Integrating Word Embeddings And Traditional Nlp Features To Measure Textual Entailment And Semantic Relatedness Of Sentence Pairs
2015 International Joint Conference on Neural Networks (IJCNN)(2015)
摘要
Recent years the distributed representations of words (i.e., word embeddings) have been shown to be able to significantly improve performance in many natural language processing tasks, such as pos-of-tag tagging, chunking, named entity recognition and sentiment polarity judgement, etc. However, previous tasks only involve a single sentence. In contrast, this paper evaluates the effectiveness of word embeddings in sentence pair classification or regression problems. Specifically, we propose novel simple yet effective features based on word embeddings and extract many traditional linguistic features. Then these features serve as input of a classification/regression algorithm in isolation and in combination. Evaluations are conducted on three sentence pair classification/regression tasks, i.e., textual entailment, cross-lingual textual entailment and semantic relatedness estimation. Experiments on benchmark datasets provided by Semantic Evaluation 2013 and 2014 showed that using word embeddings is able to significantly improve the performance and our results outperform the best achieved results so far.
更多查看译文
关键词
word embeddings,traditional NLP features,textual entailment measurement,sentence pairs,word distributed representations,natural language processing,pos-of-tag tagging,chunking,named entity recognition,sentiment polarity judgement,sentence pair classification,regression problems,traditional linguistic feature extraction,classification algorithm,regression algorithm,sentence pair regression tasks,cross-lingual textual entailment,semantic relatedness estimation,semantic evaluation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络