Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora
Ernie-M: تعزيز التمثيل المتعدد اللغات من خلال محاذاة دلالات عبر اللغات مع مونولينغ
271
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أظهرت الدراسات الحديثة أن النماذج المتبادلة المدربة مسبقا تحقق أداء مثير للإعجاب في المهام المتقاطعة المتبادلة. يستفيد هذا التحسن من تعلم كمية كبيرة من مونوللقي والموازيات. على الرغم من أنه من المعترف به عموما أن شركة فورانيا الموازية أمر بالغ الأهمية لتحسين الأداء النموذجي، فإن الأساليب الحالية غالبا ما تكون مقيدة بحجم Corpora المتوازي، خاصة لغات الموارد المنخفضة. في هذه الورقة، نقترح Ernie-M، وهي طريقة تدريب جديدة تشجع النموذج على محاذاة تمثيل لغات متعددة مع شركة أحادية الأحادية، للتغلب على القيد أن أماكن حجم Corpus الموازي على الأداء النموذجي. إن رؤيتنا الرئيسية هي دمج الترجمة الخلفي في عملية التدريب المسبق. نحن نولد أزواج جملة زائفة بالموازاة على كائن أحادي مونولينغ لتمكين تعلم المحاذاات الدلالية بين لغات مختلفة، وبالتالي تعزيز النمذجة الدلالية للنماذج المتبقية. تظهر النتائج التجريبية أن Ernie-M يتفوق على النماذج الحالية عبر اللغات الحالية ويوفر نتائج حالة جديدة من بين الفنين في مختلف مهام المصب عبر اللغات. سيتم إجراء الرموز والنماذج المدربة مسبقا متاحة للجمهور.
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 generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose Ernie-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance. Our key insight is to integrate back-translation into the pre-training process. We generate pseudo-parallel sentence pairs on a monolingual corpus to enable the learning of semantic alignments between different languages, thereby enhancing the semantic modeling of cross-lingual models. Experimental results show that Ernie-M outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-lingual downstream tasks. The codes and pre-trained models will be made publicly available.
References used
https://aclanthology.org/
rate research
Read More
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 mode
ls 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.
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
he 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.
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework th
at further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels. Three different uncertainties are adapted and analyzed specifically for the cross lingual transfer: Language Heteroscedastic/Homoscedastic Uncertainty (LEU/LOU), Evidential Uncertainty (EVI). We evaluate our framework with uncertainties on two cross-lingual tasks including Named Entity Recognition (NER) and Natural Language Inference (NLI) covering 40 languages in total, which outperforms the baselines significantly by 10 F1 for NER on average and 2.5 accuracy for NLI.
Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE
can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.
Multilingual language models exhibit better performance for some languages than for others (Singh et al., 2019), and many languages do not seem to benefit from multilingual sharing at all, presumably as a result of poor multilingual segmentation (Pyy
sal o et al., 2020). This work explores the idea of learning multilingual language models based on clustering of monolingual segments. We show significant improvements over standard multilingual segmentation and training across nine languages on a question answering task, both in a small model regime and for a model of the size of BERT-base.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
