Building Natural Language Understanding (NLU) capabilities for Indic languages, which have a collective speaker base of more than one billion speakers is absolutely crucial. In this work, we aim to improve the NLU capabilities of Indic languages by making contributions along 3 important axes (i) monolingual corpora (ii) NLU testsets (iii) multilingual LLMs focusing on Indic languages. Specifically, we curate the largest monolingual corpora, IndicCorp, with 20.9B tokens covering 24 languages from 4 language families - a 2.3x increase over prior work, while supporting 12 additional languages. Next, we create a human-supervised benchmark, IndicXTREME, consisting of nine diverse NLU tasks covering 20 languages. Across languages and tasks, IndicXTREME contains a total of 105 evaluation sets, of which 52 are new contributions to the literature. To the best of our knowledge, this is the first effort towards creating a standard benchmark for Indic languages that aims to test the multilingual zero-shot capabilities of pretrained language models. Finally, we train IndicBERT v2, a state-of-the-art model supporting all the languages. Averaged across languages and tasks, the model achieves an absolute improvement of 2 points over a strong baseline. The data and models are available at https://github.com/AI4Bharat/IndicBERT.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
Institute of Artificial Intelligence, Soochow University（苏州大学人工智能研究院）；Peking University（北京大学）；The Hong Kong Polytechnic University（香港理工大学）；Pharmcube（药智魔方）；Changping Laboratory（昌平实验室）
Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose ERNIE-M, a new training method that encourages the model to align the representation of multiple languages with monolingual …
University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））；Elhuyar Foundation（埃尔胡亚基金会）
Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are …
The automatic identification of discourse relations is still a challenging task in natural language processing. Discourse connectives, such as "since" or "but", are the most informative cues to identify explicit relations; however discourse parsers typically use a closed inventory of such connectives. As a result, discourse relations signaled by markers outside these inventories (i.e. AltLexes) are not detected as effectively. In this paper, we propose a novel method to leverage parallel corpora in text simplification and lexical resources to automatically identify alternative lexicalizations …
Microsoft India（微软印度）；IIT Madras（马德拉斯印度理工学院）；AI4Bharat
We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2.7 billion words for 10 Indian languages from two language families. We share pre-trained word embeddings trained on these corpora. We create news article category classification datasets for 9 languages to evaluate the embeddings. We show that the IndicNLP embeddings significantly outperform publicly available pre-trained embedding on multiple evaluation tasks. We hope that the availability of the corpus will accelerate Indic NLP research. The resources are available at https://github.com/ai4bharat-indicnlp/indic…
National Institute of Technology, Hamirpur（哈米尔普尔国家理工学院）
In this paper we present the dataset of Himachali low resource endangered language, Kangri (ISO 639-3xnr) listed in the United Nations Educational, Scientific and Cultural Organization (UNESCO). The compilation of kangri corpus has been a challenging task due to the non-availability of the digitalized resources. The corpus contains 1,81,552 Monolingual and 27,362 Hindi-Kangri Parallel corpora. We shared pre-trained kangri word embeddings. We also reported the Bilingual Evaluation Understudy (BLEU) score and Metric for Evaluation of Translation with Explicit ORdering (METEOR) score of Statistic…
Université de Montréal（蒙特利尔大学）；Middle East Technical University（中东技术大学）；Université du Maine（曼恩大学）
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation. Arguably, one of the major factors behind this success has been the availability of high quality parallel corpora. In this work, we investigate how to leverage abundant monolingual corpora for neural machine translation. Compared to a phrase-based and hierarchical baseline, we obtain up to $1.96$ BLEU improvement on the low-resource language pair Turkish-English, and $1.59$ BLEU on the focused domain task of Chinese-English chat messages. While our m…
