The Berkeley FrameNet Project

Abstract

FrameNet is a three-year NSF-supported project in corpus-based computational lexicography, now in its second year (NSF IRI-9618838, "Tools for Lexicon Building"). The project's key features are (a) a commitment to corpus evidence for semantic and syntactic generalizations, and (b) the representation of the valences of its target words (mostly nouns, adjectives, and verbs) in which the semantic portion makes use of frame semantics. The resulting database will contain (a) descriptions of the semantic frames underlying the meanings of the words described, and (b) the valence representation (semantic and syntactic) of several thousand words and phrases, each accompanied by (c) a representative collection of annotated corpus attestations, which jointly exemplify the observed linkings between "frame elements" and their syntactic realizations (e.g. grammatical function, phrase type, and other syntactic traits). This report will present the project's goals and workflow, and information about the computational tools that have been adapted or created in-house for this work.

A Hybrid Approach to Multi-document Summarization of Opinions in Reviews

“…These summary templates are composed by the text planner to build summary discourse plans. The JSPARKY sentence planner then converts input discourse plans into sentence plans, performing sentence ordering, sentence aggregation, cross-sentence reference resolution, sentence tense and mode (passive or active), discourse cue insertion, and the selection of some lexical forms from FrameNet (Baker et al, 1998) relations. Figure 2 illustrates a typical RST template representing a positive review summary and corresponding text output generated by JSPARKY.…”

Spoken language understanding: a survey

“…For this purpose, classes of objects, called frames, have been introduced [3]. Frames are structures identified by a name and a set of role-value pairs called slots.…”

Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings

“…FrameNet (FN) (Baker et al, 1998) is a lexicalsemantic resource manually built by FN experts. It embodies the theory of frame semantics (Fillmore, 1976): the frames capture units of meaning corresponding to prototypical situations.…”