., 2009; inter alia).”
Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge (2012, background): “For ease of exposition, we will assume below that there are two candidate antecedents per sentence.”
Exploiting Wikipedia as External Knowledge for Named Entity Recognition (2007, background): “In fact, many studies that try to exploit Wikipedia as a knowledge source have recently emerged (Bunescu and Pas ¸ca, 2006; Toral and Mu˜ noz, 2006; Ruiz-Casado et al., 2006; Ponzetto and Strube, 2006; Strube and Ponzetto, 2006; Zesch et al., 2007).”
Supervised Noun Phrase Coreference Research: The First Fifteen Years (2010, methodology): “To address this problem, Denis and Baldridge (2008) apply an independently trained anaphoricity classifier to identify non-anaphoric NPs prior to ranking, and Rahman and Ng (2009) propose a model that jointly learns coreference and anaphoricity.”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, methodology): “Entity linking has been employed for coreference resolution (Ponzetto and Strube, 2006; Rahman and Ng, 2011; Ratinov and Roth, 2012) and coreference for entity linking (Cheng and Roth, 2013) shown that tighter integration of coreference and entity linking is promising (Hajishirzi et al., 2013;…”
Semantic Role Labeling (2010, unknown): “…exploited SRL—for example, for question answering (Moschitti et al. 2007; Shen and Lapata 2007; Surdeanu, Ciaramita, and Zaragoza 2008), for sentiment analysis (Johansson and Moschitti 2010), and for cross-document coreference resolution (Ponzetto and Strube 2006)—could have been attempted.”
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language (2015, unknown): “Our QA-driven annotation instructions are 5 pages.”
Turkers, Scholars, "Arafat" and "Peace": Cultural Communities and Algorithmic Gold Standards (2015, background): “[32]) to high-level technologies like search [6, 34] and information visualization systems [4, 37, 3].”
Dynamic Knowledge-Base Alignment for Coreference Resolution (2013, methodology): “This widely adopted model casts the problem as a series of binary classifications (Soon et al., 2001; Ng and Cardie, 2002; Ponzetto and Strube, 2006; Bengston and Roth, 2008; Stoyanov et al., 2010).”
Coreference Resolution with World Knowledge (2011, background): “Despite the usefulness of world knowledge for coreference resolution, early learning-based coreference resolvers have relied mostly on morphosyntactic features (e.g., Soon et al. (2001), Ng and Cardie (2002), Yang et al. (2003)).”
CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes (2012, background): “Automatic identification of coreferring entities and events in text has been an uphill battle for several decades, partly because it is a problem that requires world knowledge to solve and word knowledge is hard to define, and partly owing to the lack of substantial annotated data.”
Cross-lingual Name Tagging and Linking for 282 Languages (2017, methodology): “…pages have been used as additional features to improve various Information Extraction (IE) tasks, including name tagging (Kazama and Torisawa, 2007), coreference resolution (Paolo Ponzetto and Strube, 2006), relation extraction (Chan and Roth, 2010) and event extraction (Hogue et al., 2014).”
Easy Victories and Uphill Battles in Coreference Resolution (2013, background): “For feature conjunctions, other authors have exploited three classes (Lee et al., 2011) or automatically learned conjunction schemes (Fernandes et al., 2012; Lassalle and Denis, 2013), but to our knowledge we are the ﬁrst to do ﬁne-grained modeling of every pronoun.”
Learning-based Multi-Sieve Co-reference Resolution with Knowledge (2012, methodology): “There has been an increasing interest in knowledge-rich co-reference resolution (Ponzetto and Strube, 2006; Haghighi and Klein, 2010; Rah-man and Ng, 2011).”