While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, especially for low-resource languages, it is appealing to exploit monolingual corpora to improve NMT. We propose a semi-supervised approach for training NMT models on the concatenation of labeled (parallel corpora) and unlabeled (monolingual corpora) data. The central idea is to reconstruct the monolingual corpora using an autoencoder, in which the source-to-tar…
Pretrained language models are now of widespread use in Natural Language Processing. Despite their success, applying them to Low Resource languages is still a huge challenge. Although Multilingual models hold great promise, applying them to specific low-resource languages e.g. Roman Urdu can be excessive. In this paper, we show how the code-switching property of languages may be used to perform cross-lingual transfer learning from a corresponding high resource language. We also show how this transfer learning technique termed Bilingual Language Modeling can be used to produce better performing…
Previous work on document-level NMT usually focuses on limited contexts because of degraded performance on larger contexts. In this paper, we investigate on using large contexts with three main contributions: (1) Different from previous work which pertrained models on large-scale sentence-level parallel corpora, we use pretrained language models, specifically BERT, which are trained on monolingual documents; (2) We propose context manipulation methods to control the influence of large contexts, which lead to comparable results on systems using small and large contexts; (3) We introduce a multi…
Ancient Chinese is the essence of Chinese culture. There are several natural language processing tasks of ancient Chinese domain, such as ancient-modern Chinese translation, poem generation, and couplet generation. Previous studies usually use the supervised models which deeply rely on parallel data. However, it is difficult to obtain large-scale parallel data of ancient Chinese. In order to make full use of the more easily available monolingual ancient Chinese corpora, we release AnchiBERT, a pre-trained language model based on the architecture of BERT, which is trained on large-scale ancient…
Kyoto University（京都大学）；National Institute of Information and Communications Technology（信息通信研究机构）
Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks in low-resource settings. However, large monolingual corpora might not always be available for the languages of interest (LOI). To this end, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI. A case study of low-resource Japanese-English neural machine translation (NMT) reveals that leveraging large Chinese and French monolingual corpora can help overcome the shortage of Japanese and English monol…
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
University College London（伦敦大学学院）；Nanyang Technological University（南洋理工大学）；University of Waterloo（滑铁卢大学）；NVIDIA（英伟达）；National Institute of Informatics（信息研究院）
Facebook AI Research（脸书人工智能研究院）；Sorbonne Universités, UPMC Univ Paris 06（索邦大学、巴黎第六大学）
Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource language pairs, yet requiring tens of thousands of parallel sentences. In this work, we take this research direction to the extreme and investigate whether it is possible to learn to translate even without any parallel data. We propose a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space. By …
Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only
School of Foreign Languages, University of Electronic Science and Technology of China（电子科技大学外国语言学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
IBM Research - Tokyo（IBM 东京研究院）；University of Melbourne（墨尔本大学）；National ICT Australia（澳大利亚国家信息通信技术研究院）；International Computer Science Institute（国际计算机科学研究所）
Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive resul…
MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors
Centre for Linguistics, Humanities, Leiden University（莱顿大学人文学院语言学中心）；LIACS, Leiden University（莱顿大学LIACS）；BDS, Leiden University Medical Centre（莱顿大学医学中心BDS）
Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models
Shandong Inspur Artificial Intelligence Research Institute Co., Ltd.（山东浪潮人工智能研究院有限公司）；Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Center Co., Ltd.（山东云海国创云计算装备产业创新中心有限公司）
Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to mitigate this problem, such as transfer learning, semi-supervised and unsupervised learning techniques. In this paper, we review the existing methods, where the main idea is to exploit the power of monolingual data, which, compared to parallel, is usually easier to obtain and significantly greater in amount.
