Collective entity linking in web text: a graph-based method

By Xianpei Han, Le Sun, Jun Zhao. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2011

424 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/1ccf386465081b6f8cad5a753827de7576dfe436

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

Re-ranking for joint named-entity recognition and linking (2013, result): “Ratinov et al. [18] point out that ﬁnding mentions using NER is a non-trivial task, and hence their experiments report linking performance using gold-standard mentions, as do several other recent EL systems [20, 4, 8].”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning (2016, background): “Entity linking, multi-document extraction and event coreference Our work also relates to the task of multi-document information extraction, where the goal is to connect different mentions of the same entity across input documents (Mann and Yarowsky, 2005; Han et al., 2011; Durrett and Klein, 2014).”
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).”
Learning Entity Representation for Entity Disambiguation (2013, methodology): “Another line of work focuses on collective disambiguation (Kulkarni et al., 2009; Han et al., 2011; Ratinov et al., 2011; Hoffart et al., 2011).”
Joint Entity Linking with Deep Reinforcement Learning (2019, methodology): “cent studies [14, 37] use fully-connected pairwise Conditional Random Field(CRF) model and exploit loopy belief propagation to estimate the max-marginal probability. Moreover, PageRank or Random Walk [16, 19, 42] are utilized to select the target entity for each mention. „e above probabilistic model”
Evaluating Entity Linking with Wikipedia (2013, methodology): “Recent experiments on other data sets have also explored evidence propagation (Han et al., 2011) and community detection (Hoffart et al.”
Robust Entity Linking via Random Walks (2014, methodology): “The approach closest to ours is that of Han et. al [10], which uses a random walk with restart to obtain a vector of relevance for all candidates of mentions, and considers the relevance value in the vector to be the relatedness be-tween a mention and its candidate.”
Robust named entity disambiguation with random walks (2018, methodology): “al [12], which uses a random walk with restart to obtain a vector of relevance for all candidates of mentions, and considers the relevance value in the vector to be the relatedness between a mention and its candidate.”
Knowledge base completion via search-based question answering (2014, methodology): “For this, we use standard entity linkage techniques, such as [6], which takes into account the lexical context of each mention, and [7], which takes into account other entities near the given mention, using joint inference.”
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],”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, background): “Several aspects of evidence are useful for entity disambiguation, such as semantic similarity, global consistency (Han, Sun, and Zhao 2011) and entity popularity (Cheng and Roth 2013; Durrett and Klein 2014; Huang et al. 2014; Heinzerling, Strube, and Lin 2017).”
From TagME to WAT: a new entity annotator (2014, methodology): “At the end we can confess that in attacking the ERD challenge we did the same mistake, spending lot of time and efforts in trying to improve and implement new disambiguation algorithms based on the recent trends in the literature [7, 18].”
Linking People in Videos with "Their" Names Using Coreference Resolution (2014, background): “1 Our setting differs slightly from classic coreference resolution in that we must resolve each mention to a fixed set of names, which is the problem of entity linking [18].”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning by Adam Yala (2017, background): “Our work also relates to the task of multi-document information extraction, where the goal is to connect different mentions of the same entity across input documents [15, 11, 6].”
Joint Entity Recognition and Disambiguation (2015, background): “Non-local features are also considered in linking (Ratinov et al., 2011; Han et al., 2011).”
Constrained Semi-supervised Learning in the Presence of Unanticipated Classes (2016, background): “In fact, we face a ‘chicken and egg’ problem, as most EL methods assume that KB entities have glosses, whereas we do not [60, 80].”