Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations
arXiv:1805.02442
Abstract
Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.
arXiv commentLong paper at ACL 2018
References in corpus (5)
- Scikit-learn: Machine Learning in Python
- DyNet: The Dynamic Neural Network Toolkit
- SemEval-2013 Task 4: Free Paraphrases of Noun Compounds
- Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus
- Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model