Learning paraphrasing for multi-word expressions

Abstract

In this paper, we investigate the impact of context for the paraphrase ranking task, comparing and quantifying results for multi-word expressions and single words. We focus on systematic integration of existing paraphrase resources to produce paraphrase candidates and later ask human annotators to judge paraphrasability in context. We first conduct a paraphrase-scoring annotation task with and without context for targets that are i) single- and multi-word expressions ii) verbs and nouns. We quantify how differently annotators score paraphrases when context information is provided. Furthermore, we report on experiments with automatic paraphrase ranking. If we regard the problem as a binary classification task, we obtain an F1-score of 81.56% and 79.87% for multi-word expressions and single words resp. using kNN classifier. Approaching the problem as a learning-to-rank task, we attain MAP scores up to 87.14% and 91.58% for multiword expressions and single words resp. using LambdaMART, thus yielding high-quality contextualized paraphrased selection. Further, we provide the first dataset with paraphrase judgments for multi-word targets in context.