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-translating as measured by BLEU, and furthermore it allows adding unseen languages incrementally.
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of task-specific trainable parameters. While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). Starting from different pre-trained models (a multilingual ST trained on parallel data or a multilingual BART (mBART) t…
Meta AI Research（Meta人工智能研究院）；University of Edinburgh（爱丁堡大学）
Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters. However, adapters of related languages are unable to transfer information, and their total number of parameters becomes prohibitively expensive as the number of languages grows. In this work, we overcome these drawbacks using hyper-adapters -- hyper-networks that generate adapters from language and layer embeddings. While past work had poor results when scaling hyper-networks, we propose a rescaling fix that signific…
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair seen at training time. However, when a MNMT model is used to translate under domain shift or to a new language pair, performance drops dramatically. We consider a very challenging scenario: adapting the MNMT model both to a new domain and to a new language pair at the same time. In this paper, we propose $m^4Adapter$ (Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter), which combines domain and language knowledge using me…
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…
University of Edinburgh（爱丁堡大学）；NAVER LABS Europe（NAVER LABS 欧洲）
Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a small set of parameters for each new setting (language pair or domain). In this work we study the compositionality of language and domain adapters in the context of Machine Translation. We aim to study, 1) parameter-efficient adaptation to multiple domains and languages simultaneously (full-resource scenario) and 2) cross-lingual transfer in domains where pa…
Technical University of Darmstadt（达姆施塔特工业大学）；University of Cambridge（剑桥大学）；DeepMind（深度思维）
The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingual transfer. However, due to limited model capacity, their transfer performance is the weakest exactly on such low-resource languages and languages unseen during pre-training. We propose MAD-X, an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations. In addit…
ByteDance AI Lab（字节跳动人工智能实验室）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual model is inferior to separately trained bilingual ones on rich-resource languages. We conjecture that such a phenomenon is due to interference caused by joint training with multiple languages. To accommodate the issue, we propose CIAT, an adapted Transformer model with a small parameter overhead for multilingual machine translation. We evaluate CIAT on multiple benchmark datasets, including IWSLT, OPUS-100, and WMT. E…
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 …
ETH Zürich（苏黎世联邦理工学院）；Tencent AI Lab（腾讯人工智能实验室）；Shandong University（山东大学）
Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models have recently been extended to multilingual language models (MLLMs), enabling knowledge to be learned across hundreds of languages. Meanwhile, knowledge graphs contain facts in an explicit triple format, which require careful and costly curation and are only available in a few high-resource languages, restricting their research and application. To …
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）；University of Würzburg（维尔茨堡大学）
State-of-the-art neural (re)rankers are notoriously data-hungry which -- given the lack of large-scale training data in languages other than English -- makes them rarely used in multilingual and cross-lingual retrieval settings. Current approaches therefore commonly transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders: they fine-tune all parameters of pretrained massively multilingual Transformers (MMTs, e.g., multilingual BERT) on English relevance judgments, and then deploy them in the target language(s). In this work, we show…
TALP Research Center, Universitat Politècnica de Catalunya（加泰罗尼亚理工大学TALP研究中心）；Telefónica I+D（西班牙电信研发部）
Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on higher-quality and more massive data sets. Our proposed method extends a MultiNMT architecture based on language-specific encoders-decoders to the task of Multilingual SLT (MultiSLT). Our method entirely eliminates the dependency from MultiSLT data and it is able to translate while training only on ASR and MultiNMT data. Our experiments on four different languages sho…
Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages
University of Saarland（萨尔大学）；Brno University of Technology（布尔诺理工大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Kempelen Institute of Intelligent Technologies (KInIT)（肯佩伦智能技术研究所）
University of Cambridge（剑桥大学）；University of Mannheim（曼海姆大学）
Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained transformers, have recently been used for language specialization of multilingual transformers, improving downstream zero-shot cross-lingual transfer. In this work, we propose orthogonal language and task adapters (dubbed orthoadapters) for cross-lingual transfer. They are trained to encode language- and task-specific information that is complementary (i.e., orthogonal) to the knowledge already stored in the pretrained transformer's parameters. Our zero-shot cross-lingual transfer experiments, invo…
Large pretrained multilingual models, trained on dozens of languages, have delivered promising results due to cross-lingual learning capabilities on variety of language tasks. Further adapting these models to specific languages, especially ones unseen during pre-training, is an important goal towards expanding the coverage of language technologies. In this study, we show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages in a structured, linguistically-informed manner. We perform adapter-based training on languages from diver…
Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize intra-distillation…
This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small language-specific vocabulary and fine-tuning the new embeddings on the new language's parallel data. Some additional language-specific components may be trained to improve performance (e.g., Transformer layers or adapter modules). Because the parameters of the original model are not modified, its performance on the initial languages does not degrade. We show on two set…
