Sequence model learning algorithms typically maximize log-likelihood minus the norm of the model (or minimize Hamming loss + norm). In cross-lingual part-of-speech (POS) tagging, our target language training data consists of sequences of sentences with word-by-word labels projected from translations in $k$ languages for which we have labeled data, via word alignments. Our training data is therefore very noisy, and if Rademacher complexity is high, learning algorithms are prone to overfit. Norm-based regularization assumes a constant width and zero mean prior. We instead propose to use the $k$ source language models to estimate the parameters of a Gaussian prior for learning new POS taggers. This leads to significantly better performance in multi-source transfer set-ups. We also present a drop-out version that injects (empirical) Gaussian noise during online learning. Finally, we note that using empirical Gaussian priors leads to much lower Rademacher complexity, and is superior to optimally weighted model interpolation.
There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets. However, the progress of dialogue systems in low-resource languages lags far behind due to the lack of high-quality data. To advance the cross-lingual technology in building dialog systems, DSTC9 introduces the task of cross-lingual dialog state tracking, where we test the DST module in a low-resource language given the rich-resource training dataset. This paper studies the transferability of a cross-lingual generative dialogue state tracking system using a multilingual pr…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Corporation（微软公司）；Microsoft Research（微软研究院）
Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use example consistency regularization to penalize the prediction sensitivity to four types of data augmentations, i.e., subword sampling, Gaussian noise, code-switch substitution, and machine translation. In addition, we employ model consistency to regularize the models trained with two augmented versions of the same training set. Experimental results on the …
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Duolingo（多邻国）；University of Pennsylvania（宾夕法尼亚大学）
Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data. In this work, we provide a comprehensive study of the contribution of different components in M-BERT to its cross-lingual ability. We study the impact of linguistic properties of the languages, the architecture of the model, and the learning objectives. The experimental study is done in the context of three typologically different languages -- Spanish, Hindi, and Russian -- and using two conceptually diffe…
Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective cross-lingual UD parsing framework for transferring parser from only one source monolingual treebank to any other target languages without treebank available. To reach satisfactory parsing accuracy among quite different languages, we introduce two language modeling tasks into dependency parsing as multi-tasking. Assuming only unlabeled data from target lang…
HiTZ Center - Ixa, University of the Basque Country UPV/EHU（HiTZ中心-Ixa，巴斯克大学UPV/EHU）
This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing word vectors are projected to a common semantic space using linear transformations and averaging. With our method the resulting meta-embeddings maintain the dimensionality of the original embeddings without losing information while dealing with the out-of-vocabulary problem. An extensive empirical evaluation demonstrates the effectiveness of our technique wit…
University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（讯飞研究院）
Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER), as well as on cross-lingual model transfer. At present, the mainstream methods to solve the cross-lingual downstream tasks are always using the last transformer layer's output of mBERT as the representation of linguistic information. In this work, we explore the complementary property of lower layers to the last transformer layer of mBERT. A feature aggregat…
The University of Sydney（悉尼大学）；Nagoya University（名古屋大学）
This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the \textit{mismatching issue} when directly adopting BERTScore to QE. Specifically, there exist lots of mismatching errors between the source sentence and translated candidate sentence with token pairwise similarity. In response to this issue, we propose to expose explicit cross-lingual patterns, \textit{e.g.} word alignments and generation score, to our proposed zero-shot models. Experiments show that our proposed QE model with exp…
The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages. Its dominant approaches assumed that the relationship between embeddings could be represented by a linear mapping, but there has been no exploration of the conditions under which this assumption holds. Such a research gap becomes very critical recently, as it has been evidenced that relaxing mappings to be non-linear can lead to better performance in some cases. We, for the first time, present a theoretical analysis that identifies the pre…
Perspectives on Cross-Lingual Consistency in LLMs for Medical Questions
Johannes Gutenberg University Mainz（美因茨约翰内斯·古腾堡大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Marburg（马尔堡大学）；Universidad Iberoamericana（伊比利亚美洲大学）
University of Mannheim（曼海姆大学）；National University of Ireland, Galway（爱尔兰国立高威大学）；Aylien Ltd.（Aylien有限公司）；University of Cambridge（剑桥大学）；PolyAI Ltd.（PolyAI有限公司）
Cross-lingual word embeddings (CLEs) enable multilingual modeling of meaning and facilitate cross-lingual transfer of NLP models. Despite their ubiquitous usage in downstream tasks, recent increasingly popular projection-based CLE models are almost exclusively evaluated on a single task only: bilingual lexicon induction (BLI). Even BLI evaluations vary greatly, hindering our ability to correctly interpret performance and properties of different CLE models. In this work, we make the first step towards a comprehensive evaluation of cross-lingual word embeddings. We thoroughly evaluate both super…
University of Mannheim（曼海姆大学）；University of Oslo（奥斯陆大学）；University of Cambridge（剑桥大学）
Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance. Current downstream evaluations, however, verify their efficacy predominantly in transfer settings involving languages with sufficient amounts of pretraining data, and with lexically and typologically close languages. In this work, we analyze their limitations and show that cross-lingual transfer via massively multilingual transformers, much like transfer via cr…
Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation
Zhejiang University（浙江大学）；Westlake University（西湖大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Sichuan Lan-bridge Information Technology Co., Ltd.（四川语言桥信息技术有限公司）；Westlake Institute for Advanced Study（西湖高等研究院）
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…
