The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an under-studied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages - without access to large-scale monolingual corpora or large amounts of labeled data - for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.
Meta learning with auxiliary languages has demonstrated promising improvements for cross-lingual natural language processing. However, previous studies sample the meta-training and meta-testing data from the same language, which limits the ability of the model for cross-lingual transfer. In this paper, we propose XLA-MAML, which performs direct cross-lingual adaption in the meta-learning stage. We conduct zero-shot and few-shot experiments on Natural Language Inference and Question Answering. The experimental results demonstrate the effectiveness of our method across different languages, tasks…
The success of pretrained cross-lingual language models relies on two essential abilities, i.e., generalization ability for learning downstream tasks in a source language, and cross-lingual transferability for transferring the task knowledge to other languages. However, current methods jointly learn the two abilities in a single-phase cross-lingual pretraining process, resulting in a trade-off between generalization and cross-lingual transfer. In this paper, we propose cross-lingual language model meta-pretraining, which learns the two abilities in different training phases. Our method introdu…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）；Adobe Research（Adobe研究院）
Multilingual models, such as M-BERT and XLM-R, have gained increasing popularity, due to their zero-shot cross-lingual transfer learning capabilities. However, their generalization ability is still inconsistent for typologically diverse languages and across different benchmarks. Recently, meta-learning has garnered attention as a promising technique for enhancing transfer learning under low-resource scenarios: particularly for cross-lingual transfer in Natural Language Understanding (NLU). In this work, we propose X-METRA-ADA, a cross-lingual MEta-TRAnsfer learning ADAptation approach for NLU.…
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…
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…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
Localizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods although these approaches can struggle to model how native speakers ask questions. We consider how to effectively leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing. We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample efficiency during cross-lingual transfer. Our algorithm uses high-resource languages to train the parser and si…
Istituto di Scienza e Tecnologie dell’Informazione, Consiglio Nazionale delle Ricerche（信息科学与技术研究所，意大利国家研究委员会）；Dipartimento di Informatica, Università di Pisa（比萨大学信息学院）
\emph{Funnelling} (Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classifiers, each working on a different and language-dependent feature space, return a vector of calibrated posterior probabilities (with one dimension for each class) for each document, and the final classification decision is taken by a metaclassifier that uses this vector as its input. The metaclassifier can thus exploit class-class correlations, and this (among other things) giv…
The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint training when limited target-language data is available during training. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability and show …
University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）；King’s College London（伦敦国王学院）
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual dependency parsing. We train our model on a diverse set of languages to learn a parameter initialization that can adapt quickly to new languages. We find that meta-learning with pre-training can significantly improve upon the performance of language transfer and standard supervised learning baselines for a variety of unseen, typologically diverse, and low…
University of Oslo（奥斯陆大学）；Vrije Universiteit Brussel - imec（布鲁塞尔自由大学 - 欧洲微电子研究中心）；University of Copenhagen（哥本哈根大学）；Aalborg University（奥尔堡大学）
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as most languages in the world are under-resourced. Here, we consider the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning, where, in addition to training a source language model, another model…
University of Amsterdam（阿姆斯特丹大学）；Google Research（谷歌研究院）
Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this paper, we propose novel methods for using language-specific subnetworks, which control cross-lingual parameter sharing, to reduce conflicts and increase positive transfer during fine-tuning. We introduce dynamic subnetworks, which are jointly updated with the model, and we combine our methods with meta-learning, an established, but complementary, technique fo…
Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization
University of California, San Diego（加利福尼亚大学圣迭戈分校）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）
Supervised deep learning-based approaches have been applied to task-oriented dialog and have proven to be effective for limited domain and language applications when a sufficient number of training examples are available. In practice, these approaches suffer from the drawbacks of domain-driven design and under-resourced languages. Domain and language models are supposed to grow and change as the problem space evolves. On one hand, research on transfer learning has demonstrated the cross-lingual ability of multilingual Transformers-based models to learn semantically rich representations. On the…
A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition
National Institute for Research and Development in Informatics - ICI Bucharest（布加勒斯特国家信息研究与发展学院）；Academy of Romanian Scientists（罗马尼亚科学院）；University of Bucharest（布加勒斯特大学）；National University of Science and Technology POLITEHNICA Bucharest（布加勒斯特理工国立科技大学）；Paris 1 Panthéon-Sorbonne University（巴黎第一大学先贤祠-索邦大学）
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized re…
Cross-Lingual Steering for Figurative Language Generation
Department of Computer Science, University of Cincinnati（卡内基梅隆大学计算机科学系）；School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院）；Independent Researcher（独立研究者）
Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits accruing to low-resource languages. However, recent work has shown that this approach can degrade performance on high-resource languages, a phenomenon known as negative interference. In this paper, we present the first systematic study of negative interference. We show that, contrary to previous belief, negative interference also impacts low-resource languages. While parameters are maximally shared to learn language-u…
Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs
Nilekani Centre at AI4Bharat（AI4Bharat 奈尔肯中心）；IIT Madras（印度理工学院马德拉斯分校）；New York University（纽约大学）；Microsoft（微软）；National Institute of Information and Communications Technology, Kyoto, Japan（京都国立信息与通信技术研究所）
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）
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this paper, we study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting by considering the inference speed, performance, and number of parameters to measure their practicality. We conduct experiments in three language pairs on named entity recognition and part-of-speech tagging and compa…
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related. Sharing information between unrelated tasks might hurt performance, and it is unclear how to transfer knowledge across tasks with a hierarchical structure. Our research extends a model agnostic meta-learning model, MAML, by exploiting hierarchical task relationships. Our algorithm, TreeMAML, adapts the model to each task with a few gradient steps, but the adaptation follows the hierarchical tree structure: in each step, gradients are pooled across tasks clu…
Pralekha: Cross-Lingual Document Alignment for Indic Languages
Nilekani Centre at AI4Bharat（AI4Bharat的Nilekani中心）；Microsoft（微软）；National Institute of Information and Communications Technology, Japan（日本信息与通信技术国家研究所）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Indian Institute of Technology, Bombay（印度理工学院孟买分校）
CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents
CONICET-Universidad de Buenos Aires. Instituto de Ciencias de la Computación (ICC). Buenos Aires, Argentina（CONICET-阿根廷布宜诺斯艾利斯大学。信息计算研究所（ICC）。布宜诺斯艾利斯，阿根廷）；École de bibliothéconomie et des sciences de l’information. Université de Montréal. Montréal, Canada（信息与图书馆科学学院。蒙特利尔大学。蒙特利尔，加拿大）
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高科技园区（滨江）区块链与数据安全研究院）；Tongyi Lab, Alibaba Group（阿里集团通义实验室）；Nanyang Technological University（南洋理工大学）
Charles University, Faculty of Mathematics and Physics（查理大学数学与物理学院）
We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous approaches. Our model is based on Tacotron 2 with a fully convolutional input text encoder whose weights are predicted by a separate parameter generator network. To boost voice cloning, the model uses an adversarial speaker classifier with a gradient reversal layer that removes speaker-specific information from the encoder. We arranged two experiments to compa…
University of the Basque Country UPV/EHU（巴斯克大学UPV/EHU）
The lack of wide coverage datasets annotated with everyday metaphorical expressions for languages other than English is striking. This means that most research on supervised metaphor detection has been published only for that language. In order to address this issue, this work presents the first corpus annotated with naturally occurring metaphors in Spanish large enough to develop systems to perform metaphor detection. The presented dataset, CoMeta, includes texts from various domains, namely, news, political discourse, Wikipedia and reviews. In order to label CoMeta, we apply the MIPVU method…
This paper presents a novel prototype for biomedical term normalization of electronic health record excerpts with the Unified Medical Language System (UMLS) Metathesaurus. Despite being multilingual and cross-lingual by design, we first focus on processing clinical text in Spanish because there is no existing tool for this language and for this specific purpose. The tool is based on Apache Lucene to index the Metathesaurus and generate mapping candidates from input text. It uses the IXA pipeline for basic language processing and resolves ambiguities with the UKB toolkit. It has been evaluated …
The University of Edinburgh（爱丁堡大学）；Samsung AI Research Centre, Cambridge（三星人工智能研究中心）
Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing approaches are relatively expensive as they need to compute second-order derivatives and store a longer computational graph. This cost prevents scaling them to larger network architectures. We present EvoGrad, a new approach to meta-learning that draws upon evolutionary techniques to more efficiently compute hypergradients. EvoGrad estimates hypergradient with respect to hyperpa…
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previ…
BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation
School of Computer Engineering and Science, Shanghai University, Shanghai, China（1 上海大学计算机工程与科学学院，上海，中国）；Funstory.ai Limited, Hong Kong SAR, China（2 Funstory.ai有限公司，香港特别行政区，中国）；Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China（3 上海交通大学计算机科学与工程系，上海，中国）
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the cross-lingual transfer is not uniform across languages, particularly in the zero-shot setting. Towards this goal, one promising research direction is to learn shareable structures across multiple tasks with limited annotated data. The downstream multilingual applications may benefit from such a learning setup as most of the languages across the globe are low-resou…
For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to th…
