Multilingual contextual embeddings have demonstrated state-of-the-art performance in zero-shot cross-lingual transfer learning, where multilingual BERT is fine-tuned on one source language and evaluated on a different target language. However, published results for mBERT zero-shot accuracy vary as much as 17 points on the MLDoc classification task across four papers. We show that the standard practice of using English dev accuracy for model selection in the zero-shot setting makes it difficult to obtain reproducible results on the MLDoc and XNLI tasks. English dev accuracy is often uncorrelated (or even anti-correlated) with target language accuracy, and zero-shot performance varies greatly at different points in the same fine-tuning run and between different fine-tuning runs. These reproducibility issues are also present for other tasks with different pre-trained embeddings (e.g., MLQA with XLM-R). We recommend providing oracle scores alongside zero-shot results: still fine-tune using English data, but choose a checkpoint with the target dev set. Reporting this upper bound makes results more consistent by avoiding arbitrarily bad checkpoints.
Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages. The idea is to focus on a single representation for a pair of languages such that semantically similar words are closer to one another in the induced representation irrespective of the language. In this way, when data are missing for a particular language, classifiers from another language can be used.
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented dialogue system to low-resource languages. To tackle this challenge, we first use a set of very few parallel word pairs to refine the aligned cross-lingual word-level representations. We then employ a latent variable model to cope with the variance of similar sentences across different languages, which is induced by imperfect cross-lingual alignments and inher…
University of Ljubljana（卢布尔雅那大学）；Jožef Stefan Institute（约瑟夫·斯特凡研究所）
Word embeddings represent words in a numeric space so that semantic relations between words are represented as distances and directions in the vector space. Cross-lingual word embeddings transform vector spaces of different languages so that similar words are aligned. This is done by constructing a mapping between vector spaces of two languages or learning a joint vector space for multiple languages. Cross-lingual embeddings can be used to transfer machine learning models between languages, thereby compensating for insufficient data in less-resourced languages. We use cross-lingual word embedd…
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related languages which is not utilized by these methods. This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages. This is done by mapping phonemes of the training languages to the target language using articulatory features. Experiments show that this simple me…
University of Florida（佛罗里达大学）；Amazon Alexa AI（亚马逊Alexa人工智能）
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve this problem, from conventional rulebased or statistical slot-filling systems to shiftreduce based neural parsers. For complex parsing tasks, the state-of-the-art method is based on autoregressive sequence to sequence models to generate the parse directly. This model is slow at inference time, generating parses in O(n) decoding steps (n is the length of the targ…
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…
We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i.e. Hanja). We employ cross-lingual transfer learning in training word representations by leveraging the fact that Hanja is closely related to Chinese. We evaluate the intrinsic quality of representations learned through our approach using the word analogy and similarity tests. In addition, we demonstrate their effectiveness on several downstream tasks, including a novel Korean news headline generation task.
Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input models for structured prediction. We show that the means of aggregating over the input models is critical, and that multiplying marginal probabilities of substructures to obtain high-probability structures for distant supervision is substantially better than taking the union of such structures over the input models, as done in prior work. Testing on 18 languages…
This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the dec…
There is an increasing amount of evidence that in cases with little or no data in a target language, training on a different language can yield surprisingly good results. However, currently there are no established guidelines for choosing the training (source) language. In attempt to solve this issue we thoroughly analyze a state-of-the-art multilingual model and try to determine what impacts good transfer between languages. As opposed to the majority of multilingual NLP literature, we don't only train on English, but on a group of almost 30 languages. We show that looking at particular syntac…
The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Charles University in Prague（布拉格查理大学）
We show that the choice of pretraining languages affects downstream cross-lingual transfer for BERT-based models. We inspect zero-shot performance in balanced data conditions to mitigate data size confounds, classifying pretraining languages that improve downstream performance as donors, and languages that are improved in zero-shot performance as recipients. We develop a method of quadratic time complexity in the number of languages to estimate these relations, instead of an exponential exhaustive computation of all possible combinations. We find that our method is effective on a diverse set o…
Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them for new speakers or languages is not straightforward in a low-resource setup. In this paper, we show that by applying minor modifications to a Tacotron model, one can transfer an existing TTS model for new speakers from the same or a different language using only 20 minutes of data. For this purpose, we first introduce a base multi-lingual Tacotron with language-agnostic input, then demonstrate how transfer learning is done for different scenarios of speaker a…
Southern Medical University（南方医科大学）；Mayo Clinic（妙佑医疗国际）
Text classification is a fundamental task for text data mining. In order to train a generalizable model, a large volume of text must be collected. To address data insufficiency, cross-lingual data may occasionally be necessary. Cross-lingual data sources may however suffer from data incompatibility, as text written in different languages can hold distinct word sequences and semantic patterns. Machine translation and word embedding alignment provide an effective way to transform and combine data for cross-lingual data training. To the best of our knowledge, there has been little work done on ev…
National University of Ireland（爱尔兰国立大学）；Aylien Ltd.（Aylien有限公司）；University of Cambridge（剑桥大学）；University of Copenhagen（哥本哈根大学）
Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent modulo optimization strategies, hy…
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. We utilized these findings to develop a new approach -- cross-lingual retrieval for iterative self-supervised training (CRISS), where mining and training processes are applied iteratively, improving cross-lingual alignment and translation ability at the same time. Using this method, we achieved state-of-the-art unsupervis…
Bilingual Word Embeddings (BWEs) are one of the cornerstones of cross-lingual transfer of NLP models. They can be built using only monolingual corpora without supervision leading to numerous works focusing on unsupervised BWEs. However, most of the current approaches to build unsupervised BWEs do not compare their results with methods based on easy-to-access cross-lingual signals. In this paper, we argue that such signals should always be considered when developing unsupervised BWE methods. The two approaches we find most effective are: 1) using identical words as seed lexicons (which unsuperv…
Hong Kong University of Science and Technology（香港科技大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingual Dataless Document Classification (CLDDC) relies on mapping the English labels or short category description into a Wikipedia-based semantic representation, and on the use of the target language Wikipedia. Consequently, performance could suffer when Wikipedia in the target language is small. In this paper, we focus on languages with small Wikipedias, (Small-Wikipedia languages, SWLs). We use a word-level dictionary …
University of Geneva（日内瓦大学）；Idiap Research Institute（Idiap研究所）
Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages. Current unsupervised adversarial approaches show that it is possible to build a mapping matrix that align two sets of monolingual word embeddings together without high quality parallel data such as a dictionary or a sentence-aligned corpus. However, without post refinement, the performance of these methods' preliminary mapping is not good, leading to poor performance for typologically …
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the fine-tuned model is evaluated on another target language. While this works surprisingly well, substantial variance has been observed in target language performance between different fine-tuning runs, and in the zero-shot setup, no target-language development data is available to select among multiple fine-tuned models. Prior work has relied on English dev data to se…
University of Amsterdam（阿姆斯特丹大学）；University of Copenhagen（哥本哈根大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
When humans read a text, their eye movements are influenced by the structural complexity of the input sentences. This cognitive phenomenon holds across languages and recent studies indicate that multilingual language models utilize structural similarities between languages to facilitate cross-lingual transfer. We use sentence-level eye-tracking patterns as a cognitive indicator for structural complexity and show that the multilingual model XLM-RoBERTa can successfully predict varied patterns for 13 typologically diverse languages, despite being fine-tuned only on English data. We quantify the …
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of high-quality data. In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented dialogue systems. It leverages very few task-related parallel word pairs to generate code-switching sentences for learning the inter-lingual semant…
Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Microsoft Research Asia（微软亚洲研究院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
本文分析了多语言模型跨语言迁移中的性能差距问题，发现影响性能的关键网络权重，并提出包含四种训练策略的Fine-tuning slow and fast方法，通过减少遗忘有效缩小差距，显著优于基线方法。
University of Augsburg（奥格斯堡大学）；TU Munich（慕尼黑工业大学）；Imperial College London（帝国理工学院）
Detecting hate speech, especially in low-resource languages, is a non-trivial challenge. To tackle this, we developed a tailored architecture based on frozen, pre-trained Transformers to examine cross-lingual zero-shot and few-shot learning, in addition to uni-lingual learning, on the HatEval challenge data set. With our novel attention-based classification block AXEL, we demonstrate highly competitive results on the English and Spanish subsets. We also re-sample the English subset, enabling additional, meaningful comparisons in the future.
