Work

Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition

Year: 2019

Type: article

Abstract: Building meaningful phrase representations is challenging because phrase meanings are not simply the sum of their constituent meanings. Lexical composition can shift the meanings of the constituent words and introduce implicit information. We tested a broad range of textual representations for their capacity to address these issues. We found that, as expected, contextualized word representations perform better than static word embeddings, more so on detecting meaning shift than in recovering implicit information, in which their performance is still far from that of humans. Our evaluation suite, consisting of six tasks related to lexical composition effects, can serve future research aiming to improve representations.

Source: Transactions of the Association for Computational Linguistics

DOI: 10.1162/tacl_a_00277

Authors: Vered Shwartz, Ido Dagan

Institution: Bar-Ilan University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Deutsche Forschungsgemeinschaft, Israel Science Foundation, Intel Collaboration Research Institute for Computational Intelligence

Award: G7805275943