Exploiting Definitions for Frame Identification

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 2429–2434 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 2429 Exploiting Definitions for Frame Identification Tianyu Jiang and Ellen Riloff School of Computing University of Utah Salt Lake City, UT 84112 {tianyu, riloff}@cs.utah.edu Abstract Frame identification is one of the key chal- lenges for frame-semantic parsing. The goal of this task is to determine which frame best cap- tures the meaning of a target word or phrase in a sentence. We present a new model for frame identification that uses a pre-trained transformer model to generate representations for frames and lexical units (senses) using their formal definitions in FrameNet. Our frame identification model assesses the suitability of a frame for a target word in a sentence based on the semantic coherence of their meanings. We evaluate our model on three data sets and show that it consistently achieves better perfor- mance than previous systems. 1 Introduction Research on frame semantics has grown within the fields of natural language processing and cognitive science since the 1970s as the study of how we associate words and phrases with cognitive struc- tures called frames, which characterize a small ab- stract scene or situation (Fillmore, 1976, 1982). The Berkeley FrameNet project (Baker et al., 1998) provides an online lexical database for frame se- mantics together with a corpus of annotated doc- uments. Frame semantic parsing is the task of automatically extracting frame semantic structures from sentences. The process typically consists of three steps: target identification, which identifies frame-evoking predicates in the sentence; frame identification, which identifies the evoked frame for each target; and argument identification, which identifies arguments of a frame and labels them with semantic roles (frame elements). In this work, we focus on the frame identification problem. FrameNet 1.7 contains more than 13,000 lexical units (a word lemma with a sense), each associated with a semantic frame. A polysemous word is associated with multiple lexical units (one for each sense), and is therefore linked to multiple frames. The frame identification task requires a system to identify the most relevant frame for a target word or phrase based on its sentence context. Here is an example: The pandemic has sparked a lot of prob- lems for the economy. Given the target word sparked, the goal is to determine which frame should be triggered. The word lemma spark has two senses in FrameNet: “with obj. ignite” and “provide the stimulus for”. The former sense is associated with the Setting fire frame and the latter one is associated with the Cause to start frame. The Setting fire frame is defined as “this frame describes the creation of a flame...”, and the Cause to start frame is defined as “a cause, animate or inanimate, causes a pro- cess, the effect, to begin”. So Cause to start is the correct frame for this sentence. Previous work has shown the success of using feature engineering with linear classification mod- els …

Content truncated to 500 words