Translation quality estimation (TQE) is the task of predicting translation quality without reference translations. Due to the enormous cost of creating training data for TQE, only a few translation directions can benefit from supervised training. To address this issue, unsupervised TQE methods have been studied. In this paper, we extensively investigate the usefulness of synthetic TQE data and pre-trained multilingual encoders in unsupervised sentence-level TQE, both of which have been proven effective in the supervised training scenarios. Our experiment on WMT20 and WMT21 datasets revealed that this approach can outperform other unsupervised TQE methods on high- and low-resource translation directions in predicting post-editing effort and human evaluation score, and some zero-resource translation directions in predicting post-editing effort.
University of Chicago（芝加哥大学）；University of Washington（华盛顿大学）
This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only two languages can encode multilingually more aligned representations. We thus introduce dual-pivot transfer: training on one language pair and evaluating on other pairs. To study this theory, we design unsupervised models trained on unpaired sentences and single-pair supervised models trained on bitexts, both based on the unsupervised language model XLM-R wit…
Charles University（查理大学）；University of the Basque Country（巴斯克大学）
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data. We first produce a synthetic parallel corpus using unsupervised machine translation, and use it to fine-tune a pretrained cross-lingual masked language model (XLM) to derive the multilingual sentence representations. The quality of the representations is evaluated on two parallel corpus mining tasks with improvements of up to 22 F1 points o…
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where there is only monolingual data available, we propose a novel setup where one language in the (source, target) pair is not associated with any parallel data, but there may exist auxiliary parallel data that contains the other. This auxiliary data can naturally be utilized in our probabilistic framework via a novel cross-translation loss term. Empirically, we show that our approac…
University of Groningen（格罗宁根大学）；NAVER LABS Europe（NAVER LABS 欧洲）
We consider the problem of multilingual unsupervised machine translation, translating to and from languages that only have monolingual data by using auxiliary parallel language pairs. For this problem the standard procedure so far to leverage the monolingual data is back-translation, which is computationally costly and hard to tune. In this paper we propose instead to use denoising adapters, adapter layers with a denoising objective, on top of pre-trained mBART-50. In addition to the modularity and flexibility of such an approach we show that the resulting translations are on-par with back-tra…
Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages, unsupervised translation performs poorly, achieving less than 3.0 BLEU. In this work, we show that multilinguality is critical to making unsupervised systems practical for low-resource settings. In particular, we present a single model for 5 low-resource languages (Gujarati, Kazakh, Nepali, Sinhala, and Turkish) to and from English directions, which leverag…
Tokyo Metropolitan University（东京都立大学）；National Institute of Information and Communications Technology（日本国立信息通信技术研究所）
This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking. Although there are many solutions for low-resource scenarios, such as multilingual NMT and back-translation, we have empirically confirmed their limited success when restricted to in-domain data. We therefore propose to exploit out-of-domain data through transfer learning, by using it to first train a multilingual NMT model followed by multistage fine-tuning on in-domain parallel and back-translated pseudo-para…
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions are infeasible for most languages, especially for languages with large linguistic distances, e.g., English and Chinese. In this work, we propose a Multilingual Language Model with deep semantic Alignment (MLMA) to generate language-independent representations for cross-lingual sequence labeling. Our methods require only monolingual corpora with no bilingual resources at all and take advantage of deep contextualized rep…
We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of embeddings that exhibit higher accuracy on syntactic and semantic compositionality, as well as multilingual semantic similarity, compared to previous models trained in an unsupervised fashion. We also show that such multilingual embeddings, optimized for semantic similarity, can improve the performance of statistical machine translation with respect to how it ha…
Institute for Anthropomatics and Robotics（人机与机器人研究所）；KIT - Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
In this work we look into adding a new language to a multilingual NMT system in an unsupervised fashion. Under the utilization of pre-trained cross-lingual word embeddings we seek to exploit a language independent multilingual sentence representation to easily generalize to a new language. While using cross-lingual embeddings for word lookup we decode from a yet entirely unseen source language in a process we call blind decoding. Blindly decoding from Portuguese using a basesystem containing several Romance languages we achieve scores of 36.4 BLEU for Portuguese-English and 12.8 BLEU for Russi…
