KORE: keyphrase overlap relatedness for entity disambiguation

By Johannes Hoffart, Stephan Seufert, Dat Ba Nguyen, Martin Theobald, Gerhard Weikum. 2012

242 citations recorded by the source corpus.

Measuring the semantic relatedness between two entities is the basis for numerous tasks in IR, NLP, and Web-based knowledge extraction. This paper focuses on disambiguating names in a Web or text document by jointly mapping all names onto semantically related entities registered in a knowledge base. To this end, we have developed a novel notion of semantic relatedness between two entities represented as sets of weighted (multi-word) keyphrases, with consideration of partially overlapping phrases. This measure improves the quality of prior link-based models, and also eliminates the need for (usually Wikipedia-centric) explicit interlinkage between entities. Thus, our method is more versatile and can cope with long-tail and newly emerging entities that have few or no links associated with them. For efficiency, we have developed approximation techniques based on min-hash sketches and locality-sensitive hashing. Our experiments on semantic relatedness and on named entity disambiguation demonstrate the superiority of our method compared to state-of-the-art baselines.

Subfields: Artificial Intelligence, 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 Information Systems

In Natural Language Processing

Citations in the corpus

Autoregressive Entity Retrieval (2020, methodology): “We evaluate on seven out-of-domain test sets: MSNBC, Derczynski (Der) (Der-czynski et al., 2015), KORE 50 (K50) (Hoffart et al., 2012), N3-Reuters-128 (R128), N3-RSS-500 (R500) (R ¨ oder et al., 2014), and OKE challenge 2015 and 2016 (OKE15 and OKE16) (Nuzzolese et al., 2015).”
CM3: A Causal Masked Multimodal Model of the Internet (2022, methodology): “For both setting we evaluate on seven test sets: MSNBC, Derczynski (Der) (Derczynski et al., 2015), KORE 50 (K50) (Hoffart et al., 2012), N3-Reuters-128 (R128), N3-RSS-500 (R500) (R¨oder et al., 2014), and OKE challenge 2015 and 2016 (OKE15 and OKE16) (Nuzzolese et al., 2015).”
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training (2016, background): “Second, the relatively slow speed of current disambiguation systems, such as graph-based approaches (Hoffart et al., 2012; Agirre et al., 2014; Moro et al., 2014), or word-expert supervised sys-”
GERBIL - Benchmarking Named Entity Recognition and Linking consistently (2017, methodology): “Babelfy has been evaluated using six datasets: three from earlier SemEval tasks [48,43,42], one from a Senseval task [55] and two already used for evaluating AIDA [26,25].”
Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, unknown): “[111] proposed an efficient measure called KORE that calculates the topical coherence between two entities represented as sets of weighted (multi-word) keyphrases, with consideration of partially”
Entity Linking meets Word Sense Disambiguation: a Unified Approach (2014, methodology): “Our system outperforms all other approaches, with KORE-LSH-G getting closest, and Tagme and Wikiﬁer lagging behind on the KORE50 dataset.”
RDF2Vec: RDF Graph Embeddings for Data Mining (2016, unknown): “processing, and Web-based knowledge extractions [6].”
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation (2016, background): “Despite its simplicity, WLM yields state-of-the-art performance (Hoffart et al., 2012).”
End-to-End Neural Entity Linking (2018, methodology): “(2013); Hoffart et al. (2011); Steinmetz and Sack (2013) was to solve these two sub-problems independently.”
Towards a Seamless Integration of Word Senses into Downstream NLP Applications (2017, background): “Conventional knowledge-based disambiguation systems (Hoffart et al., 2012; Agirre et al., 2014; Moro et al., 2014; Ling et al., 2015; Pilehvar and Navigli, 2014) often rely on computationally expen-”
Robust named entity disambiguation with random walks (2018, background): “One successful strategy [13] computes the set-similarity involving (multiword) keyphrases about the mentions and the entities, collected from the KB.”
Methods for exploring and mining tables on Wikipedia (2013, background): “Experimenting with other SR measures that utilize other inputs, beyond Wikipedia links (e.g., [21,22]), is an item of future work.”
Robust Entity Linking via Random Walks (2014, methodology): “One successful strategy uses a text-based relatedness measure [12] based on weighted (multi-word) keyphrases about the entities, collected at the time the KB is built.”