While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's languages lack such resources. Hence, we investigate a more radical form of unsupervised knowledge transfer in the absence of linguistic data. In particular, for the first time we pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images---as a crude approximation of real-world environments---inductively biases the model towards learning natural languages. On the one hand, we show that this substantially benefits machine translation in few-shot settings. On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For instance, in this work we measure the influence of communication success and maximum sequence length on downstream performances. Finally, we introduce a customised adapter layer and annealing strategies for the regulariser of maximum-a-posteriori inference during fine-tuning. These turn out to be crucial to facilitate knowledge transfer and prevent catastrophic forgetting. Compared to a recurrent baseline, our method yields gains of $59.0\%$$\sim$$147.6\%$ in BLEU score with only $500$ NMT training instances and $65.1\%$$\sim$$196.7\%$ with $1,000$ NMT training instances across four language pairs. These proof-of-concept results reveal the potential of emergent communication pretraining for both natural language processing tasks in resource-poor settings and extrinsic evaluation of artificial languages.
Recent studies have demonstrated a perceivable improvement on the performance of neural machine translation by applying cross-lingual language model pretraining (Lample and Conneau, 2019), especially the Translation Language Modeling (TLM). To alleviate the need for expensive parallel corpora by TLM, in this work, we incorporate the translation information from dictionaries into the pretraining process and propose a novel Bilingual Dictionary-based Language Model (BDLM). We evaluate our BDLM in Chinese, English, and Romanian. For Chinese-English, we obtained a 55.0 BLEU on WMT-News19 (Tiedeman…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯AI实验室）；University of Alberta（阿尔伯塔大学）
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the…
We evaluate a simple approach to improving zero-shot multilingual transfer of mBERT on social media corpus by adding a pretraining task called translation pair prediction (TPP), which predicts whether a pair of cross-lingual texts are a valid translation. Our approach assumes access to translations (exact or approximate) between source-target language pairs, where we fine-tune a model on source language task data and evaluate the model in the target language. In particular, we focus on language pairs where transfer learning is difficult for mBERT: those where source and target languages are di…
The University of Tokyo（东京大学）；Carnegie Mellon University（卡内基梅隆大学）
Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in low-resource machine translation, there are no standardized reproducible benchmarks for many African languages, many of which are used by millions of speakers but have less digitized textual data. To tackle these challenges, we propose AfroMT, a standardized, clean, and reproducible machine translation benchmark for eight widely spoken African languages…
New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）；CIFAR Azrieli Global Scholar（加拿大高级研究院阿兹列利全球学者）
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication game where two agents, native speakers of their own respective languages, jointly learn to solve a visual referential task. We find that the ability to understand and translate a foreign language emerges as a means to achieve shared goals. The emergent translation is interactive and multimodal, and crucially does not require parallel corpora, but only monoli…
It is expensive to evaluate the results of Machine Translation(MT), which usually requires manual translation as a reference. Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the emergence of predictor-estimator framework which trains the predictor as a feature extractor and estimator as a QE predictor, and pre-trained language models(PLM) have achieved promising QE performance. However, we argue that there are still gaps between the predictor and the estimator in both data quality and training o…
In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude. Unprecedented challenges emerge in this situation compared to previous NMT work, including severe noise in the data and prohibitively long training time. We propose practical solutions to handle these issues and demonstrate that large-scale pretraining significantly improves NMT performance. We are able to push the BLEU score of WMT17 Chinese-English dataset to 32.…
Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the predictor-estimator framework trains the predictor as a feature extractor, which leverages the extra parallel corpora without QE labels, achieving promising QE performance. However, we argue that there are gaps between the predictor and the estimator in both data quality and training objectives, which preclude QE models from benefiting from a large number of parallel corpora more directly. We propose a novel framework called DirectQE that provi…
Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified representation for both speech and text is needed by tasks such as end-to-end speech translation, and as a result,(b) they can not exploit various large-scale text and speech data and their performance is limited by the scarcity of parallel speech translation data.To address these problems, we propose a Fused Acoustic and Text Masked Language Model (FAT-MLM) which join…
The University of Tokyo（东京大学）；Facebook AI Research（脸书人工智能研究院）
Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora, and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present PARADISE (PARAllel & Denoising Integration in SEquence-to-sequence models), which extends the conventional denoising objective used to train these models by (i) replacing words in the noised sequence according to a multilingual dictionary, and (ii) predicting the reference translation according to a parallel corpus instead of recovering the original sequence. Our e…
University of Edinburgh（爱丁堡大学）；Institute for Language, Cognition and Computation（语言、认知与计算研究所）
Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. In this work, we systematically compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context. We pretrain models with different methods on English$\leftrightarrow$German, English$\le…
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）
This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and then fine-tune the model on parallel data using Elastic Weight Consolidation (EWC) to avoid forgetting of the original language modeling tasks. We compare the regularization by EWC with the previous work that focuses on regularization by language modeling objectives. The positive result is that using EWC with the decoder achieves BLEU scores similar to the …
This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights of two language models and then fine-tuned with labeled data. We apply this method to challenging benchmarks in machine translation and abstractive summarization and find that it significantly improves the subsequent supervised models. Our main result is that pretraining improves the generalization of seq2seq models. We achieve state-of-the art results on t…
Facebook AI Research（Facebook人工智能研究）；Sorbonne Universités（巴黎索邦大学）；Université Le Mans（勒芒大学）
Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingual language model objective. We obtain state-of-the-art results on cross-lingual classification, unsupervised and supervised machine translation. On XNLI, our approach pu…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical- and high-level representations of the two languages. While cross-lingual pretraining works for similar languages with abundant corpora, it performs poorly in low-resource and distant languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language m…
We translate a closed text that is known in advance into a severely low resource language by leveraging massive source parallelism. In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ~1,000 lines of low resource data without any external help. Firstly, we propose a systematic method to rank and choose source languages that are close to the low resource language. We call the linguistic definition of language family Family of Origin (FAMO), and we call the empirical definition of higher-ranked languages using our metrics Family …
The University of Hong Kong（香港大学）；Microsoft Research（微软研究院）；Shanghai University of Finance and Economics（上海财经大学）；Texas A&M University（德州农工大学）
This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source languages unseen during supervised training. Following this idea, we present SixT+, a strong many-to-English NMT model that supports 100 source languages but is trained with a parallel dataset in only six source languages. SixT+ initializes the decoder embedding and the full encoder with XLM-R large and then trains the encoder and decoder layers with a simple tw…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level genera…
The University of Sydney（悉尼大学）；Beihang University（北京航空航天大学）；JD Explore Academy, JD.com（京东探索研究院）
We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. Specifically, we update the model parameters with source- and target-side denoising tasks at the early stage and then tune the model normally. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experiments show that DoT consistently improves the neural machine translation performance across 12 bilingual and 16 multilingual directions (data size ranges from 80K to 20M). In addition, we show that DoT can complement existing…
University of Washington（华盛顿大学）；Meta AI Research（Meta人工智能研究院）
The emergent cross-lingual transfer seen in multilingual pretrained models has sparked significant interest in studying their behavior. However, because these analyses have focused on fully trained multilingual models, little is known about the dynamics of the multilingual pretraining process. We investigate when these models acquire their in-language and cross-lingual abilities by probing checkpoints taken from throughout XLM-R pretraining, using a suite of linguistic tasks. Our analysis shows that the model achieves high in-language performance early on, with lower-level linguistic skills ac…
Why Pretraining Fails to Share Cross-Lingual Knowledge
Weizmann Institute of Science（魏茨曼科学研究所）；Bar-Ilan University（巴伊兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；A*STAR（新加坡科技研究局）；University of Washington（华盛顿大学）；MIT（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
China University of Petroleum (East China)（中国石油大学（华东））；JD Explore Academy（京东探索研究院）
For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e.g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e.g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e.g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages. To bridge the above cross-lingual domain and task gaps, we exten…
RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale "silver-standard" discourse treebank MEGA-DT provides even larger performanc…
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT training benefit, however, is often limited to many-to-one directions. The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strateg…
Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）；University of Engineering and Technology, VNU（越南国立大学工程技术大学）；National Institute of Informatics（国立信息学研究所）
Ambiguity is a characteristic of natural language, which makes expression ideas flexible. However, in a domain that requires accurate statements, it becomes a barrier. Specifically, a single word can have many meanings and multiple words can have the same meaning. When translating a text into a foreign language, the translator needs to determine the exact meaning of each element in the original sentence to produce the correct translation sentence. From that observation, in this paper, we propose ParaLaw Nets, a pretrained model family using sentence-level cross-lingual information to reduce am…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；DAMO Academy, Alibaba Group Inc.（阿里巴巴集团达摩院）
Document-level MT models are still far from satisfactory. Existing work extend translation unit from single sentence to multiple sentences. However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail. In this paper, we find such failure is not caused by overfitting, but by sticking around local minima during training. Our analysis shows that the increased complexity of target-to-source attention is a reason for the failure. As a solution, we propose G-Transformer, introducing locality assumption as an inductive bias in…
