Paraphrase Database
Related Papers
From Paraphrase Database to Compositional Paraphrase Model and Back
AbstractThe Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how …...
Clustering Paraphrases by Word Sense
Automatically generated databases of English paraphrases have the drawback that they re- turn a single list of paraphrases for an input word or phrase. This means that all senses of …...
DCU-SEManiacs at SemEval-2016 Task 1: Synthetic Paragram Embeddings for Semantic Textual Similarity
We experiment with learning word representa- tions designed to be combined into sentence- level semantic representations, using an ob- jective function which does not directly make use of the supervised …...
Learning Typed Entailment Graphs with Global Soft Constraints
AbstractThis paper presents a new method for learning typed entailment graphs from text. We extract predicate-argument structures from multiple-source news corpora, and compute local distributional similarity scores to learn entailments …...
Using Paraphrases to Study Properties of Contextual Embeddings
AbstractWe use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide …...