Using Encyclopedic Knowledge for Named entity Disambiguation

By Razvan C. Bunescu, Marius Pasca. Conference of the European Chapter of the Association for Computational Linguistics, 2006

961 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9d0616073ac858d53474a696455b3ffcf86ea208

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

AIDA (2011, background): “NLP research has harnessed Wikipedia as a means for linking words and phrases onto canonical entities [3, 6].”
Entity Linking at Web Scale (2012, methodology): “• New York Yankees at 8,647 inlinks • New York University at 7,983 inlinks After obtaining a list of candidate entities, we employ a context matching (Bunescu and Pas¸ca, 2006) step that uses cosine similarity to measure the semantic distance between the assertion and each can-didate’s Wikipedia…”
Annotating and searching web tables using entities, types and relationships (2010, background): “Early work [10, 15, 3] disambiguated each potential entity mention independent of others.”
Collective annotation of Wikipedia entities in web text (2009, methodology): “Data used by Bunescu and Pasca [3] was not publicly available.”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, background): “Among all these aspects, it has been widely accepted that semantic similarity between the context of an entity mention and its target entity candidates is the key to resolve the ambiguity (Bunescu and Pasca 2006; Cucerzan 2007; Ji and Grishman 2011; Shen, Wang, and Han 2015).”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, background): “Heuristics (Mihalcea and Csomai, 2007) or linear classifiers (Bunescu and Pasca, 2006; Cucerzan, 2007; Ratinov et al., 2011; McNamee et al., 2009) are used over these features to rank entity candidates for linking.”
Zero-Shot Entity Linking by Reading Entity Descriptions (2019, background): “Standard EL While there are numerous differences between EL datasets (Bunescu and Pasca, 2006; Ling et al., 2015), most focus on a standard setting where mentions from a comprehensive test entity dictionary (often Wikipedia) are seen during training, and rich statistics and meta-data can be utilized”
REL: An Entity Linker Standing on the Shoulders of Giants (2020, background): “It was also them who first recognized the utility of Wikipedia as a largescale knowledge repository to disambiguate against [4, 6].”
YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia: Extended Abstract (2013, background): “Named entity disambiguation for Wikipedia entities dates back to Bunescu and Pasca [28], with substantial improvements by Cucerzan [29], Milne and Witten [30], and Kulkarni et al.”
BabelNet: Building a Very Large Multilingual Semantic Network (2010, background): “These include, among others, text summarization (Nastase, 2008), Named Entity Recognition (Bunescu and Pas¸ca, 2006), Question Answering (Harabagiu et al., 2000) and text categorization (Gabrilovich and Markovitch, 2006).”
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, background): “These include, among others, text summarization [82], named entity disambiguation [16], Question Answering [48] [66], text categorization [40] [130] [88], coreference resolution [107] [111], sentiment analysis [125] [129] and plagiarism detection [10].”
Learning Text Representations for 500K Classification Tasks on Named Entity Disambiguation (2018, background): “…known as Entity Linking or Entity Resolution, is a task where entity mentions in running text need to be linked to its entity entry in a Knowledge Base (KB), such as Wikidata, Wikipedia or other derived resources like DBpedia (Bunescu and Pasca, 2006; McNamee and Dang, 2009; Hoffart et al., 2011).”
Learning-based Multi-Sieve Co-reference Resolution with Knowledge (2012, methodology): “We are the ﬁrst to use context-sensitive disambiguation to Wikipedia, which received a lot of attention recently (Bunescu and Pasca, 2006; Cucerzan, 2007; Mihalcea and Csomai, 2007; Milne and Witten, 2008; Ratinov et al., 2011).”
Neural Cross-Lingual Entity Linking (2017, background): “Previous works in EL (Bunescu and Pasca 2006; Mihalcea and Csomai 2007) involved finding the similarity of the context in the source document and the context of the candidate Wikipedia titles.”
Local and Global Algorithms for Disambiguation to Wikipedia (2011, methodology): “A local approach solves the following optimization problem: Γ∗ local = arg max Γ N∑ i=1 φ(mi, ti) (1) Local D2W approaches, exemplified by (Bunescu and Pasca, 2006) and (Mihalcea and Csomai, 2007), utilize φ functions that assign higher scores to titles with content similar to that of the input…”
Highly Parallel Autoregressive Entity Linking with Discriminative Correction (2021, unknown): “Task Entity Linking (EL) is the task of predicting a set Y of mention-entity pairs contained in some input text x (Hoffmann et al., 2011).”
Named Entity Disambiguation for Noisy Text (2017, background): “Local vs Global NED Early work on Named Entity Disambiguation, such as Bunescu and Pas¸ca (2006) and Mihalcea and Csomai (2007) focused on local approaches where each mention is disambiguated separately using hand-crafted features.”
Extracting Lexical Semantic Knowledge from Wikipedia and Wiktionary (2008, background): “…categorization (Gabrilovich and Markovitch, 2006), information extraction (Ruiz-Casado et al., 2005), information retrieval (Gurevych et al., 2007), question answering (Ahn et al., 2004), computing semantic relatedness (Zesch et al., 2007), or named entity recognition (Bunescu and Pasca, 2006).”