Numerous recent work on unsupervised machine translation (UMT) implies that competent unsupervised translations of low-resource and unrelated languages, such as Nepali or Sinhala, are only possible if the model is trained in a massive multilingual environment, where these low-resource languages are mixed with high-resource counterparts. Nonetheless, while the high-resource languages greatly help kick-start the target low-resource translation tasks, the language discrepancy between them may hinder their further improvement. In this work, we propose a simple refinement procedure to separate lang…
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve the latter problem is to jointly solve the following two sub-problems: 1) learning unsupervised word alignment between several pairs of languages, and 2) learning how to map the monolingual embeddings of every language to a shared multilingual space. In contrast, we propose a simple, two-stage framework in which we decouple the above two sub-problems and solve them separately …
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）
Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted as a go-to paradigm for multilingual and cross-lingual representation learning and transfer, rendering cross-lingual word embeddings (CLWEs) effectively obsolete. However, questions remain to which extent this finding generalizes 1) to unsupervised settings and 2) for ad-hoc cross-lingual IR (CLIR) tasks. Therefore, in this work we present a systematic empiri…
Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation
School of Mathematical and Computational Sciences, Massey University（马歇尔大学数学与计算科学学院）；Mila – Quebec AI Institutes（魁北克人工智能研究院）；Computer Science, Ontario Technology University and University of Toronto（安大略技术大学与多伦多大学计算机科学系）
ByteDance AI Lab（字节跳动人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）
Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising results. However, there are still big gaps between UNMT and NMT with parallel supervision. In this work, we introduce a multilingual unsupervised NMT (\method) framework to leverage weakly supervised signals from high-resource language pairs to zero-resource translation directions. More specifically, for unsupervised language pairs \texttt{En-De}, we can make full use of the informa…
We are proposing a simple, but efficient basic approach for a number of multilingual and cross-lingual language technology applications that are not limited to the usual two or three languages, but that can be applied with relatively little effort to larger sets of languages. The approach consists of using existing multilingual linguistic resources such as thesauri, nomenclatures and gazetteers, as well as exploiting the existence of additional more or less language-independent text items such as dates, currency expressions, numbers, names and cognates. Mapping texts onto the multilingual reso…
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…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；NTT Communication Science Laboratories（NTT通信科学实验室）
We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as an input. The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages. The other parameters, i.e. word embeddings and linear transformation between hidden states and outputs, are specific to each language. The shared LSTMs can capture the common sentence structure …
Idiap Research Institute（Idiap研究所）；University of Edinburgh（爱丁堡大学）；Stellenbosch University（斯泰伦博斯大学）
Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good representation should capture phonetic content and abstract away from other types of variability, such as speaker differences and channel noise. Previous work in this area has primarily focused unsupervised learning from target language data only, and has been evaluated only intrinsically. Here we directly compare multiple methods, including some that use only ta…
This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages, using more than two terabytes of filtered CommonCrawl data. Our model, dubbed XLM-R, significantly outperforms multilingual BERT (mBERT) on a variety of cross-lingual benchmarks, including +14.6% average accuracy on XNLI, +13% average F1 score on MLQA, and +2.4% F1 score on NER. XLM-R performs particularly well on low-resource languages, improving 15.7% in XNL…
Transliterations play an important role in multilingual entity reference resolution, because proper names increasingly travel between languages in news and social media. Previous work associated with machine translation targets transliteration only single between language pairs, focuses on specific classes of entities (such as cities and celebrities) and relies on manual curation, which limits the expression power of transliteration in multilingual environment. By contrast, we present an unsupervised transliteration model covering 69 major languages that can generate good transliterations for …
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））
It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during training. While recent literature has studied this phenomenon, the reasons for the multilinguality are still somewhat obscure. We aim to identify architectural properties of BERT and linguistic properties of languages that are necessary for BERT to become multilingual. To allow for fast experimentation we propose an efficient setup with small BERT models trained on a mix of syn…
College of Electrical Engineering and Computer Science, National Taiwan University（台湾大学电机资讯学院）
Recently, multilingual BERT works remarkably well on cross-lingual transfer tasks, superior to static non-contextualized word embeddings. In this work, we provide an in-depth experimental study to supplement the existing literature of cross-lingual ability. We compare the cross-lingual ability of non-contextualized and contextualized representation model with the same data. We found that datasize and context window size are crucial factors to the transferability. We also observe the language-specific information in multilingual BERT. By manipulating the latent representations, we can control t…
