We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16. Reduced-rank singular value decomposition of a bilingual term-document matrix derived from known English/French page pairs in the training data allows us to map monolingual documents into a joint semantic space. Two variants of cosine similarity between the vectors that place each document into the joint semantic space are combined with a measure of string similarity between corresponding URLs to produce 1:1 alignments of English/French web pages in a variety of domains. The system achieves a recall of ca. 88% if no in-domain data is used for building the latent semantic model, and 93% if such data is included.
Analysing the system's errors on the training data, we argue that evaluating aligner performance based on exact URL matches under-estimates their true performance and propose an alternative that is able to account for duplicates and near-duplicates in the underlying data.
In this paper, we propose to boost low-resource cross-lingual document retrieval performance with deep bilingual query-document representations. We match queries and documents in both source and target languages with four components, each of which is implemented as a term interaction-based deep neural network with cross-lingual word embeddings as input. By including query likelihood scores as extra features, our model effectively learns to rerank the retrieved documents by using a small number of relevance labels for low-resource language pairs. Due to the shared cross-lingual word embedding s…
ETH Zürich（苏黎世联邦理工学院）；Microsoft Research Asia（微软亚洲研究院）
Machine translation (MT) has almost achieved human parity at sentence-level translation. In response, the MT community has, in part, shifted its focus to document-level translation. However, the development of document-level MT systems is hampered by the lack of parallel document corpora. This paper describes BWB, a large parallel corpus first introduced in Jiang et al. (2022), along with an annotated test set. The BWB corpus consists of Chinese novels translated by experts into English, and the annotated test set is designed to probe the ability of machine translation systems to model various…
Google AI（谷歌人工智能）；Carnegie Mellon University（卡内基梅隆大学）
This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of each other. This is achieved using a novel training method that introduces hard negatives consisting of sentences that are not translations but that have some degree of semantic similarity. The quality of the resulting embeddings are evaluated on parallel corpus reconstruction and by assessing machine translation systems trained on gold vs. mined sentence pa…
Recent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of translating Bilingual Multi-Speaker Conversations, and explore neural architectures which exploit both source and target-side conversation histories for this task. To initiate an evaluation for this task, we introduce datasets extracted from Europarl v7 and OpenSubtitles2016. Our experiments on four language-pairs confirm the significance of leveraging conversation history, both in terms of …
Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, primarily due to the dearth of available data. Existing methods resort to machine translation to synthesize training data, but such pipeline approaches suffer from error propagation. In this work, we propose an end-to-end cross-lingual text summarization model. The model uses reinforcement learning to directly optimize a bilingual semantic similarity metric between the summaries generated in a target language and gold sum…
IBM Research - Tokyo（IBM 东京研究院）；University of Melbourne（墨尔本大学）；National ICT Australia（澳大利亚国家信息通信技术研究院）；International Computer Science Institute（国际计算机科学研究所）
Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive resul…
Google Inc.（谷歌公司）；Université de Montréal（蒙特利尔大学）；Canadian Institute for Advanced Research（加拿大高等研究院）
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-aligned data. This is achieved using a novel sampled bag-of-words cross-lingual objective, which is used to regularize two noise-contrastive language models for efficient cross-lingual feature learning. We …
Tsinghua University（清华大学）；Chinese Academy of Medical Sciences/Peking Union Medical College（中国医学科学院/北京协和医学院）
Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the development of translation systems for highly specialized domains, such as biomedicine. This work presents an unsupervised algorithm for deriving parallel corpora from document-level translations by using sentence alignment and explores how training materials affect the performance of biomedical NMT systems. Materials and Methods: Document-level translations are mixed to train bilin…
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…
Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic difficulty of locating parallel texts in all but the most dominant of the world's languages. A parallel corpus resource not yet explored is the World Wide Web, which hosts an abundance of pages in parallel translation, offering a potential solution to some of these problems and unique opportunities of its own. This paper presents the necessary first step in that exploration: a method for automatically …
UGA（格勒诺布尔阿尔卑斯大学）；GETALP-LIG（格勒诺布尔信息学实验室GETALP团队）；Institute of Advanced Studies (IAS) of the United Nations University（联合国大学高等研究所）