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…
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a simple yet efficient approach for adaptation in NMT. Our proposed approach consists of injecting tiny task specific adapter layers into a pre-trained model. These lightweight adapters, with just a small fraction of the original model size, adapt the model to multiple individual tasks simultaneously. We evaluate our approach on two tasks: (i) Domain Adaptation…
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science Technical University of Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany（技术大学达姆施塔特计算机科学系通用知识处理实验室（UKP实验室）和应用网络安全国家研究中心ATHENE德国）；Center for AI and Data Science, University of Würzburg（人工智能与数据科学中心，乌尔姆大学）
University of Copenhagen（哥本哈根大学）；Athens University of Economics and Business（雅典经济与商业大学）；Cognitiv+ Ltd.（Cognitiv+ 有限公司）
We introduce MULTI-EURLEX, a new multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. We highlight the effect of temporal concept drift and the importance of chronological, instead of random splits. We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target). We find that fine-tuning a multilingually pret…
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 Cambridge（剑桥大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）
Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properti…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Consumer Business Group（华为消费者业务集团）
Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to this end. However, we notice that the pivoting process involves multiple machine translation models and is likely to incur semantic drift during the two-step translations. In this paper, inspired by the Transformer-based language models, we propose a simple and unified paraphrasing model, which is purely trained on multilingual parallel data and can conduct …
PRHLT Research Center, Universitat Politècnica de València（瓦伦西亚理工大学PRHLT研究中心）；DW Innovation（德国之声创新部）；University of Marburg（马尔堡大学）
Check-worthiness detection is the task of identifying claims, worthy to be investigated by fact-checkers. Resource scarcity for non-world languages and model learning costs remain major challenges for the creation of models supporting multilingual check-worthiness detection. This paper proposes cross-training adapters on a subset of world languages, combined by adapter fusion, to detect claims emerging globally in multiple languages. (1) With a vast number of annotators available for world languages and the storage-efficient adapter models, this approach is more cost efficient. Models can be u…
This work studies the long-standing problems of model capacity and negative interference in multilingual neural machine translation MNMT. We use network pruning techniques and observe that pruning 50-70% of the parameters from a trained MNMT model results only in a 0.29-1.98 drop in the BLEU score. Suggesting that there exist large redundancies even in MNMT models. These observations motivate us to use the redundant parameters and counter the interference problem efficiently. We propose a novel adaptation strategy, where we iteratively prune and retrain the redundant parameters of an MNMT to i…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Microsoft（微软）
While monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less explored area. In this work, we propose a multi-task learning (MTL) framework that jointly trains the model with the translation task on bitext data and two denoising tasks on the monolingual data. We conduct extensive empirical studies on MNMT systems with 10 language pairs from WMT datasets. We show that the proposed approach can effectively improve the translation quality for both hig…
University of Science and Technology of China（中国科学技术大学）
In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by inserting language-specific and language-universal adapters. An online knowledge distillation is then used to enable the language-universal adapters to learn both language-specific and universal features. The linguistic information confusion is also reduced by leveraging language identifiers (LIDs). With LIDs we perform a position-wise modification on the m…
General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks. In this work, we present a methodology for collecting high quality training data for relation extraction from unlabeled text that achieves a near-recreation of their zero-shot and few-shot results at a fraction of the training cost. Our approach exploits the predictable distributional structure of date-marked news articles to build a denoised corpus -- the extract…
University of Cambridge（剑桥大学）；University of Mannheim（曼海姆大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）
In parallel to their overwhelming success across NLP tasks, language ability of deep Transformer networks, pretrained via language modeling (LM) objectives has undergone extensive scrutiny. While probing revealed that these models encode a range of syntactic and semantic properties of a language, they are still prone to fall back on superficial cues and simple heuristics to solve downstream tasks, rather than leverage deeper linguistic knowledge. In this paper, we target one such area of their deficiency, verbal reasoning. We investigate whether injecting explicit information on verbs' semanti…
Language Fusion for Parameter-Efficient Cross-lingual Transfer
Research Centre for Information Systems Engineering, KU Leuven, Belgium（信息系统工程研究中心，鲁汶大学）；IESEG School of Management, France（IESEG管理学院，法国）；Language Technology Lab, University of Cambridge, United Kingdom（语言技术实验室，剑桥大学）；Department of Computer Science, KU Leuven, Belgium（计算机科学系，鲁汶大学）
University of Groningen（格罗宁根大学）；Google Research（谷歌研究院）
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such heterogeneous supervision, we propose Hyper-X, a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. This model generates weights for adapter modules conditioned on both tasks and language embeddings. By learning to combine task and language-specific knowledge, our model enables zero-shot transfer for unseen lang…