We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word level through the recently proposed Translation Language Modeling objective as well as on the sentence level via contrastive learning and random input shuffling. We also perform sentence-level code-switching with English when finetuning on downstream tasks. On XNLI, our best model (initialized from mBERT) improves over mBERT by 4.7% in the zero-shot setting a…
We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, a simple regularization method that forces the consistency between the output distributions of the original and the cutoff sentence pairs. Without leveraging extra dataset via back-translation or integrating large-scale pretrained model, Bi-SimCut achieves strong translation performance across five translation benchmarks (data sizes range from 160K to 20.2M)…
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）
This paper describes the system developed at the Universitat Politècnica de Catalunya for the Workshop on Machine Translation 2022 Sign Language Translation Task, in particular, for the sign-to-text direction. We use a Transformer model implemented with the Fairseq modeling toolkit. We have experimented with the vocabulary size, data augmentation techniques and pretraining the model with the PHOENIX-14T dataset. Our system obtains 0.50 BLEU score for the test set, improving the organizers' baseline by 0.38 BLEU. We remark the poor results for both the baseline and our system, and thus, the unr…
Transformer based language models have led to impressive results across all domains in Natural Language Processing. Pretraining these models on language modeling tasks and finetuning them on downstream tasks such as Text Classification, Question Answering and Neural Machine Translation has consistently shown exemplary results. In this work, we propose a Multitask Finetuning methodology which combines the Bilingual Machine Translation task with an auxiliary Causal Language Modeling task to improve performance on the former task on Indian Languages. We conduct an empirical study on three languag…
University of Chinese Academy of Sciences（中国科学院大学）；School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
The University of Sydney（悉尼大学）；Peking University（北京大学）；JD Explore Academy, JD.com（京东探索学院，京东集团（注：根据机构含义，JD.com 是京东集团，此处按要求提取到公司级别，学院名称保留英文））
We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from "src$\rightarrow$tgt" to "src+tgt$\rightarrow$tgt+src" without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translat…
Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation
University of Maryland College Park（马里兰大学帕克分校）；Institute of Health Computing, University of Maryland College Park（马里兰大学帕克分校健康计算研究所）；City University of Hong Kong（香港城市大学）
University of Edinburgh（爱丁堡大学）；Amazon AI（亚马逊人工智能研究院）
A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather". The meaning of these expressions is not composed by the meaning of their constituent words, and NMT models tend to translate them literally (i.e., word-by-word), which leads to confusing and nonsensical translations. Research on idioms in NMT is limited and obstructed by the absence of automatic methods for quantifying these errors. In this work, first, we propose a novel metric for automatically measuring the frequency of literal translation errors without human i…
Translation quality evaluation plays a crucial role in machine translation. According to the input format, it is mainly separated into three tasks, i.e., reference-only, source-only and source-reference-combined. Recent methods, despite their promising results, are specifically designed and optimized on one of them. This limits the convenience of these methods, and overlooks the commonalities among tasks. In this paper, we propose UniTE, which is the first unified framework engaged with abilities to handle all three evaluation tasks. Concretely, we propose monotonic regional attention to contr…
This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech reco…
The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation
Laboratoire de Sciences Cognitives et Psycholinguistique（认知科学与心理语言学实验室）；École Normale Supérieure（巴黎高等师范学院）；PSL University（巴黎文理研究大学）；University of Washington（华盛顿大学）
Aalto University（阿尔托大学）；University of Helsinki（赫尔辛基大学）；Utopia Analytics
There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a…
Facebook AI Research（脸书人工智能研究院）；The University of Hong Kong（香港大学）；New York University（纽约大学）
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot. In this work, we address the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between la…
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Microsoft（微软）
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Self-supervised pretrained models are often fine-tuned on parallel data from one or multiple language pairs for machine translation. Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive. Training a new adapter on each language pair or training a single adapter on all language pairs without updating the pretrained model has been proposed as a parameter-efficient…
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resource language. However, it is not clear what factors --e.g., language relatedness or size of the pretraining data-- yield the biggest improvements, or whether pretraining can be effectively combined with other methods such as data augmentation. Here, we experiment with pretraining on datasets of varying sizes, including languages related and unrelated to the AST source language. W…
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages. Previous work in multilingual pretraining has demonstrated that machine translation systems can be created by finetuning on bitext. In this work, we show that multilingual translation models can be created through multilingual finetuning. Instead of finetuning on one direction, a pretrained model is finetuned on many directions at the same time. Compared to multilingual models trained from scratch, starting from pretrained models incorporates the b…
