Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger

Abstract

In this paper we approach word sense disambiguation and information extraction as a unified tagging problem. The task consists of annotating text with the tagset defined by the 41 Wordnet supersense classes for nouns and verbs. Since the tagset is directly related to Wordnet synsets, the tagger returns partial word sense disambiguation. Furthermore, since the noun tags include the standard named entity detection classes-person, location, organization, time, etc.-the tagger, as a by-product, returns extended named entity information. We cast the problem of supersense tagging as a sequential labeling task and investigate it empirically with a discriminatively-trained Hidden Markov Model. Experimental evaluation on the main sense-annotated datasets available, i.e., Semcor and Senseval, shows considerable improvements over the best known "first-sense" baseline.

Evaluation of Word Vector Representations by Subspace Alignment

“…WordNet (Fellbaum, 1998, WN) partitions nouns and verbs into coarse semantic categories known as supersenses (Ciaramita and Altun, 2006;Nastase, 2008 …”

When is multitask learning effective? Semantic sequence prediction under varying data conditions

“…While frame identification is normally treated as single classification, we keep the sequence-prediction paradigm so all main tasks rely on the same architecture. SUPERSENSES: We use the supersense version of SemCor (Miller et al, 1993) from (Ciaramita and Altun, 2006), with coarse-grained semantic labels like noun.person or verb.change. NER: The CONLL2003 shared-task data for named entity recognition for labels Person, Loc, etc.…”

Proceedings of The 9th Linguistic Annotation Workshop

“…Because prepositions are so frequent, so polysemous, and so crucial in establishing relations, we believe that a wide variety of NLP applications (including knowledge base construction, reasoning about events, summarization, paraphrasing, and translation) stand to benefit from automatic disambiguation of preposition supersenses. 2 Supersense inventories have also been described for nouns and verbs (Ciaramita and Altun, 2006;Schneider and Smith, 2015) and adjectives . Other inventories characterize semantic functions expressed via morphosyntax: e.g., tense/aspect (Reichart and Rappoport, 2010), definiteness (Bhatia et al, 2014, also hierarchical).…”