Harbin University（哈尔滨学院）；University of Washington（华盛顿大学）
This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network structure to model similarity between two sentences. Due to the limitation of available parallel corpora, the model is trained in a semi-supervised way, by using the output of a knowledge-based high performance aligning system. We apply the resulting similarity score to rescore the knowledge-based output, and adapt the model by a small hand-aligned dataset. Experiments show that both rescoring and adaptation improve the p…
The zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result. However, due to the costs of pretraining, most research uses public models whose pretraining methodology, such as the choice of tokenization, corpus size, and computational budget, might differ drastically. When researchers pretrain their own models, they often do so under a constrained budget, and the resulting models might underperform significantly compared to SOTA models. These experimental differences led to various …
National Laboratory of Pattern Recognition, CASIA（模式识别国家重点实验室，中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；Toshiba (China) Co.,Ltd.（东芝（中国）有限公司）
While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in which there only exists monolingual corpora and phrase pairs. We propose a new method towards translation with partially aligned sentence pairs which are derived from the phrase pairs and monolingual corpora. To make full use of the partially aligned corpora, we adapt the conventional NMT training method in two aspects. On one hand, different generation strate…
Dublin City University（都柏林城市大学）；Huawei Technologies（华为技术）
In this paper, a novel approach is proposed to automatically construct parallel discourse corpus for dialogue machine translation. Firstly, the parallel subtitle data and its corresponding monolingual movie script data are crawled and collected from Internet. Then tags such as speaker and discourse boundary from the script data are projected to its subtitle data via an information retrieval approach in order to map monolingual discourse to bilingual texts. We not only evaluate the mapping results, but also integrate speaker information into the translation. Experiments show our proposed method…
Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector spaces to align them such that similar words are mapped to each other. We show empirically that the per…
Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are applied in real-world settings. In this paper, we investigate the bias present in monolingual BERT models across a diverse set of languages (English, Greek, and Persian). While recent research has mostly focused on gender-related biases, we analyze religious and ethnic biases as well and propose a template-based method to measure any kind of bias, based on sent…
Center for Information and Language Processing, LMU Munich, Germany（慕尼黑大学信息与语言处理中心，德国慕尼黑大学（LMU Munich）/慕尼黑大学信息与语言处理中心，德国慕尼黑大学（LMU Munich）/慕尼黑大学信息与语言处理中心（LMU Munich），德国慕尼黑大学（LMU Munich）/慕尼黑大学信息与语言处理中心（LMU Munich），德国慕尼黑大学（LMU Munich），这里统一按原文机构名翻译，正确常见译法为：慕尼黑大学信息与语言处理中心，德国慕尼黑大学（LMU Munich））
Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one language, however, this method leads to poor translations. We present an effective approach that reuses an LM that is pretrained only on the high-resource language. The monolingual LM is fine-tuned on both languages and is then used to initialize a UNMT model. To reuse the pretrained LM, we have to modify its predefined vocabulary, to account for the new languag…
Pre-training text representations have led to significant improvements in many areas of natural language processing. The quality of these models benefits greatly from the size of the pretraining corpora as long as its quality is preserved. In this paper, we describe an automatic pipeline to extract massive high-quality monolingual datasets from Common Crawl for a variety of languages. Our pipeline follows the data processing introduced in fastText (Mikolov et al., 2017; Grave et al., 2018), that deduplicates documents and identifies their language. We augment this pipeline with a filtering ste…
University of Turku（图尔库大学）；University of Oulu（奥卢大学）；Northern Arizona University（北亚利桑那大学）
We explore cross-lingual transfer of register classification for web documents. Registers, that is, text varieties such as blogs or news are one of the primary predictors of linguistic variation and thus affect the automatic processing of language. We introduce two new register annotated corpora, FreCORE and SweCORE, for French and Swedish. We demonstrate that deep pre-trained language models perform strongly in these languages and outperform previous state-of-the-art in English and Finnish. Specifically, we show 1) that zero-shot cross-lingual transfer from the large English CORE corpus can m…
Harbin Institute of Technology（哈尔滨工业大学）；JD AI Research（京东人工智能研究院）；Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（信息通信技术研究所）
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for some extremely low-resource languages such as Estonian, and UNMT systems usually perform poorly when there is not adequate training corpus for one language. In this paper, we first define and analyze the unbalanced training data scenario for UNMT. Based on this scenario, we propose UNMT self-training mechanisms to train a robust UNMT system and improve its per…
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）
We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. The framework leverages shared cross-lingual word embedding spaces in which terms, queries, and documents can be represented, irrespective of their actual language. The shared embedding spaces are induced solely on the basis of monolingual corpora in two languages through an iterative process based on adversarial neural networks. Our experiments on the standard CLEF CLIR collections for three language pairs of varying degrees of language similarity (English-D…
