Local and Global Algorithms for Disambiguation to Wikipedia

By Lev-Arie Ratinov, Dan Roth, Doug Downey, Mike Anderson. 2011

755 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, 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 Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, methodology): “Extensions include joint resolution over all entities in a document (Ratinov et al., 2011; Globerson et al., 2016; Ganea and Hofmann, 2017), joint modeling with related tasks like textual similarity (Yamada et al., 2017b; Barrena et al., 2018) and cross-lingual modeling (Sil et al., 2018), for…”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, methodology): “To further collect examples that are not annotated by LDC, we ﬁrst run annotations on the corpus using a combination of Stanford’s statistical coreference system (Clark and Manning, 2015) and the Illinois Wik-iﬁer (Ratinov et al., 2011).”
Solving Hard Coreference Problems (2019, methodology): “To address this issue, we use the publicly avaiable Illinois Wikiﬁer (Cheng and Roth, 2013; Ratinov et al., 2011), a system that disambiguates mentions by mapping them into correct Wikipedia pages, to process the Wikipedia data.”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, methodology): “…techniques, including: random graph walks (Guo and Barbosa, 2016), personalized PageRank (Pershina et al., 2015), inter-mention voting (Ferragina and Scaiella, 2010), graph pruning (Hoffart et al., 2011), integer linear programming (Cheng and Roth, 2013), or ranking SVMs (Ratinov et al., 2011).”
A Survey on Context Learning (2017, methodology): “Table 4 [25] shows the superiority of the ensemble approach as compared to a simple conditional probability based approach (simulating an N-gram approach) and a modification of WLM framework [22] in doing Wikification task.”
Entity Linking at Web Scale (2012, background): “at (Hoffart et al., 2011; Ratinov et al., 2011) can take up to several seconds to link documents, which makes them difficult to run at Web scale without massive distributed computing.”
Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, background): “…of many useful natural language applications such as search query expansions (Jones et al., 2006), fact extraction for information retrieval (Pas¸ca et al., 2006) and automatic annotation of text with disambiguated Wikipedia links (Ratinov et al., 2011), among many others (Turney and Pantel, 2010).”
Collective Entity Disambiguation with Structured Gradient Tree Boosting (2018, background): “Joint entity disambiguation has been shown to signiﬁcantly boost performance when used in conjunction with other machine learning techniques (Ratinov et al., 2011; Hoffart et al., 2011).”
Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, methodology): “the similarity between vectors, different methods have been utilized, including dot-product [22], [62], [75], cosine similarity [44], [59], [62], [65], [66], [68], [70], [76], [79], [83], [90], [94],”
Deep Neural Architectures for Joint Named Entity Recognition and Disambiguation (2019, neutral): “ACE04 [21]: This dataset is a subset of ACE2004 coreference documents annotated by Amazon Mechanical Turk.”
Dynamic Knowledge-Base Alignment for Coreference Resolution (2013, methodology): “First, our alignment to a knowledgebase can benefit from more document-aware linking to entities, such as the Wikifier (Ratinov et al., 2011).”
Re-ranking for joint named-entity recognition and linking (2013, methodology): “To evaluate EL accuracy Bag-of-Freebase ids (BOF) evaluation analogous to the Bag-of-Titles (BOT) F1 evaluation as introduced by [15, 18].”
Named Entity Disambiguation for Noisy Text (2017, methodology): “This algorithm uses GLOW (Ratinov et al., 2011) for local disam-biguation.”
Entity Linking meets Word Sense Disambiguation: a Unified Approach (2014, background): “To overcome this issue a novel class of approaches have been proposed (Kulkarni et al., 2009; Ratinov et al., 2011; Hoffart et al., 2011) that exploit global and local features.”
MPQA 3.0: An Entity/Event-Level Sentiment Corpus (2015, background): “Or, to augment an automatic wikiﬁcation system (Ratinov et al., 2011) – in addition to relationships such as spouse and parents , the system could include information about whom or what the subject supports or opposes.”
Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks (2016, methodology): “These CNN features also clearly supersede the sparse features based on tf-idf (taken from (Ratinov et al., 2011)), showing that indeed that CNNs are better at learning semantic topic similarity than heuristics like tf-idf.”
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; Ferrag-ina and Scaiella, 2010).”
Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation (2015, background): “…2008b; Guo et al., 2013) to collective approaches that leverage the global topical coherence for joint disambiguation (Cucerzan, 2007; Kulkarni et al., 2009; Han et al., 2011; Ratinov et al., 2011; Hoffart et al., 2011; Cassidy et al., 2012; Shen et al., 2013; Liu et al., 2013; Huang et al., 2014).”
Improving Entity Linking by Modeling Latent Entity Type Information (2020, neutral): “pe Prediction In Methods MSNBC AQUAINT ACE2004 CWEB WIKI Avg prior p^(ejm) 89.3 83.2 84.4 69.8 64.2 78.18 Milne and Witten (2008) 78 85 81 64.1 81.7 77.96 Hoffart et al. (2011) 79 56 80 58.6 63 67.32 Ratinov et al. (2011) 75 83 82 56.2 67.2 72.68 Cheng and Roth (2013) 90 90 86 67.5 73.4 81.38 Guo an”
Learning Cross-Context Entity Representations from Text (2020, result): “The Wikiﬁcation task (Ratinov et al., 2011; Cheng & Roth, 2013), in particular, is similar to the work presented in this paper, as it requires systems to map mentions to the Wikipedia pages describing the entities mentioned.”