Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English. They not only suffer from the shortcomings of non-English document retrieval, but are reliant on language-specific supervision for either the task or translation. We formulate a task setup more realistic to available resources, that circumvents document retrieval to reliably transfer knowledge from English to lower resource languages. Assuming a strong English question answering model or database, we compare and analyze methods that pivot through English: to map foreign queries to English and then English answers back to target language answers. Within this task setup we propose Reranked Multilingual Maximal Inner Product Search (RM-MIPS), akin to semantic similarity retrieval over the English training set with reranking, which outperforms the strongest baselines by 2.7% on XQuAD and 6.2% on MKQA. Analysis demonstrates the particular efficacy of this strategy over state-of-the-art alternatives in challenging settings: low-resource languages, with extensive distractor data and query distribution misalignment. Circumventing retrieval, our analysis shows this approach offers rapid answer generation to almost any language off-the-shelf, without the need for any additional training data in the target language.
Carnegie Mellon University（卡内基梅隆大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
We demonstrate a new approach to Neural Machine Translation (NMT) for low-resource languages using a ubiquitous linguistic resource, Interlinear Glossed Text (IGT). IGT represents a non-English sentence as a sequence of English lemmas and morpheme labels. As such, it can serve as a pivot or interlingua for NMT. Our contribution is four-fold. Firstly, we pool IGT for 1,497 languages in ODIN (54,545 glosses) and 70,918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25.94. We introduce a multilingual NMT model that tags all glossed text with gl…
SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics
MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP、信息与语言处理中心、慕尼黑大学）；Language Science and Technology, Saarland University（语言科学与技术、萨尔兰大学）
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Consumer Business Group（华为消费者业务集团）
Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to this end. However, we notice that the pivoting process involves multiple machine translation models and is likely to incur semantic drift during the two-step translations. In this paper, inspired by the Transformer-based language models, we propose a simple and unified paraphrasing model, which is purely trained on multilingual parallel data and can conduct …
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）
In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common representation for images and their descriptions in two different languages (which need not be parallel) by considering the image as a pivot between two languages. We introduce a new pairwise ranking loss function which can handle both symmetric and asymmetric similarity between the two modalities. We evaluate our models on image-description r…
The University of Tokyo（东京大学）；Salesforce Research（赛富时研究院）
Despite recent work in Reading Comprehension (RC), progress has been mostly limited to English due to the lack of large-scale datasets in other languages. In this work, we introduce the first RC system for languages without RC training data. Given a target language without RC training data and a pivot language with RC training data (e.g. English), our method leverages existing RC resources in the pivot language by combining a competitive RC model in the pivot language with an attentive Neural Machine Translation (NMT) model. We first translate the data from the target to the pivot language, an…
IIT Madras（印度理工学院马德拉斯分校）；IBM Research India（IBM印度研究院）；University of Montreal（蒙特利尔大学）
Recently there has been a lot of interest in learning common representations for multiple views of data. Typically, such common representations are learned using a parallel corpus between the two views (say, 1M images and their English captions). In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, $V_1$ and $V_2$) but parallel data is available between each of these views and a pivot view ($V_3$). We propose a model for learning a common representation for $V_1$, $V_2$ and $V_3$ using only the parallel data available bet…
Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；ByteDance Research（字节跳动研究院）；Damo Academy, Alibaba（阿里巴巴达摩院）
Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and low resource, one-to-many, and many-to-one translation). This paper concentrates on a deep understanding of multilingual NMT and conducts a comprehensive study on a multilingual dataset with more than 20 languages. Our results show that (1) low-resource language pairs benefit much from multilingual training, while rich-resource language pairs may get hurt und…
Microsoft Research（微软研究院）；Tencent Cloud（腾讯云）；Beihang University（北京航空航天大学）
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all languages compared to the two-pass pivot translation but often underperforms the pivot-based method. In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). Our method unifies source-teacher, target-teacher, and pivot-teacher models to guide the student model for the zero-resource translation. The …
For a news content distribution platform like Dailyhunt, Named Entity Recognition is a pivotal task for building better user recommendation and notification algorithms. Apart from identifying names, locations, organisations from the news for 13+ Indian languages and use them in algorithms, we also need to identify n-grams which do not necessarily fit in the definition of Named-Entity, yet they are important. For example, "me too movement", "beef ban", "alwar mob lynching". In this exercise, given an English language text, we are trying to detect case-less n-grams which convey important informa…
Economic issues related to the information processing techniques are very important. The development of such technologies is a major asset for developing countries like Cambodia and Laos, and emerging ones like Vietnam, Malaysia and Thailand. The MotAMot project aims to computerize an under-resourced language: Khmer, spoken mainly in Cambodia. The main goal of the project is the development of a multilingual lexical system targeted for Khmer. The macrostructure is a pivot one with each word sense of each language linked to a pivot axi. The microstructure comes from a simplification of the expl…
Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
Tsinghua University（清华大学）；Zhihu Inc.（知乎公司）；ModelBest Inc.（模贝斯特公司）；Beijing University of Posts and Telecommunications（北京邮电大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Renmin University of China（中国人民大学）
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）；Borealis AI（博瑞利斯人工智能公司）
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that we transit through. However, it is well-known that transiting through a poorly chosen pivot language (such as English) may severely degrade the translation quality, since the assumed transitive relations among all pairs of languages may not be enforced in the training process. Ins…
