Large-Scale Named Entity Disambiguation Based on Wikipedia Data

By Silviu Cucerzan. Conference on Empirical Methods in Natural Language Processing, 2007

1,282 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/1c909ac1c331c0c246a88da047cbdcca9ec9b7e7

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

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (2019, unknown): “Following the standard approach of using mention text and hyper-link information (Cucerzan, 2007; Ji and Grishman, 2011), we create a mapping (alias ta-”
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification (2018, background): “Thus, the document retrieval step can be framed as an entity linking problem (Cucerzan, 2007).”
YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia: Extended Abstract (2013, background): “Cucerzan [29] was the first to introduce this notion of joint disambiguation of all entity mentions in a text.”
Piggyback: Using Search Engines for Robust Cross-Domain Named Entity Recognition (2011, methodology): “Cucerzan (2007) uses Wikipedia and web search frequencies to improve NE disam-biguation, including simple web search frequencies BASE: lexical and input-text part-of-speech features 1 WORD ( k , i ) binary: w k = w i 2 POS ( k , t ) binary: w k has part-of-speech t 3 SHAPE ( k , i ) binary: w k has…”
KORE: keyphrase overlap relatedness for entity disambiguation (2012, background): “Cucerzan [8] was the first to recognize the potential of joint inference by mapping all named entities in a text simultaneously, aiming to enforce coherence among the chosen entities as expressed by their pair-wise semantic relatedness.”
ProjE: Embedding Projection for Knowledge Graph Completion (2016, background): “Knowledge Graphs (KGs) have become a crucial resource for many tasks in machine learning, data mining, and artificial intelligence applications including question answering [34], entity disambiguation [7], named entity linking [14], fact checking [32], and link prediction [28] to name a few.”
Collective Entity Resolution with Multi-Focal Attention (2016, methodology): “Cucerzan (2007) creates a relation vector for each candidate, and disambiguates each entity to the candidate whose vector is most similar to the aggregate (which includes both correct and incorrect labels).”
DBpedia - A crystallization point for the Web of Data (2009, unknown): “Further potential for the DBpedia extraction as well as for the NLP-eld in general lies in the idea to use huge bodies of background knowledge | like DBpedia | to improve the results of NLP-algorithms [11, 8 ].”
Implicit Entity Linking in Tweets (2016, background): “The word-level entity linking has been studied extensively for text like Wikipedia and News [2] [5] [9] [13] [14]; however, these approaches have proved to be ineffective on short and noisy text like tweets [4] [6].”
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation (2016, background): “NED has lately been extensively studied (Cucerzan, 2007; Mihalcea and Csomai, 2007; Milne and Witten, 2008b; Ratinov et al., 2011) and used as a fundamental component in numerous tasks, such as information extraction, knowledge base population (McNamee and Dang, 2009; Ji et al.”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, background): “A separate line of work has considered the problem of entity linking or “Wikiﬁcation” (Cucerzan, 2007; Milne and Witten, 2008; Ji and Grishman, 2011), where mentions are linked to entries in a given knowledge base.”
DBpedia spotlight: shedding light on the web of documents (2011, background): “Bunesco and Pasca [6], Cucerzan [7], Mihalcea and Cso-mai (Wikify”
Learning Text Representations for 500K Classification Tasks on Named Entity Disambiguation (2018, methodology): “Given a mention in context, NED methods (Cucerzan, 2007; Han and Sun, 2011; Ratinov et al., 2011; Lazic et al., 2015) typically rely on three models: (1) a mention model which collects possible entities which can be referred to by the mention string (aliases or surface forms), possibly weighted…”
Entity Linking at Web Scale (2012, background): “Linking each textual argument string to its corresponding Wikipedia entity, known as entity linking (Bunescu and Paşca, 2006; Cucerzan, 2007), would offer benefits such as semantic type information, integration with linked data resources (Bizer et al.”
Dynamic Knowledge-Base Alignment for Coreference Resolution (2013, background): “Alignment to an external knowledge-base has improved performance for a number of NLP and information extraction tasks, such as named-entity recognition (Cucerzan, 2007; Han and Zhao, 2009), cross-document coreference (Finin et al.”
Joint Entity Linking with Deep Reinforcement Learning (2019, background): “CoNLL [20] is annotated on Reuters news articles. It contains training (AIDA-Train), validation (AIDA-A) and test (AIDA-B) sets. ACE2004 [34] is a subset of the ACE2004 Coreference documents. MSNBC [9] contains top two stories in the ten news categories(Politics, Business, Sports etc.) AQUAINT [25] ”