J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features

J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features Dat Ba Nguyen1, Martin Theobald2, Gerhard Weikum1 1 Max Planck Institute for Informatics 2 University of Ulm {datnb,weikum}@mpi-inf.mpg.de martin.theobald@uni-ulm.de Abstract Methods for Named Entity Recognition and Disambiguation (NERD) perform NER and NED in two separate stages. Therefore, NED may be penalized with respect to precision by NER false positives, and suffers in recall from NER false negatives. Conversely, NED does not fully exploit information computed by NER such as types of mentions. This paper presents J-NERD, a new approach to perform NER and NED jointly, by means of a prob- abilistic graphical model that captures men- tion spans, mention types, and the mapping of mentions to entities in a knowledge base. We present experiments with different kinds of texts from the CoNLL’03, ACE’05, and ClueWeb’09-FACC1 corpora. J-NERD con- sistently outperforms state-of-the-art competi- tors in end-to-end NERD precision, recall, and F1. 1 Introduction Motivation: Methods for Named Entity Recogni- tion and Disambiguation, NERD for short, typically proceed in two stages: • At the NER stage, text spans of entity mentions are detected and tagged with coarse-grained types like Person, Organization, Location, etc. This is typically performed by a trained Condi- tional Random Field (CRF) over word sequences (e.g., Finkel et al. (2005)). • At the NED stage, mentions are mapped to en- tities in a knowledge base (KB) based on con- textual similarity measures and the semantic co- herence of the selected entities (e.g., Cucerzan (2014); Hoffart et al. (2011); Ratinov et al. (2011)). This two-stage approach has limitations. First, NER may produce false positives that can misguide NED. Second, NER may miss out on some entity mentions, and NED has no chance to compensate for these false negatives. Third, NED is not able to help NER, for example, by disambiguating “easy” mentions (e.g., of prominent entities with more or less unique names), and then using the entities and knowledge about them as enriched features for NER. Example: Consider the following sentences: David played for manu, real, and la galaxy. His wife posh performed with the spice girls. This is difficult for NER because of the absence of upper-case spelling, which is not untypical in so- cial media, for example. Most NER methods will miss out on multi-word mentions or words that are also common nouns (“spice”) or adjectives (“posh”, “real”). Typically, NER would pass only the men- tions “David”, “manu”, and “la” to the NED stage, which then is prone to many errors like mapping the first two mentions to any prominent people with first names David and Manu, and mapping the third one to the city of Los Angeles. With NER and NED per- formed jointly, the possible disambiguation of “la galaxy” to the soccer club can guide NER to tag the right mentions with the right types (e.g., recogniz- ing that “manu” could be a short name for a soccer team), which in turn helps NED to map “David” to the right entity David Beckham. Contribution: This …

Content truncated to 500 words