Relevant and timely information collected from social media during crises can be an invaluable resource for emergency management. However, extracting this information remains a challenging task, particularly when dealing with social media postings in multiple languages. This work proposes a cross-lingual method for retrieving and summarizing crisis-relevant information from social media postings. We describe a uniform way of expressing various information needs through structured queries and a way of creating summaries answering those information needs. The method is based on multilingual tran…
Pretrained contextual representation models (Peters et al., 2018; Devlin et al., 2018) have pushed forward the state-of-the-art on many NLP tasks. A new release of BERT (Devlin, 2018) includes a model simultaneously pretrained on 104 languages with impressive performance for zero-shot cross-lingual transfer on a natural language inference task. This paper explores the broader cross-lingual potential of mBERT (multilingual) as a zero shot language transfer model on 5 NLP tasks covering a total of 39 languages from various language families: NLI, document classification, NER, POS tagging, and de…
Athens University of Economics and Business（雅典经济与商业大学）；Cognitiv+ Ltd（Cognitiv+有限公司）；University of Copenhagen（哥本哈根大学）
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a new version of the dataset without parallel documents. We use it to show that translation-based methods vastly outperform cross-lingual fine-tuning of multilingually pre-trained models, the best previous zero-shot transfer method for MultiEURLEX. We also develop a bilingual teacher-student zero-shot transfer approach, which exploits additional unlabeled doc…
Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in multilingual understanding due to the steeply increasing necessity of working in different languages. One of the points that stands out is that since there are now so many pre-trained multilingual models, we can utilize them for cross-lingual understanding tasks. Using cross-lingual understanding and Natural Language Inference, it is possible to train models whose app…
Georgia Institute of Technology（佐治亚理工学院）；Samsung AI Center（三星人工智能中心）；University of Edinburgh（爱丁堡大学）
The availability of corpora to train semantic parsers in English has lead to significant advances in the field. Unfortunately, for languages other than English, annotation is scarce and so are developed parsers. We then ask: could a parser trained in English be applied to language that it hasn't been trained on? To answer this question we explore zero-shot cross-lingual semantic parsing where we train an available coarse-to-fine semantic parser (Liu et al., 2018) using cross-lingual word embeddings and universal dependencies in English and test it on Italian, German and Dutch. Results on the P…
Harbin Institute of Technology（哈尔滨工业大学）；MIT（麻省理工学院）
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018). In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages. We demonstrate the effectiveness of this approach on zero-shot cross-lingual transfer parsing. Experiments show …
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…
NLP systems typically require support for more than one language. As different languages have different amounts of supervision, cross-lingual transfer benefits languages with little to no training data by transferring from other languages. From an engineering perspective, multilingual NLP benefits development and maintenance by serving multiple languages with a single system. Both cross-lingual transfer and multilingual NLP rely on cross-lingual representations serving as the foundation. As BERT revolutionized representation learning and NLP, it also revolutionized cross-lingual representation…
University of Campinas（坎皮纳斯大学）；NeuralMind；University of Waterloo（滑铁卢大学）
An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate…
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Centre for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；Faculty of Mathematics and Physics, Charles University（查理大学数学与物理学院）
Universidade de Vigo（维戈大学）；University of the Basque Country (UPV/EHU)（巴斯克大学）；Universitat Oberta de Catalunya（加泰罗尼亚开放大学）
Language resources are necessary for language processing,but building them is costly, involves many researches from different areas and needs constant updating. In this paper, we describe the crosslingual framework used for developing the Multilingual Central Repository (MCR), a multilingual knowledge base that includes wordnets of Basque, Catalan, English, Galician, Portuguese, Spanish and the following ontologies: Base Concepts, Top Ontology, WordNet Domains and Suggested Upper Merged Ontology. We present the story of MCR, its state in 2017 and the developed tools.
We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is to capture similarities as well as idiosyncrasies among typologically different languages. In this paper, we show that models trained using UD parse trees for complex NLP tasks can characterize very different languages. We study two tasks of paraphrase identification and semantic relation extraction as case studies. Based on UD parse trees, we develop several…
The George Washington University（乔治华盛顿大学）；AWS, Amazon AI（亚马逊云科技，亚马逊人工智能）
We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment. Our results support representation transfer as a scalable approach for modular cross-lingual alignment of neural sentence embeddings, where we observe better performance compared to joint models in intrinsic and extri…
Facebook AI Research（脸书人工智能研究院）；University College London（伦敦大学学院）
Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English, making training QA systems in other languages challenging. An alternative to building large monolingual training datasets is to develop cross-lingual systems which can transfer to a target language without requiring training data in that language. In order to develop such systems, it is crucial to invest in high quality multilingual evaluation benchmarks to m…
Recent advances in cross-lingual commonsense reasoning (CSR) are facilitated by the development of multilingual pre-trained models (mPTMs). While mPTMs show the potential to encode commonsense knowledge for different languages, transferring commonsense knowledge learned in large-scale English corpus to other languages is challenging. To address this problem, we propose the attention-based Cross-LIngual Commonsense Knowledge transfER (CLICKER) framework, which minimizes the performance gaps between English and non-English languages in commonsense question-answering tasks. CLICKER effectively im…
Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this operation. Otherwise, its performance will drop sharply, thus making it impractical to be deployed to memory-limited devices. To address this issue, we delve into cross-lingual knowledge distillation and propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model. In our framework, contrastive learning, bottle…
Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP
Ghent University（根特大学）；imec；KU Leuven（鲁汶大学）；BeCode asbl；Internet and Data Science Lab (IDLab)（互联网与数据科学实验室（IDLab））；AI & Data Bootcamp Ghent 2024（2024年根特人工智能与数据训练营）
Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that different natural languages share enough semantic structure that it should be possible, in principle, to learn compatible vector representations just by analyzing the monolingual distribution of words. In order to evaluate this hypothesis, we propose a scheme to map word vectors trained on a source language to vectors semantically compatible with word vectors…
Negation scope has been annotated in several English and Chinese corpora, and highly accurate models for this task in these languages have been learned from these annotations. Unfortunately, annotations are not available in other languages. Could a model that detects negation scope be applied to a language that it hasn't been trained on? We develop neural models that learn from cross-lingual word embeddings or universal dependencies in English, and test them on Chinese, showing that they work surprisingly well. We find that modelling syntax is helpful even in monolingual settings and that cros…
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on high-resource languages so that it transfers well to the zero-shot languages is a non-trivial task. In this paper, we propose a novel meta-optimizer to soft-select which layers of the pre-trained model to freeze during fine-tuning. We train the meta-optimizer by simulating the zero-shot transfer scenario. Results on cross-lingual natural language inference show that…
University of Cambridge（剑桥大学）；University of Würzburg（维尔茨堡大学）；University of Edinburgh（爱丁堡大学）
Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear how to best leverage them to represent sub-sentence lexical items (i.e., words and phrases) in cross-lingual lexical tasks. In this work, we probe SEs for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a simple yet efficient method for exposing the cross-lingual l…
The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language barrier using language universal representations. However, even if the language problem was resolved, models trained in one language would not transfer to another language perfectly due to the natural domain drift across languages and cultures. We consider the setting of semi-supervised cross-lingual understanding, where labeled data is available in a source lang…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Facebook AI（脸书人工智能研究院）
In recent years, we have seen a colossal effort in pre-training multilingual text encoders using large-scale corpora in many languages to facilitate cross-lingual transfer learning. However, due to typological differences across languages, the cross-lingual transfer is challenging. Nevertheless, language syntax, e.g., syntactic dependencies, can bridge the typological gap. Previous works have shown that pre-trained multilingual encoders, such as mBERT \cite{devlin-etal-2019-bert}, capture language syntax, helping cross-lingual transfer. This work shows that explicitly providing language syntax…
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…
