Exploiting Semantic Role Resources for Preposition Disambiguation

Abstract

This article describes how semantic role resources can be exploited for preposition disambiguation. The main resources include the semantic role annotations provided by the Penn Treebank and FrameNet tagged corpora. The resources also include the assertions contained in the Factotum knowledge base, as well as information from Cyc and Conceptual Graphs. A common inventory is derived from these in support of definition analysis, which is the motivation for this work. The disambiguation concentrates on relations indicated by prepositional phrases, and is framed as word-sense disambiguation for the preposition in question. A new type of feature for word-sense disambiguation is introduced, using WordNet hypernyms as collocations rather than just words. Various experiments over the Penn Treebank and FrameNet data are presented, including prepositions classified separately versus together, and illustrating the effects of filtering. Similar experimentation is done over the Factotum data, including a method for inferring likely preposition usage from corpora, as knowledge bases do not generally indicate how relationships are expressed in English (in contrast to the explicit annotations on this in the Penn Treebank and FrameNet). Other experiments are included with the FrameNet data mapped into the common relation inventory developed for definition analysis, illustrating how preposition disambiguation might be applied in lexical acquisition.

Towards knowledge modeling and manipulation technologies: A survey

“…Knowledge in FN is represented as frames and an annotated corpus (Baker, 2012;Wandmacher et al, 2011). Frames represent generalizations over groups of words which illustrate equivalent situations, similar set of roles and related syntactic behaviour (Martínez-Santiago et al, 2015;O'Hara & Wiebe, 2009). In the theory of frame semantics, the roles or common situations which describes a frame are called frame elements (Das et al, 2014;Pimentel et al, 2012).…”

Developing a knowledge base for preposition sense disambiguation: A view from Role and Reference Grammar and FunGramKB

“…CRITERION #4). Once we focused on the #TIME dimension, we determined to create deeper metaconceptual levels, so that finer temporal dimensions would reflect the way that "the senses of prepositions tend to be closely related to one another" (O'Hara and Wiebe, 2009: 151). To avoid having to reinvent the wheel, we reviewed scientific literature to look for a taxonomy of temporal prepositions to be computerized for natural language understanding and to provide an adequate account of the RRG aspectual distinctions.…”

Joint learning of preposition senses and semantic roles of prepositional phrases

“…O'Hara and Wiebe (2003) proposed a WSD system to disambiguate function tags of prepositional phrases. An extended version of their work was recently presented in (O'Hara and Wiebe, 2009). Ye and Baldwin (2006) extended their work to a semantic role tagger specifically for prepositional phrases.…”