We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a language-independent representation by performing direct zero-shot translation (without using pivot translation), and by using the source sentence embeddings to create an English Yelp review classifier that, through the mediation of the neural interlingua, can also classify French and German reviews. Furthermore, we show that, despite using a smaller number of parameters than a pairwise collection of bilingual NMT models, our ap…
Maastricht University（马斯特里赫特大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an alternative to pivot translation which also allows us to better understand how the model captures information between languages. In this work, we carried out an investigation on this capability of the multilingual NMT models. First, we intentionally create an encoder architecture which is independent with respect to the source language. Such experiments shed …
In this paper, we present an extensive investigation of multi-bridge, many-to-many multilingual NMT models (MB-M2M) ie., models trained on non-English language pairs in addition to English-centric language pairs. In addition to validating previous work which shows that MB-M2M models can overcome zeroshot translation problems, our analysis reveals the following results about multibridge models: (1) it is possible to extract a reasonable amount of parallel corpora between non-English languages for low-resource languages (2) with limited non-English centric data, MB-M2M models are competitive wit…
Facebook AI Research（脸书人工智能研究院）；The University of Hong Kong（香港大学）；New York University（纽约大学）
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot. In this work, we address the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between la…
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）；University of Zurich（苏黎世大学）
Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot perfo…
The impact of different multilingual data mixtures in pretraining large language models (LLMs) has been a topic of ongoing debate, often raising concerns about potential trade-offs between language coverage and model performance (i.e., the curse of multilinguality). In this work, we investigate these assumptions by training 1.1B and 3B parameter LLMs on diverse multilingual corpora, varying the number of languages from 25 to 400. Our study challenges common beliefs surrounding multilingual training. First, we find that combining English and multilingual data does not necessarily degrade the in…
Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-tuning. In this work, we build upon some of the existing techniques for predicting the zero-shot performance on a task, by modeling it as a multi-task learning problem. We jointly train predictive models for different tasks which helps us build more accurate predictors for tasks where we have test data in very few languages to measure the actual pe…
University of Chicago（芝加哥大学）；University of Washington（华盛顿大学）
This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only two languages can encode multilingually more aligned representations. We thus introduce dual-pivot transfer: training on one language pair and evaluating on other pairs. To study this theory, we design unsupervised models trained on unpaired sentences and single-pair supervised models trained on bitexts, both based on the unsupervised language model XLM-R wit…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
We present the results of research with the goal of automatically creating a multilingual thesaurus based on the freely available resources of Wikipedia and WordNet. Our goal is to increase resources for natural language processing tasks such as machine translation targeting the Japanese-Spanish language pair. Given the scarcity of resources, we use existing English resources as a pivot for creating a trilingual Japanese-Spanish-English thesaurus. Our approach consists of extracting the translation tuples from Wikipedia, disambiguating them by mapping them to WordNet word senses. We present re…
Multilinguality is gradually becoming ubiquitous in the sense that more and more researchers have successfully shown that using additional languages help improve the results in many Natural Language Processing tasks. Multilingual Multiway Corpora (MMC) contain the same sentence in multiple languages. Such corpora have been primarily used for Multi-Source and Pivot Language Machine Translation but are also useful for developing multilingual sequence taggers by transfer learning. While these corpora are available, they are not organized for multilingual experiments and researchers need to write …
Contextualizing language technologies beyond a single language kindled embracing multiple modalities and languages. Individually, each of these directions undoubtedly proliferated into several NLP tasks. Despite this momentum, most of the multimodal research is primarily centered around English and multilingual research is primarily centered around contexts from text modality. Challenging this conventional setup, researchers studied the unification of multilingual and multimodal (MultiX) streams. The main goal of this work is to catalogue and characterize these works by charting out the catego…
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods great…
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
HKUST, Hong Kong（香港理工大学）；NVIDIA AI Technology Center (NVAITC), USA（NVIDIA AI技术中心（NVAITC））；Shanghai Jiao Tong University, China（上海交通大学）；Technische Universtität Darmstadt, Germany（德累斯顿技术大学）；LMU Munich, Germany（慕尼黑大学）；Munich Center for Machine Learning, Germany（慕尼黑机器学习中心）
Technische Universität Darmstadt（达姆施塔特工业大学）；University of Copenhagen（哥本哈根大学）；Aalborg University（奥尔堡大学）
Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In this work, we address these obstacles by removing language identity signals from multilingual embeddings. We examine three approaches for this: (i) re-aligning the vector spaces of target languages (all together) to a pivot source language; (ii) removing language-specific means and variances, which yields better discriminativeness of embeddings as a by-product;…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly lowresource multilingual setting. We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions. The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are the…
Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences（智能信息处理重点实验室，计算技术研究所，中国科学院）；State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；MMT Srl（MMT有限公司）
In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in translating low-resourced languages, due to the significant amount of parallel data that is required to learn useful mappings between languages. In this work, we show how the so-called multilingual NMT can help to tackle the challenges associated with low-resourced language translation. The underlying principle of multilingual NMT is to force the creation of hidden…
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
Department of CSE, Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校计算机科学与工程系）；Department of CSE, Indian Institute of Technology Bombay（印度理工学院孟买分校计算机科学与工程系）；SCEE, Indian Institute of Technology Mandi（印度理工学院曼迪分校软件工程系）；Adobe Research（Adobe研究）
