نقترح طريقة لتقطير معنى المعنى اللاإرادي للغات من تشفير الجملة متعددة اللغات.عن طريق إزالة المعلومات الخاصة باللغة من التضمين الأصلي، نسترجع التضمين الذي يمثله بشكل كامل معنى الجملة.تعتمد الطريقة المقترحة فقط على Corpora الموازي دون أي شروح بشرية.يتيح Edgedding المعنى لدينا تقدير تشابه تشابه التشابه من خلال حساب التشابه الجيبائي البسيط.النتائج التجريبية على حد كلا تقدير الجودة للترجمة الآلية ومهام التشابه النصي من الدلالات المتبادلة - أن طريقتنا تتفوق باستمرار على خطوط الأساس القوية باستخدام التضمين الأصلي متعدد اللغات.تعمل طريقتنا باستمرار على تحسين أداء أي تشفير جملة متعددة اللغات المدربة مسبقا، حتى في أزواج لغة الموارد المنخفضة حيث تتوفر عشرات الآلاف فقط من أزواج الجملة بالتوازي.
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. The proposed method relies only on parallel corpora without any human annotations. Our meaning embedding allows efficient cross-lingual sentence similarity estimation by simple cosine similarity calculation. Experimental results on both quality estimation of machine translation and cross-lingual semantic textual similarity tasks reveal that our method consistently outperforms the strong baselines using the original multilingual embedding. Our method consistently improves the performance of any pre-trained multilingual sentence encoder, even in low-resource language pairs where only tens of thousands of parallel sentence pairs are available.
References used
https://aclanthology.org/
Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity eval
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand
Semantic textual similarity (STS) systems estimate the degree of the meaning similarity between two sentences. Cross-lingual STS systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-a
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
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-s