Paraphrase to explicate: Revealing implicit noun-compound relations

Vered Shwartz, Ido Dagan

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

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.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيفACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
ناشرAssociation for Computational Linguistics (ACL)
الصفحات1200-1211
عدد الصفحات12
رقم المعيار الدولي للكتب (الإلكتروني)9781948087322
المعرِّفات الرقمية للأشياء
حالة النشرنُشِر - 2018
الحدث56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, أستراليا
المدة: ١٥ يوليو ٢٠١٨٢٠ يوليو ٢٠١٨

سلسلة المنشورات

الاسمACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
مستوى الصوت1

!!Conference

!!Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
الدولة/الإقليمأستراليا
المدينةMelbourne
المدة١٥/٠٧/١٨٢٠/٠٧/١٨

All Science Journal Classification (ASJC) codes

  • !!Software
  • !!Computational Theory and Mathematics

بصمة

أدرس بدقة موضوعات البحث “Paraphrase to explicate: Revealing implicit noun-compound relations'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا