本文提出了一种贝叶斯多语言文档模型，用于学习独立于语言的文档嵌入。该模型是 BaySMM [Kesiraju et al 2020] 在多语言场景下的扩展。它学习以高斯分布的形式表示文档嵌入，从而在其协方差中编码不确定性。我们将学习到的不确定性传播到线性分类器中，这有利于零样本跨语言主题识别。我们在 17 种语言上的实验表明，与其他基于大规模神经网络（LASER、XLM-R、mUSE）的系统相比，所提出的多语言贝叶斯文档模型在 8 种高资源语言上表现具有竞争力，并在 9 种中资源语言上优于这些系统。我们通过深入探讨当前的数据集、基线系统和涵盖的语言，重新审视了零样本设置下的跨语言主题识别。我们发现了现有评估协议（MLDoc 数据集）的缺陷，并提出了一种稳健的替代方案，同时将跨语言实验设置扩展到 17 种语言。最后，我们整合了所有实验的观察结果，并讨论了可能有益于依赖跨语言迁移的应用中未来研究工作的要点。
英文摘要：
In this paper, we present a Bayesian multilingual document model for learning language-independent document embeddings. The model is an extension of BaySMM [Kesiraju et al 2020] to the multilingual scenario. It learns to represent the document embeddings in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. We propagate the learned uncertainties through linear classifiers that benefit zero-shot cross-lingual topic identification. Our experiments on 17 languages show that the proposed multilingual Bayesian document model performs competitively, when compared to other systems based on large-scale neural networks (LASER, XLM-R, mUSE) on 8 high-resource languages, and outperforms these systems on 9 mid-resource languages. We revisit cross-lingual topic identification in zero-shot settings by taking a deeper dive into current datasets, baseline systems and the languages covered. We identify shortcomings in the existing evaluation protocol (MLDoc dataset), and propose a robust alternative scheme, while also extending the cross-lingual experimental setup to 17 languages. Finally, we consolidate the observations from all our experiments, and discuss points that can potentially benefit the future research works in applications relying on cross-lingual transfers.
Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure AI（微软Azure人工智能）
Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chin…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level genera…
Facebook AI Research（脸书人工智能研究院）；Facebook AML（脸书应用机器学习部门）
Cross-lingual document classification aims at training a document classifier on resources in one language and transferring it to a different language without any additional resources. Several approaches have been proposed in the literature and the current best practice is to evaluate them on a subset of the Reuters Corpus Volume 2. However, this subset covers only few languages (English, German, French and Spanish) and almost all published works focus on the the transfer between English and German. In addition, we have observed that the class prior distributions differ significantly between th…
Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
Instituto Superior Técnico, Universidade de Lisboa (ELLIS Unit Lisbon)（里斯本大学理工学院（ELLIS单位里斯本））；Instituto de Telecomunicações（电信研究所）；Carnegie Mellon University（卡内基梅隆大学）；Unbabel
University of Edinburgh（爱丁堡大学）；Google Research（谷歌研究院）
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily available. In this paper, we study whether and how contextual modeling in DocNMT is transferable via multilingual modeling. We focus on the scenario of zero-shot transfer from teacher languages with document level data to student languages with no documents but sentence level data, and for the first time treat document-level translation as a transfer learning …
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 Copenhagen（哥本哈根大学）；Athens University of Economics and Business（雅典经济与商业大学）；Cognitiv+ Ltd.（Cognitiv+ 有限公司）
We introduce MULTI-EURLEX, a new multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. We highlight the effect of temporal concept drift and the importance of chronological, instead of random splits. We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target). We find that fine-tuning a multilingually pret…
The Hong Kong University of Science and Technology（香港科技大学）
One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM neural machine translation model. This paper presents a transformer-based sentence/document embedding model, T-LASER, which makes three significant improvements. Firstly, the BiLSTM layers is replaced by the attention-based transformer layers, which is more capable of learning sequential patterns in longer texts. Secondly, due to the absence of recurrence, T-LASER enables faster parallel computations in the encoder to generate the text embedding. Thirdly, we augment the NMT transl…
In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN) parallel corpus retrieval task. In all the languages tested, the system achieves P@1 of 86% or higher. We use pairs retrieved by our approach to train NMT models that achieve similar performance to models trained on gold pairs. We explore simple document-level embeddings constructed by averaging our sentence embeddings. On the UN document-level retrieval task, docu…
TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries
College of Application and Technology, Shenzhen University, China（应用技术学院，深圳大学，中国）；College of Big Data and Internet, Shenzhen Technology University, China（大数据与互联网学院，深圳科技大学，中国）
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 …
University of the Basque Country (UPV/EHU)（巴斯克大学 (UPV/EHU)）
In this paper we present an approach to extract ordered timelines of events, their participants, locations and times from a set of multilingual and cross-lingual data sources. Based on the assumption that event-related information can be recovered from different documents written in different languages, we extend the Cross-document Event Ordering task presented at SemEval 2015 by specifying two new tasks for, respectively, Multilingual and Cross-lingual Timeline Extraction. We then develop three deterministic algorithms for timeline extraction based on two main ideas. First, we address implici…
Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. Such aligned data can be used for a variety of NLP tasks from training cross-lingual representations to mining parallel data for machine translation. In this paper we develop an unsupervised scoring function that leverages cross-lingual sentence embeddings to compute the semantic distance between documents in different languages. These semantic distances are then used to guide a document alignment algorithm to properly pair cross-lingual web documents a…
Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
Research Laboratory in Algebra Numbers theory and Intelligent Systems（代数数论与智能系统研究实验室）；CNRS（法国国家科学研究中心）；Bordeaux INP（波尔多国立高等工程技术学院）；LaBRI（波尔多计算机科学实验室）；Laboratory LIG（LIG实验室）
Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data
Centre for Data Science, School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia（数据科学中心，计算机科学学院，昆士兰理工大学，布里斯班，QLD 4000，澳大利亚）
Nowadays, digital news articles are widely available, published by various editors and often written in different languages. This large volume of diverse and unorganized information makes human reading very difficult or almost impossible. This leads to a need for algorithms able to arrange high amount of multilingual news into stories. To this purpose, we extend previous works on Topic Detection and Tracking, and propose a new system inspired from newsLens. We process articles per batch, looking for monolingual local topics which are then linked across time and languages. Here, we introduce a …
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 Colorado（科罗拉多大学）；University of Maryland（马里兰大学）
Multilingual topic models enable document analysis across languages through coherent multilingual summaries of the data. However, there is no standard and effective metric to evaluate the quality of multilingual topics. We introduce a new intrinsic evaluation of multilingual topic models that correlates well with human judgments of multilingual topic coherence as well as performance in downstream applications. Importantly, we also study evaluation for low-resource languages. Because standard metrics fail to accurately measure topic quality when robust external resources are unavailable, we pro…
Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first demystify the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. Based on this analysis, we then relax the assumption of training data required by most existing models, creating a model that only requires a dictionary for training. Experiments show that our new method effectively learns coherent…
Idiap Research Institute（伊迪亚普研究所）；HEIG-VD / HES-SO（沃州工程与管理高等学院 / 瑞士西部应用科学与艺术大学）
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging but potentially beneficial objective. To this end, we propose multilingual hierarchical attention networks for learning document structures, with shared encoders and/or shared attention mechanisms across …
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 …
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand. In this paper, instead of these unsupervised distance measurement techniques, we employ Metric Learning to derive task-specific distance measurements. These measurements are supervised, meaning that the distance measurement metric is trained using a parallel dataset. Using a dataset belonging to English, Sinhala, and Tamil, which belong to three …
Probabilistic topic modeling is a popular choice as the first step of crosslingual tasks to enable knowledge transfer and extract multilingual features. While many multilingual topic models have been developed, their assumptions on the training corpus are quite varied, and it is not clear how well the models can be applied under various training conditions. In this paper, we systematically study the knowledge transfer mechanisms behind different multilingual topic models, and through a broad set of experiments with four models on ten languages, we provide empirical insights that can inform the…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Text discourse parsing weighs importantly in understanding information flow and argumentative structure in natural language, making it beneficial for downstream tasks. While previous work significantly improves the performance of RST discourse parsing, they are not readily applicable to practical use cases: (1) EDU segmentation is not integrated into most existing tree parsing frameworks, thus it is not straightforward to apply such models on newly-coming data. (2) Most parsers cannot be used in multilingual scenarios, because they are developed only in English. (3) Parsers trained from single…
Language Identification in textual documents is the process of automatically detecting the language contained in a document based on its content. The present Language Identification techniques presume that a document contains text in one of the fixed set of languages, however, this presumption is incorrect when dealing with multilingual document which includes content in more than one possible language. Due to the unavailability of large standard corpora for Hindi-English mixed lingual language processing tasks we propose the language lexicons, a novel kind of lexical database that supports se…
MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching
Center for Artificial Intelligence and Data Science, University of Würzburg（维尔茨堡大学人工智能与数据科学中心）；Language Technology Group, University of Hamburg（汉堡大学语言技术组）
The need for raw large raw corpora has dramatically increased in recent years with the introduction of transfer learning and semi-supervised learning methods to Natural Language Processing. And while there have been some recent attempts to manually curate the amount of data necessary to train large language models, the main way to obtain this data is still through automatic web crawling. In this paper we take the existing multilingual web corpus OSCAR and its pipeline Ungoliant that extracts and classifies data from Common Crawl at the line level, and propose a set of improvements and automati…
We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective…
This paper presents M3L-Contrast -- a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is trained jointly on texts and images and takes advantage of pretrained document and image embeddings to abstract the complexities between different languages and modalities. As a multilingual topic model, it produces aligned language-specific topics and as multimodal model, it infers textual representations of semantic concepts in images. We demonstrate that our model is competitive with a zero…
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 q…
This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text segments from the online documentation for an enterprise software platform. These Web pages have been professionally translated from English into 16 languages and maintained by domain experts, and around 100,000 text segments are available for each language pair. We build and evaluate translation models for seven target languages from English, with several d…