Although classifiers/quantifiers (CQs) expressions appear frequently in everyday communications or written documents, they are described neither in classical bilingual paper dictionaries , nor in machine-readable dictionaries. The paper describes a CQs dictionary, edited from the corpus we have annotated, and its usage in the framework of French-Japanese machine translation (MT). CQs treatment in MT often causes problems of lexical ambiguity, polylexical phrase recognition difficulties in analysis and doubtful output in transfer-generation, in particular for distant languages pairs like French…
We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual word embeddings (BWEs). Unlike prior work on inducing BWEs which heavily relied on parallel sentence-aligned corpora and/or readily available translation resources such as dictionaries, the article reveals that BWEs may be learned solely on the basis of document-aligned comparable data without any additional lexical resources nor syntactic information. We pre…
Monash University（莫纳什大学）；Unbabel；Instituto de Telecomunicações（电信研究所）
Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or w…
Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）
Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation. However, little attention is paid to inaugurate more diverse context for abundant context information. In this paper, we propose a Selective Memory-augmented Neural Document Translation model to deal with documents containing large hypothesis space of the context. Specifically, we retrieve similar bilingual sentence pairs from the training corpus to augment global context and then extend the two-stream attention model with selective me…
Salesforce（赛富时）；University of Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；University of Lorraine（洛林大学）
Probabilistic topic models like Latent Dirichlet Allocation (LDA) have been previously extended to the bilingual setting. A fundamental modeling assumption in several of these extensions is that the input corpora are in the form of document pairs whose constituent documents share a single topic distribution. However, this assumption is strong for comparable corpora that consist of documents thematically similar to an extent only, which are, in turn, the most commonly available or easy to obtain. In this paper we relax this assumption by proposing for the paired documents to have separate, yet …
The algorithm of the creation texts parallel corpora was presented. The algorithm is based on the use of "key words" in text documents, and on the means of their automated translation. Key words were singled out by means of using Russian and Ukrainian morphological dictionaries, as well as dictionaries of the translation of nouns for the Russian and Ukrainianlanguages. Besides, to calculate the weights of the terms in the documents, empiric-statistic rules were used. The algorithm under consideration was realized in the form of a program complex, integrated into the content-monitoring InfoStre…
eBay, Inc.（易趣公司）；RWTH Aachen University（亚琛工业大学）；Human Language Technology and Pattern Recognition GroupRWTH Aachen University（亚琛工业大学人类语言技术与模式识别小组）
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various architectures and analyses, the effectiveness of different context-aware NMT models is not well explored yet. This paper analyzes the performance of document-level NMT models on four diverse domains with a varied amount of parallel document-level bilingual data. We conduct a comprehensive set of experiments to investigate the impact of document-level NMT. We …
Information Retrieval (IR) is an important application area of Natural Language Processing (NLP) where one encounters the genuine challenge of processing large quantities of unrestricted natural language text. While much effort has been made to apply NLP techniques to IR, very few NLP techniques have been evaluated on a document collection larger than several megabytes. Many NLP techniques are simply not efficient enough, and not robust enough, to handle a large amount of text. This paper proposes a new probabilistic model for noun phrase parsing, and reports on the application of such a parsi…
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
University College London（伦敦大学学院）；Nanyang Technological University（南洋理工大学）；University of Waterloo（滑铁卢大学）；NVIDIA（英伟达）；National Institute of Informatics（信息研究院）
IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）；IBM Research-Tokyo（IBM东京研究中心）
Topic models have been successfully applied in lexicon extraction. However, most previous methods are limited to document-aligned data. In this paper, we try to address two challenges of applying topic models to lexicon extraction in non-parallel data: 1) hard to model the word relationship and 2) noisy seed dictionary. To solve these two challenges, we propose two new bilingual topic models to better capture the semantic information of each word while discriminating the multiple translations in a noisy seed dictionary. We extend the scope of topic models by inverting the roles of "word" and "…
University of Western Ontario（西安大略大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Unity Health Toronto（多伦多联合健康中心）
Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms. Currently, the vast number of biomedical articles in the PubMed database are manually annotated by human curators, which is time consuming and costly; therefore, a computational system that can assist the indexing is highly valuable. When developing supervised MeSH indexing systems, the availability of a large-scale annotated text corpus is desirable. A publicly available, large corpus that permits robust evaluation and …
Mouloud Mammeri University of Tizi-Ouzou（穆卢德·马姆里蒂齐乌祖大学）
