Non-adversarial unsupervised word translation

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

ملخص

Unsupervised word translation from nonparallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the impressive success of the recent techniques, they suffer from the typical drawbacks of generative adversarial models: sensitivity to hyper-parameters, long training time and lack of interpretability. In this paper, we make the observation that two sufficiently similar distributions can be aligned correctly with iterative matching methods. We present a novel method that first aligns the second moment of the word distributions of the two languages and then iteratively refines the alignment. Extensive experiments on word translation of European and Non-European languages show that our method achieves better performance than recent state-of-the-art deep adversarial approaches and is competitive with the supervised baseline. It is also efficient, easy to parallelize on CPU and interpretable.

اللغة الأصليةإنجليزيّة أمريكيّة
عنوان منشور المضيفProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
المحررونEllen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
الصفحات469-478
عدد الصفحات10
رقم المعيار الدولي للكتب (الإلكتروني)9781948087841
حالة النشرنُشِر - 2018
الحدث2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, بلجيكا
المدة: ٣١ أكتوبر ٢٠١٨٤ نوفمبر ٢٠١٨

سلسلة المنشورات

الاسمProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

!!Conference

!!Conference2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
الدولة/الإقليمبلجيكا
المدينةBrussels
المدة٣١/١٠/١٨٤/١١/١٨

All Science Journal Classification (ASJC) codes

  • !!Computational Theory and Mathematics
  • !!Computer Science Applications
  • !!Information Systems

بصمة

أدرس بدقة موضوعات البحث “Non-adversarial unsupervised word translation'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا