Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTranslate \& Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data
ترجمة \ & املأ: تحسين تحليل الدلالي متعدد اللغات صفرية مع البيانات الاصطناعية
227
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في حين أظهرت نماذج اللغة المحددة مسببة اللغات متعددة اللغات (LMS) بشكل جيد على لغة واحدة إمكانات نقل مهمة متبادلة كبيرة، لا تزال هناك فجوة في الأداء الواسعة في مهام التحليل الدلالي عند توفر إشراف اللغة المستهدف.في هذه الورقة، نقترح طريقة رواية ترجمية وملء (TAF) لإنتاج بيانات تدريبية فضية لمحلل دلالي متعدد اللغات.تبسط هذه الطريقة خط أنابيب المحاذاة المشهورة للمحاذاة (انقر) وتتكون من نموذج حشو تسلسل إلى تسلسل يبني تحليل كامل مشروط على الكلام وعرض نفس التحليل.يتم تدريب الحشو لدينا على بيانات اللغة الإنجليزية فقط ولكن يمكن أن تكمل بدقة مثيلات بلغات أخرى (I.E.، ترجمات كلمات التدريب على اللغة الإنجليزية)، في أزياء صفرية بالرصاص.النتائج التجريبية على ثلاث مجموعات بيانات تحليل دلالية متعددة اللغات تظهر أن تكبير البيانات مع TAV يصل إلى دقة تنافسية مع أنظمة مماثلة تعتمد على تقنيات المحاذاة التقليدية.
While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language supervision is available. In this paper, we propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parser. This method simplifies the popular Translate-Align-Project (TAP) pipeline and consists of a sequence-to-sequence filler model that constructs a full parse conditioned on an utterance and a view of the same parse. Our filler is trained on English data only but can accurately complete instances in other languages (i.e., translations of the English training utterances), in a zero-shot fashion. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.
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.
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task. However, most of those datasets are in English, and the performances of state-of-the-art multilingual model
s are significantly lower when evaluated on non-English data. Due to high data collection costs, it is not realistic to obtain annotated data for each language one desires to support. We propose a method to improve the Cross-lingual Question Answering performance without requiring additional annotated data, leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion. We show that the proposed method allows to significantly outperform the baselines trained on English data only. We report a new state-of-the-art on four datasets: MLQA, XQuAD, SQuAD-it and PIAF (fr).
We propose a simple method to generate multilingual question and answer pairs on a large scale through the use of a single generative model. These synthetic samples can be used to improve the zero-shot performance of multilingual QA models on target
languages. Our proposed multi-task training of the generative model only requires labeled training samples in English, thus removing the need for such samples in the target languages, making it applicable to far more languages than those with labeled data. Human evaluations indicate the majority of such samples are grammatically correct and sensible. Experimental results show our proposed approach can achieve large gains on the XQuAD dataset, reducing the gap between zero-shot and supervised performance of smaller QA models on various languages.
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, le
arning 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.
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher. We constrain our exploration in a strict multilingua
l setting: there is but one model to parse all different languages including English. We identify that noisy input and precise output are the key to successful distillation. Together with extensive pre-training, we obtain an AMR parser whose performances surpass all previously published results on four different foreign languages, including German, Spanish, Italian, and Chinese, by large margins (up to 18.8 Smatch points on Chinese and on average 11.3 Smatch points). Our parser also achieves comparable performance on English to the latest state-of-the-art English-only parser.
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