University of Ljubljana（卢布尔雅那大学）；Queen Mary University of London（伦敦玛丽女王大学）；Jožef Stefan Institute（约泽夫·斯蒂芬研究所）
The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses on English; in contrast, we present here the first multilingual empirical comparison of two ELMo and several monolingual and multilingual BERT models using 14 tasks in nine languages. In monolingual settings, our analysis shows that monolingual BERT models generally dominate, with a few exceptions such as the dependency parsing task, where they are not competitive with ELMo models trained on large corpora. In cross-l…
Hate speech detection has become an important research topic within the past decade. More private corporations are needing to regulate user generated content on different platforms across the globe. In this paper, we introduce a study of multilingual hate speech classification. We compile a dataset of 11 languages and resolve different taxonomies by analyzing the combined data with binary labels: hate speech or not hate speech. Defining hate speech in a single way across different languages and datasets may erase cultural nuances to the definition, therefore, we utilize language agnostic embed…
It can be challenging to build effective open question answering (open QA) systems for languages other than English, mainly due to a lack of labeled data for training. We present a data efficient method to bootstrap such a system for languages other than English. Our approach requires only limited QA resources in the given language, along with machine-translated data, and at least a bilingual language model. To evaluate our approach, we build such a system for the Icelandic language and evaluate performance over trivia style datasets. The corpora used for training are English in origin but mac…
Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few research for document and sentence alignment. However, most of the low-resource languages are under-represented in these pre-trained models. Thus, in the context of low-resource languages, these models have to be fine-tuned for the task at hand, using additional data sources. This paper presents a weighting mechanism that makes use of available small-scale …
Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend and domain-related, so completely explaining the phenomenon by linguistic rules is challenging. Compared to most monolingual tasks, insufficient data is an issue for code-switching. To mitigate the issue without expensive human annotation, we proposed an unsupervised method for code-switching data augmentation. By utilizing a generative adversarial network, we can generate intra-sentential code-switching sentences from monolingual sentences. We applied proposed method on two corpora, an…
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Nilekani Centre at AI4Bharat（AI4Bharat的Nilekani中心）；Indian Institute of Technology（印度理工学院）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Engineering Science and Technology Shibpur（Shibpur的印度工程科学与技术学院）
Shiraz University（设拉子大学）；University of Calabria（卡拉布里亚大学）；Complutense University（马德里康普顿斯大学）
The effectiveness of a statistical machine translation system (SMT) is very dependent upon the amount of parallel corpus used in the training phase. For low-resource language pairs there are not enough parallel corpora to build an accurate SMT. In this paper, a novel approach is presented to extract bilingual Persian-Italian parallel sentences from a non-parallel (comparable) corpus. In this study, English is used as the pivot language to compute the matching scores between source and target sentences and candidate selection phase. Additionally, a new monolingual sentence similarity metric, No…
University of Oslo（奥斯陆大学）；University of Helsinki（赫尔辛基大学）；National Research University Higher School of Economics（国立研究型大学高等经济学院）
We present our experience in applying distributional semantics (neural word embeddings) to the problem of representing and clustering documents in a bilingual comparable corpus. Our data is a collection of Russian and Ukrainian academic texts, for which topics are their academic fields. In order to build language-independent semantic representations of these documents, we train neural distributional models on monolingual corpora and learn the optimal linear transformation of vectors from one language to another. The resulting vectors are then used to produce `semantic fingerprints' of document…
Parallel corpora are ideal for extracting a multilingual named entity (MNE) resource, i.e., a dataset of names translated into multiple languages. Prior work on extracting MNE datasets from parallel corpora required resources such as large monolingual corpora or word aligners that are unavailable or perform poorly for underresourced languages. We present CLC-BN, a new method for creating an MNE resource, and apply it to the Parallel Bible Corpus, a corpus of more than 1000 languages. CLC-BN learns a neural transliteration model from parallel-corpus statistics, without requiring any other bilin…
In this paper, we show that Multilingual BERT (M-BERT), released by Devlin et al. (2018) as a single language model pre-trained from monolingual corpora in 104 languages, is surprisingly good at zero-shot cross-lingual model transfer, in which task-specific annotations in one language are used to fine-tune the model for evaluation in another language. To understand why, we present a large number of probing experiments, showing that transfer is possible even to languages in different scripts, that transfer works best between typologically similar languages, that monolingual corpora can train mo…
