Negative Sampling Improves Hypernymy Extraction Based on Projection Learning
نویسندگان
چکیده
We present a new approach to extraction of hypernyms based on projection learning and word embeddings. In contrast to classification-based approaches, projection-based methods require no candidate hyponym-hypernym pairs. While it is natural to use both positive and negative training examples in supervised relation extraction, the impact of negative examples on hypernym prediction was not studied so far. In this paper, we show that explicit negative examples used for regularization of the model significantly improve performance compared to the stateof-the-art approach of Fu et al. (2014) on three datasets from different languages.
منابع مشابه
Learning Semantic Network Patterns for Hypernymy Extraction
Current approaches of hypernymy acquisition are mostly based on syntactic or surface representations and extract hypernymy relations between surface word forms and not word readings. In this paper we present a purely semantic approach for hypernymy extraction based on semantic networks (SNs). This approach employs a set of patterns sub0(a1, a2) ← premise where the premise part of a pattern is g...
متن کاملUnsupervised Hypernym Detection by Distributional Inclusion Vector Embedding
Modeling hypernymy, such as poodle is-a dog, is an important generalization aid to many NLP tasks, such as entailment, relation extraction, and question answering. Supervised learning from labeled hypernym sources, such as WordNet, limit the coverage of these models, which can be addressed by learning hypernyms from unlabeled text. Existing unsupervised methods either do not scale to large voca...
متن کاملYap, Willy and Timothy Baldwin (2009) Experiments on Pattern-based Relation Learning, in Proceedings of the 18th ACM Conference on Information and Knowledge Management (CIKM 2009), Hong Kong, China
Relation extraction is the task of extracting semantic relations— such as synonymy or hypernymy—between word pairs from corpus data. Past work in relation extraction has concentrated on manually creating templates to use in directly extracting word pairs for a given semantic relation from corpus text. Recently, there has been a move towards using machine learning to automatically learn these pa...
متن کاملMinimally Supervised Multilingual Taxonomy and Translation Lexicon Induction
We present a novel algorithm for the acquisition of multilingual lexical taxonomies (including hyponymy/hypernymy, meronymy and taxonomic cousinhood), from monolingual corpora with minimal supervision in the form of seed exemplars using discriminative learning across the major WordNet semantic relationships. This capability is also extended robustly and effectively to a second language (Hindi) ...
متن کاملLearning Term Embeddings for Hypernymy Identification
Hypernymy identification aims at detecting if isA relationship holds between two words or phrases. Most previous methods are based on lexical patterns or the Distributional Inclusion Hypothesis, and the accuracy of such methods is not ideal. In this paper, we propose a simple yet effective supervision framework to identify hypernymy relations using distributed term representations (a.k.a term e...
متن کامل