TAGME: on-the-fly annotation of short text fragments (by wikipedia entities)

By Paolo Ferragina, Ugo Scaiella. 2010

879 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Communication, Information Systems, 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 Artificial Intelligence

In Communication

In Information Systems

In Natural Language Processing

Citations in the corpus

Simple and Effective Multi-Paragraph Reading Comprehension (2017, background): “ing a Bing web search of the question, and all Wikipedia articles about entities the entity linker TAGME (Ferragina and Scaiella, 2010) identifies in the question.”
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension (2017, methodology): “We therefore collected an additional set of evidence documents by applying TAGME, an off-the-shelf entity linker (Ferragina and Scaiella, 2010), to find Wikipedia entities mentioned in the question, and added the corresponding pages as evidence documents.”
Knowledge Enhanced Contextual Word Representations (2019, methodology): “, 2019) uses TAGME (Ferragina and Scaiella, 2010) to link entities to Wikidata, retrieves the associated entity embeddings, and fuses them into BERTBASE by fine-tuning.”
ERNIE: Enhanced Language Representation with Informative Entities (2019, methodology): “We also ﬁne-tune ERNIE on the distant supervised dataset, i.e., FIGER (Ling et al., 2015 we use TAGME (Ferragina and Scaiella, 2010) to extract the entity mentions in the sentences and link them to their corresponding entities in KGs.”
Fast and Accurate Annotation of Short Texts with Wikipedia Pages (2010, background): “1 A preliminary (and short) description of Tagme has been published as poster in CIKM 2010 [5].”
Construction of the Literature Graph in Semantic Scholar (2018, neutral): “O ﬀ -the-shelf: uses existing libraries, namely (Ferragina and Scaiella, 2010, TagMe) and biomedical research (Bio).”
CoLAKE: Contextualized Language and Knowledge Embedding (2020, methodology): “To annotate entities in the sentence, we use TAGME (Ferragina and Scaiella, 2010) to link mentions to entities in KGs.”
From TagME to WAT: a new entity annotator (2014, methodology): “We can easily describe the original voting procedure introduced in [6] as depicted in Algorithm 1.”
Robustness Gym: Unifying the NLP Evaluation Landscape (2021, background): “…et al., 2020], a system that combines existing state-of-the-art approaches, (iii) W AT [Piccinno and Ferragina, 2014] an extension of the TAGME [Ferragina and Scaiella, 2010] linker, and (iv) P OP , our simple heuristic baseline that picks the most popular entity among a set of candidate…”
Collective Entity Resolution with Multi-Focal Attention (2016, background): “Milne and Witten (2008) and Ferragina and Scaiella (2010) decompose the problem over mentions and select the candidate that maximizes their relatedness score, which includes relations to all other mentions.”
Fine-Grained Entity Recognition (2012, background): “For each linked segment m in a sentence, we found the corresponding Wikipedia entry e m via its anchor link, got its types from Person, Coach Organization, Sports_Team Test Figure 1: System architecture of FIGER.”
Implicit Entity Linking in Tweets (2016, methodology): “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].”
Document Retrieval Model Through Semantic Linking (2017, methodology): “In the recent years, the field of automated semantic annotation of textual content for extracting concepts and entities and linking them to external knowledge bases [23, 9], as well as the field of computing semantic similarities between knowledge base entities [26, 10] have been widely studied, and”
Local and Global Algorithms for Disambiguation to Wikipedia (2011, background): “Subsequent work on Wikification has stressed that assigned disambiguations for the same document should be related, introducing the global approach (Cucerzan, 2007; Milne and Witten, 2008b; Han and Zhao, 2009; Ferragina and Scaiella, 2010).”
Document Retrieval Using Entity-Based Language Models (2016, background): “, its neighboring terms or other term sequences marked as entities [15, 38].”
KORE: keyphrase overlap relatedness for entity disambiguation (2012, background): “[9], Ferragina & Scaiella [10], and Hoffart et al.”
Entity based Q&A Retrieval (2012, background): “Recently there has been lot of work addressing the problem of annotating text with links to Wikipedia entities (Mihalcea and Csomai, 2007; Bunescu and Pasca, 2006; Milne and Witten, 2008; Kulkarni et al., 2009; Ratinov et al., 2011; Ferragina and Scaiella, 2010).”