في هذه الورقة، نقترحنا بمحاذاة تمثيلات الجملة من لغات مختلفة إلى مساحة تضمين موحدة، حيث يمكن حساب أوجه التشابه الدلالي (كل من الصليب اللغوي والأونولينغ) بمنتج نقطة بسيطة.نماذج اللغة المدربة مسبقا صقلها بشكل جيد مع مهمة تصنيف الترجمة.يستخدم العمل الحالي (فنغ وآخرون.، 2020) جمل داخل الدفعة مثل السلبيات، والتي يمكن أن تعاني من مسألة السلبيات السهلة.نحن نتكيف مع MOCO (هو et al.، 2020) لمزيد من تحسين جودة المحاذاة.نظرا لأن النتائج التجريبية تظهر، فإن تمثيلات الجملة التي تنتجها نموذجنا لتحقيق أحدث الولاية الجديدة في العديد من المهام، بما في ذلك البحث عن التشابه التشابه TATOEBA EN-ZH (Artetxe Andschwenk، 2019b)، Bucc En-Zh BiteXTالتشابه النصي في 7 مجموعات البيانات.
In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product. Pre-trained language models are fine-tuned with the translation ranking task. Existing work (Feng et al., 2020) uses sentences within the same batch as negatives, which can suffer from the issue of easy negatives. We adapt MoCo (He et al., 2020) to further improve the quality of alignment. As the experimental results show, the sentence representations produced by our model achieve the new state-of-the-art on several tasks, including Tatoeba en-zh similarity search (Artetxe andSchwenk, 2019b), BUCC en-zh bitext mining, and semantic textual similarity on 7 datasets.
References used
https://aclanthology.org/
We study a new problem of cross-lingual transfer learning for event coreference resolution (ECR) where models trained on data from a source language are adapted for evaluations in different target languages. We introduce the first baseline model for
Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is genera
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the language that a predictive model has been trained on. Previous
We propose a method to distill a language-agnostic meaning embedding from a multilingual sentence encoder. By removing language-specific information from the original embedding, we retrieve an embedding that fully represents the sentence's meaning. T
Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of cross-lingual entity alignment under adversarial attacks. This paper