Traditional information retrieval systems rely on keywords to index documents and queries. In such systems, documents are retrieved based on the number of shared keywords with the query. This lexical-focused retrieval leads to inaccurate and incomplete results when different keywords are used to describe the documents and queries. Semantic-focused retrieval approaches attempt to overcome this problem by relying on concepts rather than on keywords to indexing and retrieval. The goal is to retrieve documents that are semantically relevant to a given user query. This paper addresses this issue by…
University Hospital（大学医院）；OmicX（OmicX公司）；Sorbonne Université（索邦大学）；INSA（法国国立应用科学学院）
PubMed is the biggest and most used bibliographic database worldwide, hosting more than 26M biomedical publications. One of its useful features is the "similar articles" section, allowing the end-user to find scientific articles linked to the consulted document in term of context. The aim of this study is to analyze whether it is possible to replace the statistic model PubMed Related Articles (pmra) with a document embedding method. Doc2Vec algorithm was used to train models allowing to vectorize documents. Six of its parameters were optimised by following a grid-search strategy to train more …
Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial latent space based model capable of generating parallel sentences in two languages concurrently and translating bidirectionally. The bilingual generation goal is achieved by sampling from the latent space that is shared between both languages. First two denoising autoencoders are trained, with shared encoders and back-translation to enforce a shared latent state…
MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries
Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（POSTECH人工智能研究生院）；Department of Computer Science and Engineering, POSTECH, Republic of Korea（POSTECH计算机科学与工程系）；Lilt, Inc.（Lilt公司）
本文提出首个真实且较受偏好的混合语言查询公开基准 MiLQ，评估多语言 IR 模型并揭示其表现不一致，同时验证英语混用可通过增强 token 匹配改善英文文档检索。
University of Western Ontario（西安大略大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Toronto（多伦多大学）；Unity Health Toronto（多伦多联合健康中心）
Currently, Medical Subject Headings (MeSH) are manually assigned to every biomedical article published and subsequently recorded in the PubMed database to facilitate retrieving relevant information. With the rapid growth of the PubMed database, large-scale biomedical document indexing becomes increasingly important. MeSH indexing is a challenging task for machine learning, as it needs to assign multiple labels to each article from an extremely large hierachically organized collection. To address this challenge, we propose KenMeSH, an end-to-end model that combines new text features and a dynam…
St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS)（俄罗斯科学院圣彼得堡信息学与自动化研究所）
In this paper we present a profile-based approach to information filtering by an analysis of the content of text documents. The Wikipedia index database is created and used to automatically generate the user profile from the user document collection. The problem-oriented Wikipedia subcorpora are created (using knowledge extracted from the user profile) for each topic of user interests. The index databases of these subcorpora are applied to filtering information flow (e.g., mails, news). Thus, the analyzed texts are classified into several topics explicitly presented in the user profile. The pa…
We introduce a Content-based Document Alignment approach (CDA), an efficient method to align multilingual web documents based on content in creating parallel training data for machine translation (MT) systems operating at the industrial level. CDA works in two steps: (i) projecting documents of a web domain to a shared multilingual space; then (ii) aligning them based on the similarity of their representations in such space. We leverage lexical translation models to build vector representations using TF-IDF. CDA achieves performance comparable with state-of-the-art systems in the WMT-16 Biling…
One task that is included in managing documents is how to find substantial information inside. Topic modeling is a technique that has been developed to produce document representation in form of keywords. The keywords will be used in the indexing process and document retrieval as needed by users. In this research, we will discuss specifically about Probabilistic Latent Semantic Analysis (PLSA). It will cover PLSA mechanism which involves Expectation Maximization (EM) as the training algorithm, how to conduct testing, and obtain the accuracy result.
Fast and effective automated indexing is critical for search and personalized services. Key phrases that consist of one or more words and represent the main concepts of the document are often used for the purpose of indexing. In this paper, we investigate the use of additional semantic features and pre-processing steps to improve automatic key phrase extraction. These features include the use of signal words and freebase categories. Some of these features lead to significant improvements in the accuracy of the results. We also experimented with 2 forms of document pre-processing that we call l…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe diffe…
Itaú Unibanco（伊塔乌联合银行）；Federal University of Minas Gerais（米纳斯吉拉斯联邦大学）
Keyword extraction has received an increasing attention as an important research topic which can lead to have advancements in diverse applications such as document context categorization, text indexing and document classification. In this paper we propose STF-IDF, a novel semantic method based on TF-IDF, for scoring word importance of informal documents in a corpus. A set of nearly four million documents from health-care social media was collected and was trained in order to draw semantic model and to find the word embeddings. Then, the features of semantic space were utilized to rearrange the…
