Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWord Reordering for Zero-shot Cross-lingual Structured Prediction
كلمة إعادة ترتيب للحصول على التنبؤ الصفر لقطة منظم عبر اللغات
462
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تكييف ترتيب الكلمات من لغة واحدة إلى أخرى هو مشكلة رئيسية في التنبؤ المنظم عبر اللغات.تشفير الجملة الحالية (على سبيل المثال، RNN، محول مع تضيير الموقف) هي عادة ترتيب الكلمة الحساسة.حتى مع وجود تمثيلات نموذج موحدة (MUSE، MBERT)، قد تؤذي تناقضات ترتيب الكلمات التكيف مع النماذج.في هذه الورقة، نبني نماذج التنبؤ الهيكلية بمدخلات كيس من الكلمات، وإدخال وحدة إعادة ترتيب جديدة لتنظيم الكلمات بعد ترتيب لغة المصدر، والذي يتعلم استراتيجيات إعادة ترتيب محددة المهام من نموذج تنبئ النظام للأغراض العامة.تظهر التجارب على تحليل التبعية المتبادلة الصفرية وعلامات نقاط البيع، والعلامات المورفولوجية أن طرازنا يمكن أن يحسن بشكل كبير من أداء اللغات المستهدفة، وخاصة لغات بعيدة عن اللغة المصدر.
Adapting word order from one language to another is a key problem in cross-lingual structured prediction. Current sentence encoders (e.g., RNN, Transformer with position embeddings) are usually word order sensitive. Even with uniform word form representations (MUSE, mBERT), word order discrepancies may hurt the adaptation of models. In this paper, we build structured prediction models with bag-of-words inputs, and introduce a new reordering module to organizing words following the source language order, which learns task-specific reordering strategies from a general-purpose order predictor model. Experiments on zero-shot cross-lingual dependency parsing, POS tagging, and morphological tagging show that our model can significantly improve target language performances, especially for languages that are distant from the source language.
References used
https://aclanthology.org/
rate research
Read More
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.
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.
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.
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).
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
