Pith

open record

sign in

arxiv: 1910.00637 · v2 · pith:3FFRNQNC · submitted 2019-10-01 · cs.CL

Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:3FFRNQNCrecord.jsonopen to challenge →

classification cs.CL
keywords paraphrasesdomain-specifictechniquesword-alignmentcorporaessentiagraphmethods
0
0 comments X
read the original abstract

Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic paraphrases, they often fail to identify domain-specific paraphrases (e.g., {staff, concierge} in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, Essentia, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high-quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.