Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Zero-Shot Cross-Lingual Transfer Learning via Robust Training
تحسين التعلم تحويل صفرية عبر اللغات عبر التدريب القوي
253
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تشفير لغة متعددة اللغات المدربة مسبقا، مثل Bert متعدد اللغات و XLM-R، إظهار إمكانات كبيرة للتحويل الصفر - عبر اللغات. ومع ذلك، فإن هذه اللوائح متعددة اللغات لا تحيي بالتحديد الكلمات والعبارات عبر اللغات. على وجه الخصوص، يتطلب محاذاة التعلم في مساحة التضمين متعددة اللغات عادة على مستوى الجملة أو المستوى الموازي على مستوى Word، وهي مكلفة يتم الحصول عليها لغات الموارد المنخفضة. بديل هو جعل التشفير متعددة اللغات أكثر قوة؛ عند ضبط التشفير باستخدام المهمة المصدرة للمهمة، نربط التشفير لتتسامح مع الضوضاء في المساحات التضمين السياقية بحيث لا تتماشى تمثيلات اللغات المختلفة بشكل جيد، لا يزال بإمكان النموذج تحقيق أداء جيد على الصفر بالرصاص عبر اللغات نقل. في هذا العمل، نقترح استراتيجية تعليمية لتدريب النماذج القوية عن طريق رسم الروابط بين الأمثلة الخصومة وحالات فشل النقل الصفرية عبر اللغات. نعتمد اثنين من أساليب التدريب القوية المستخدمة على نطاق واسع، والتدريب الخصوم والتنعيم العشوائي، لتدريب النموذج القوي المرغوب فيه. توضح النتائج التجريبية أن التدريب القوي يحسن نقل صفرية عبر اللغات على مهام تصنيف النص. التحسن هو أكثر أهمية في إعداد النقل المتبادل المعمم، حيث ينتمي زوج جمل المدخلات إلى لغتين مختلفة.
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contextual embedding spaces such that even if the representations of different languages are not aligned well, the model can still achieve good performance on zero-shot cross-lingual transfer. In this work, we propose a learning strategy for training robust models by drawing connections between adversarial examples and the failure cases of zero-shot cross-lingual transfer. We adopt two widely used robust training methods, adversarial training and randomized smoothing, to train the desired robust model. The experimental results demonstrate that robust training improves zero-shot cross-lingual transfer on text classification tasks. The improvement is more significant in the generalized cross-lingual transfer setting, where the pair of input sentences belong to two different languages.
References used
https://aclanthology.org/
rate research
Read More
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 pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models
may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the cross-task knowledge from genera
l question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle none value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on high-resource lang
uages so that it transfers well to the zero-shot languages is a non-trivial task. In this paper, we propose a novel meta-optimizer to soft-select which layers of the pre-trained model to freeze during fine-tuning. We train the meta-optimizer by simulating the zero-shot transfer scenario. Results on cross-lingual natural language inference show that our approach improves over the simple fine-tuning baseline and X-MAML (Nooralahzadeh et al., 2020).
Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access train
ing data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages. A straightforward approach is resorting to pre-trained multilingual models (e.g., mBERT) for cross-lingual transfer, but there is a still significant gap of KGQA performance between source and target languages. In this paper, we exploit unsupervised bilingual lexicon induction (BLI) to map training questions in source language into those in target language as augmented training data, which circumvents language inconsistency between training and inference. Furthermore, we propose an adversarial learning strategy to alleviate syntax-disorder of the augmented data, making the model incline to both language- and syntax-independence. Consequently, our model narrows the gap in zero-shot cross-lingual transfer. Experiments on two multilingual KGQA datasets with 11 zero-resource languages verify its effectiveness.
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
