Context and Domain Knowledge Enhanced Entity Spotting in Informal Text

Abstract

Abstract. This paper explores the application of restricted relationship graphs (RDF) and statistical NLP techniques to improve named entity annotation in challenging Informal English domains. We validate our approach using on-line forums discussing popular music. Named entity annotation is particularly difficult in this domain because it is characterized by a large number of ambiguous entities, such as the Madonna album "Music" or Lilly Allen's pop hit "Smile". We evaluate improvements in annotation accuracy that can be obtained by restricting the set of possible entities using real-world constraints. We find that constrained domain entity extraction raises the annotation accuracy significantly, making an infeasible task practical. We then show that we can further improve annotation accuracy by over 50% by applying SVM based NLP systems trained on word-usages in this domain.

Linked Open Social Signals

“…Our collection module uses the Twitter Streaming API 5 . The Twitter Streaming API allows near-realtime access to various subsets of Twitter public statuses.…”

“…Entities such as Obama, Senate and Health Care Bill are mentioned within the text in microposts and represent finer grained semantic units that can be extracted. The task of Named Entity Recognition has been studied in casual text [5] and in more general form following both unsupervised and supervised machine learning approaches [9]. The best performing systems achieve up to 90.8 F 1 score [12] through supervised approaches, i.e.…”

Entity Reference Resolution via Spreading Activation on RDF-Graphs

“…Kleb et al [14] used concept-dependant text patterns for the disambiguation of text information. Gruhl et al [9] trained an SVM classifier in order to spot ontology entities. Here, many common ideas from information retrieval (IR) have been transferred to this domain.…”

“…Also, many try to transfer NLP approaches to this domain [26,14,9], mostly focusing on a specific domain, using domain-specific measures. So far, in the field of ontology-based entity disambiguation, domain-independent complex structures in semantic graphs have not been exploited.…”

Understanding Online Communities by Using Semantic Web Technologies

“…However when dealing with social media sites, performing NLP can be particularly difficult due to the typically informal nature of user posts, which tend to contain a lot of slang and contextdependant terms, with little attention given to spelling and grammar (Gruhl et al, 2009). Thus, while NLP algorithms are potentially very useful tools for investigating SNSs, there are challenges particular to user-generated content which must be handled.…”