Semi-compositional Method for Synonym Extraction of Multi-Word Terms

• Main Authors: Hazem, Amir, Daille, Béatrice
• Other Authors: Laboratoire d'Informatique de Nantes Atlantique (LINA), Mines Nantes (Mines Nantes)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-Centre National de la Recherche Scientifique (CNRS), Traitement Automatique du Langage Naturel (LS2N - équipe TALN ), Laboratoire des Sciences du Numérique de Nantes (LS2N), Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT), ELRA, ANR-12-CORD-0029,TermITH,TERMinologie et Indexation de Textes en sciences Humaines(2012)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2014
• Subjects: Synonyms; Multi-word terms; Compositionality; Distributional semantics; Unsupervised methods; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; Iceland
• Online Access: https://hal.science/hal-01171093; https://hal.science/hal-01171093/document; https://hal.science/hal-01171093/file/679_Paper.pdf

International audience 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 word synonym extraction, only a few investigations tackled the problem of acquiring synonyms of multi-word terms (MWT) from specialized corpora. To extract pairs of synonyms of multi-word terms, we propose in this paper an unsupervised semi-compositional method that makes use of distributional semantics and exploit the compositional property shared by most MWT. We show that our method outperforms significantly the state-of-the-art.