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART -- a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective. mBART is one of the first methods for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, while previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it …
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…
Multilingual machine translation enables a single model to translate between different languages. Most existing multilingual machine translation systems adopt a randomly initialized Transformer backbone. In this work, inspired by the recent success of language model pre-training, we present XLM-T, which initializes the model with an off-the-shelf pretrained cross-lingual Transformer encoder and fine-tunes it with multilingual parallel data. This simple method achieves significant improvements on a WMT dataset with 10 language pairs and the OPUS-100 corpus with 94 pairs. Surprisingly, the metho…
University of Cambridge（剑桥大学）；University of Mannheim（曼海姆大学）
In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs. We first treat these models as multilingual text encoders and benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR. In contrast to supervised language understanding, our results indicate that for unsupervised document-level CLIR -- a setup with no relevance judgments for IR-specific fine-tuning -- pretrained multilingual encoders on average …
Machine translation (MT) involving Indigenous languages, including those possibly endangered, is challenging due to lack of sufficient parallel data. We describe an approach exploiting bilingual and multilingual pretrained MT models in a transfer learning setting to translate from Spanish to ten South American Indigenous languages. Our models set new SOTA on five out of the ten language pairs we consider, even doubling performance on one of these five pairs. Unlike previous SOTA that perform data augmentation to enlarge the train sets, we retain the low-resource setting to test the effectivene…
National Laboratory of Pattern Recognition, Institute of Automation, CAS（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally as clean data during optimization without considering the quality diversity, leading to slow convergence and limited translation performance. To address this problem, we propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. Specifically, we first apply cross-lingual word embedding to calc…
Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information. We find that the representation of a language can be obtained by simply averaging the embeddings of the tokens of the language. Given this language representation, we control the output languages of multilingual BERT by manipulating the token embeddings, thus achieving unsupervised token translation. We further propose a computationally cheap but effective approach to improve the cross-lingual ability of m-BERT based on this observation.
Keyword extraction is the task of retrieving words that are essential to the content of a given document. Researchers proposed various approaches to tackle this problem. At the top-most level, approaches are divided into ones that require training - supervised and ones that do not - unsupervised. In this study, we are interested in settings, where for a language under investigation, no training data is available. More specifically, we explore whether pretrained multilingual language models can be employed for zero-shot cross-lingual keyword extraction on low-resource languages with limited or …
Indian Institute of Technology Bombay（孟买印度理工学院）；Google Research（谷歌研究院）
Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose …
Department of Computer Science（计算机科学系）；Johns Hopkins University（约翰斯·霍普金斯大学）
Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to further improve these representations. However, word-level alignments are often suboptimal and such bitexts are unavailable for many languages. In this paper, we propose a new contrastive alignment objective that can better utilize such signal, and examine whether these previous alignment methods can be adapted to noisier sources of aligned data: a randomly sample…
We have seen significant improvements in machine translation due to the usage of deep learning. While the improvements in translation quality are impressive, the encoder-decoder architecture enables many more possibilities. In this paper, we explore one of these, the generation of constraint translation. We focus on length constraints, which are essential if the translation should be displayed in a given format. In this work, we propose an end-to-end approach for this task. Compared to a traditional method that first translates and then performs sentence compression, the text compression is le…
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this work, we propose mSimCSE, which extends SimCSE to multilingual settings and reveal that contrastive learning on English data can surprisingly learn high-quality universal cross-lingual sentence embeddings without any parallel data. In unsupervised and weakly supervised settings, mSimCSE significantly improves previous sentence embedding methods on cross-lingual…
Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually. To better understand this overlap, we extend recent work on finding syntactic trees in neural networks' internal representations to the multilingual setting. We show that subspaces of mBERT representations recover syntactic tree distances in languages other than English, and that these subspaces are approximately shared across languages. Motivated by …
Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised Machine Translation (UNMT). However, these models still struggle in a variety of ways, including aspects of translation that for a human are the easiest - for instance, correctly translating common nouns. This work explores a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translatio…
Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant advantage over traditional supervised approaches and opens many new possibilities for low-resource languages. Prior art for learning UMWEs, however, merely relies on a number of independently trained Unsupervised Bilingual Word Embeddings (UBWEs) to obtain multilingual embeddings. These methods fail to leverage the interdependencies that exist among many lang…
Heidelberg Institute for Theoretical Studies（海德堡理论研究所）；Technische Universität Darmstadt（达姆施塔特工业大学）；Universität Bielefeld（比勒费尔德大学）
Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the availability of large parallel data, thereby leaving under-represented language communities behind. In this work, we attribute the data hungriness of previous alignment techniques to two limitations: (i) the inability to sufficiently leverage data and (ii) these techniques are not trained properly. To address these issues, we introduce supervised and unsupervise…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Virginia（弗吉尼亚大学）；Microsoft Research（微软研究院）；Stanford University（斯坦福大学）
Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by exploiting crosslingual signals to aid sense identification. We present a multi-view Bayesian non-parametric algorithm which improves multi-sense word embeddings by (a) using multilingual (i.e., more than two languages) corpora to significantly improve sense embeddings beyond what one achieves with bilingual information, and (b) uses a principled approach to learn …
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We consider two ways of applying this intuition to the problem of unsupervised part-of-speech tagging: a model that directly merges tag structures for a pair of languages into a single sequence and a second model which instead incorporates multilingual context using latent variables. Both approaches are formulated as hierarchical Bayesian models, using Markov Chain Mo…
Building natural language processing systems for non standardized and low resource languages is a difficult challenge. The recent success of large-scale multilingual pretrained language models provides new modeling tools to tackle this. In this work, we study the ability of multilingual language models to process an unseen dialect. We take user generated North-African Arabic as our case study, a resource-poor dialectal variety of Arabic with frequent code-mixing with French and written in Arabizi, a non-standardized transliteration of Arabic to Latin script. Focusing on two tasks, part-of-spee…
This paper investigates data-driven segmentation using Re-Pair or Byte Pair Encoding-techniques. In contrast to previous work which has primarily been focused on subword units for machine translation, we are interested in the general properties of such segments above the word level. We call these segments r-grams, and discuss their properties and the effect they have on the token frequency distribution. The proposed approach is evaluated by demonstrating its viability in embedding techniques, both in monolingual and multilingual test settings. We also provide a number of qualitative examples o…
In this paper we explore the use of unsupervised methods for detecting cognates in multilingual word lists. We use online EM to train sound segment similarity weights for computing similarity between two words. We tested our online systems on geographically spread sixteen different language groups of the world and show that the Online PMI system (Pointwise Mutual Information) outperforms a HMM based system and two linguistically motivated systems: LexStat and ALINE. Our results suggest that a PMI system trained in an online fashion can be used by historical linguists for fast and accurate iden…
Harbin Institute of Technology（哈尔滨工业大学）；National Institute of Information and Communications Technology (NICT)（信息通信研究机构（NICT））
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. That is, research on multilingual UNMT has been limited. In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. On the basis of the empirical findings, we propose two knowledge di…
Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation a…
While billions of non-English speaking users rely on search engines every day, the problem of ad-hoc information retrieval is rarely studied for non-English languages. This is primarily due to a lack of data set that are suitable to train ranking algorithms. In this paper, we tackle the lack of data by leveraging pre-trained multilingual language models to transfer a retrieval system trained on English collections to non-English queries and documents. Our model is evaluated in a zero-shot setting, meaning that we use them to predict relevance scores for query-document pairs in languages never …
We show that unsupervised sequence-segmentation performance can be transferred to extremely low-resource languages by pre-training a Masked Segmental Language Model (Downey et al., 2021) multilingually. Further, we show that this transfer can be achieved by training over a collection of low-resource languages that are typologically similar (but phylogenetically unrelated) to the target language. In our experiments, we transfer from a collection of 10 Indigenous American languages (AmericasNLP, Mager et al., 2021) to K'iche', a Mayan language. We compare our multilingual model to a monolingual …