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…
Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by jointly reducing the feature incongruity between the source and the target language and increasing the generalization capabilities of pre-trained multilingual transformers. We show that our approach, DiTTO, significantly outperforms the standard zero-shot fine-tuning method on multiple datasets across all languages using solely unlabeled instances in the targe…
Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；Faculty of Industrial Engineering and Management, Technion, IIT（以色列理工学院工业工程与管理学院）
Performance in cross-lingual NLP tasks is impacted by the (dis)similarity of languages at hand: e.g., previous work has suggested there is a connection between the expected success of bilingual lexicon induction (BLI) and the assumption of (approximate) isomorphism between monolingual embedding spaces. In this work we present a large-scale study focused on the correlations between monolingual embedding space similarity and task performance, covering thousands of language pairs and four different tasks: BLI, parsing, POS tagging and MT. We hypothesize that statistics of the spectrum of each mon…
International Phonetic Alphabet (IPA) has been widely used in cross-lingual text-to-speech (TTS) to achieve cross-lingual voice cloning (CL VC). However, IPA itself has been understudied in cross-lingual TTS. In this paper, we report some empirical findings of building a cross-lingual TTS model using IPA as inputs. Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance. Furthermore, we find that using a dataset including one speaker per language to build an IPA-based TTS system would fail CL VC since the language-unique IPA…
In zero-shot cross-lingual transfer, a supervised NLP task trained on a corpus in one language is directly applicable to another language without any additional training. A source of cross-lingual transfer can be as straightforward as lexical overlap between languages (e.g., use of the same scripts, shared subwords) that naturally forces text embeddings to occupy a similar representation space. Recently introduced cross-lingual language model (XLM) pretraining brings out neural parameter sharing in Transformer-style networks as the most important factor for the transfer. In this paper, we aim …
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）；Corti
Current methods of cross-lingual parser transfer focus on predicting the best parser for a low-resource target language globally, that is, "at treebank level". In this work, we propose and argue for a novel cross-lingual transfer paradigm: instance-level parser selection (ILPS), and present a proof-of-concept study focused on instance-level selection in the framework of delexicalized parser transfer. We start from an empirical observation that different source parsers are the best choice for different Universal POS sequences in the target language. We then propose to predict the best parser at…
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…
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 …
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently trained monolingual representations into a shared space, and (2) joint training, which directly learns unified multilingual representations using monolingual and cross-lingual objectives jointly. In this paper, we first conduct direct comparisons of representations learned using both of these methods across diverse cross-lingual tasks. Our empirical results r…
University of Tartu（塔尔图大学）；Institute of Computer Science（计算机科学研究所）
Related works used indexes like CKA and variants of CCA to measure the similarity of cross-lingual representations in multilingual language models. In this paper, we argue that assumptions of CKA/CCA align poorly with one of the motivating goals of cross-lingual learning analysis, i.e., explaining zero-shot cross-lingual transfer. We highlight what valuable aspects of cross-lingual similarity these indexes fail to capture and provide a motivating case study \textit{demonstrating the problem empirically}. Then, we introduce \textit{Average Neuron-Wise Correlation (ANC)} as a straightforward alt…
Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
Jožef Stefan Institute（约热夫· Stefan 研究所）；Jožef Stefan International Postgraduate School（约热夫· Stefan 国际研究生学院）；Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）
本研究比较大语言模型在跨语言零样本与全样本设置下的 adapter/全参数微调及 IT、CLV 迁移策略，发现 IT 更利于目标语言，CLV 更能保留英语知识。
Large-scale cross-lingual pre-trained language models (xPLMs) have shown effectiveness in cross-lingual sequence labeling tasks (xSL), such as cross-lingual machine reading comprehension (xMRC) by transferring knowledge from a high-resource language to low-resource languages. Despite the great success, we draw an empirical observation that there is a training objective gap between pre-training and fine-tuning stages: e.g., mask language modeling objective requires local understanding of the masked token and the span-extraction objective requires global understanding and reasoning of the input …
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 Institute of Technology Karnataka（卡纳塔克邦国立理工学院）；Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）
Developing Named Entity Recognition (NER) systems for Indian languages has been a long-standing challenge, mainly owing to the requirement of a large amount of annotated clean training instances. This paper proposes an end-to-end framework for NER for Indian languages in a low-resource setting by exploiting parallel corpora of English and Indian languages and an English NER dataset. The proposed framework includes an annotation projection method that combines word alignment score and NER tag prediction confidence score on source language (English) data to generate weakly labeled data in a targ…
While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable such transfer. Analyses involving pairs of natural languages are often inconclusive and contradictory since languages simultaneously differ in many linguistic aspects. In this paper, we perform a large-scale empirical study to isolate the effects of various linguistic properties by measuring zero-shot transfer between four diverse natural languages and their…
Computer Science Department, Bar Ilan University（巴伊兰大学计算机科学系）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple methods that expose remarkable translation capabilities with no fine-tuning. The results suggest that most of this information is encoded in a non-linear way, while some of it can also be recovered with purely linear tools. As part of our analysis, we test the hypothesis that mBERT learns representations which contain both a language-encoding component and an ab…
University of Chile（智利大学）；Millennium Institute for Foundational Research on Data (IMFD)（数据基础研究千年研究所（IMFD））；National Center for Artificial Intelligence (CENIA)（国家人工智能中心（CENIA））
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are re…
