Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMultilingual Translation via Grafting Pre-trained Language Models
الترجمة متعددة اللغات عبر طرازات اللغات المدربة مسبقا مسبقا
339
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
هل يمكن لصق Bert مدربة مسبقا بلغة واحدة و GPT لآخر لترجمة النصوص؟يؤدي التدريب للإشراف على الذات باستخدام بيانات أحادية الأونلينغ فقط إلى نجاح نماذج اللغة المدربة مسبقا (ملثمين) في العديد من مهام NLP.ومع ذلك، فإن ربط بيرت مباشرة كتشفير و GPT حيث أن وحدة فك ترميز يمكن أن يكون تحديا في الترجمة الآلية، وفصول النماذج التي تشبه gpt إلى مكون متقاطع مكون مطلوب في فك تشفير SEQ2SEQ.في هذه الورقة، نقترح Graformer إلى الكسب غير المشروع نماذج اللغة المدربة مسبقا (ملثمين) للترجمة الآلية.مع بيانات أحادية الأبعاد لبيانات التدريب المسبق والتوازي لتدريب تطعيم، نستفيد إلى حد ما من استخدام كلا النوعين من البيانات.تظهر التجارب في 60 اتجاهات أن طريقتنا تحقق متوسط التحسينات من 5.8 بلو في X2EN و 2.9 بلو في اتجاهات EN2X مقارنة مع المحول متعدد اللغات من نفس الحجم.
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However, directly connecting BERT as an encoder and GPT as a decoder can be challenging in machine translation, for GPT-like models lack a cross-attention component that is needed in seq2seq decoders. In this paper, we propose Graformer to graft separately pre-trained (masked) language models for machine translation. With monolingual data for pre-training and parallel data for grafting training, we maximally take advantage of the usage of both types of data. Experiments on 60 directions show that our method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLEU in en2x directions comparing with the multilingual Transformer of the same size.
References used
https://aclanthology.org/
rate research
Read More
As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from PLMs without
training separate parsers. We improve upon this paradigm by proposing a novel chart-based method and an effective top-K ensemble technique. Moreover, we demonstrate that we can broaden the scope of application of the approach into multilingual settings. Specifically, we show that by applying our method on multilingual PLMs, it becomes possible to induce non-trivial parses for sentences from nine languages in an integrated and language-agnostic manner, attaining performance superior or comparable to that of unsupervised PCFGs. We also verify that our approach is robust to cross-lingual transfer. Finally, we provide analyses on the inner workings of our method. For instance, we discover universal attention heads which are consistently sensitive to syntactic information irrespective of the input language.
This paper introduces our neural machine translation systems' participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (
iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cro
ss-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
n pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.
While pre-trained language models (PLMs) are the go-to solution to tackle many natural language processing problems, they are still very limited in their ability to capture and to use common-sense knowledge. In fact, even if information is available
in the form of approximate (soft) logical rules, it is not clear how to transfer it to a PLM in order to improve its performance for deductive reasoning tasks. Here, we aim to bridge this gap by teaching PLMs how to reason with soft Horn rules. We introduce a classification task where, given facts and soft rules, the PLM should return a prediction with a probability for a given hypothesis. We release the first dataset for this task, and we propose a revised loss function that enables the PLM to learn how to predict precise probabilities for the task. Our evaluation results show that the resulting fine-tuned models achieve very high performance, even on logical rules that were unseen at training. Moreover, we demonstrate that logical notions expressed by the rules are transferred to the fine-tuned model, yielding state-of-the-art results on external datasets.
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
