作者: B'eatrice Daille , Amir Hazem
DOI:
关键词: Question answering 、 Information retrieval 、 Synonym 、 Task (project management) 、 Principle of compositionality 、 Distributional semantics 、 Web search query 、 Computer science 、 Word (computer architecture) 、 Automatic summarization 、 Artificial intelligence 、 Natural language processing
摘要: Automatic synonyms and semantically related word extraction is a challenging task, useful in many NLP applications such as question answering, search query expansion, text summarization, etc. While different studies addressed the task of synonym extraction, only few investigations tackled problem acquiring multi-word terms (MWT) from specialized corpora. To extract pairs terms, we propose this paper an unsupervised semi-compositional method that makes use distributional semantics exploit compositional property shared by most MWT. We show our outperforms significantly state-of-the-art.