Recent studies have demonstrated a perceivable improvement on the performance of neural machine translation by applying cross-lingual language model pretraining (Lample and Conneau, 2019), especially the Translation Language Modeling (TLM). To alleviate the need for expensive parallel corpora by TLM, in this work, we incorporate the translation information from dictionaries into the pretraining process and propose a novel Bilingual Dictionary-based Language Model (BDLM). We evaluate our BDLM in Chinese, English, and Romanian. For Chinese-English, we obtained a 55.0 BLEU on WMT-News19 (Tiedemann, 2012) and a 24.3 BLEU on WMT20 news-commentary, outperforming the Vanilla Transformer (Vaswani et al., 2017) by more than 8.4 BLEU and 2.3 BLEU, respectively. According to our results, the BDLM also has advantages on convergence speed and predicting rare words. The increase in BLEU for WMT16 Romanian-English also shows its effectiveness in low-resources language translation.
University of Copenhagen（哥本哈根大学）；National University of Ireland, Galway（爱尔兰国立大学戈尔韦分校）；Aylien Ltd.（艾利恩有限公司）；University of Cambridge（剑桥大学）
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised alignment of word embedding spaces for bilingual dictionary induction (Conneau et al., 2018), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologicall…
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. Motivated by the ability of a monolingual speaker learning to translate via looking up the bilingual dictionary, we propose the task to see how much potential an MT system can attain using the bilingual dictionary and large scale monolingual corpora, while is independent on parallel sentences. We propose anchored training (AT) to tackle the task. AT uses the bilingual dictionary to establish anchoring points for closing the gap between …
University of California, Los Angeles（加州大学洛杉矶分校）；The State University of New York, Stony Brook（纽约州立大学石溪分校）
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited from the cross-lingual correspondence between sentences and lexicons. To bridge this gap, we propose a neural embedding model that leverages bilingual dictionaries. The proposed model is trained to map the literal word definitions to the cross-lingual target words, for which we explore with different sentence encoding techniques. To enhance the learning proc…
Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated into NMT. In this paper, we describe a new method for "attaching" dictionary definitions to rare words so that the network can learn the best way to use them. We demonstrate improvements of up to 1.8 BLEU using bilingual dictionaries.
Tokyo Institute of Technology（东京工业大学）；AIST（日本产业技术综合研究所）；Asurion Japan Holdings G.K.（Asurion日本控股合同会社）；The University of Tokyo（东京大学）；RIKEN AIP（日本理化学研究所智能信息学中心）；AIRC, AIST（日本产业技术综合研究所人工智能研究中心）
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can be infeasible because of the labeling cost, task characteristics, and privacy concerns. This paper proposes an alternative solution that uses only task-independent word embeddings of high-resource languages and bilingual dictionaries. First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibi…
University of Chinese Academy of Sciences（中国科学院大学）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in the bilingual training data. In this paper, we propose two methods to bridge NMT and the bilingual dictionaries. The core idea behind is to design novel models that transform the bilingual dictionaries into adequate sentence pairs, so that NMT can distil latent bilingual mappings from the ample and repetitive phenomena. One method leverages a mixed word/chara…
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…
In recent studies, it has been shown that Multilingual language models underperform their monolingual counterparts. It is also a well-known fact that training and maintaining monolingual models for each language is a costly and time-consuming process. Roman Urdu is a resource-starved language used popularly on social media platforms and chat apps. In this research, we propose a novel dataset of scraped tweets containing 54M tokens and 3M sentences. Additionally, we also propose RUBERT a bilingual Roman Urdu model created by additional pretraining of English BERT. We compare its performance wit…
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…
Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified representation for both speech and text is needed by tasks such as end-to-end speech translation, and as a result,(b) they can not exploit various large-scale text and speech data and their performance is limited by the scarcity of parallel speech translation data.To address these problems, we propose a Fused Acoustic and Text Masked Language Model (FAT-MLM) which join…
We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, and (b) learning a similarity metric in the common space to model similarities between the embeddings. We model the bilingual mapping problem as an optimization problem on smooth Riemannian manifolds. We show that our approach outperforms previous approaches on the bilingual lexi…
Recent approaches to cross-lingual word embedding have generally been based on linear transformations between the sets of embedding vectors in the two languages. In this paper, we propose an approach that instead expresses the two monolingual embedding spaces as probability densities defined by a Gaussian mixture model, and matches the two densities using a method called normalizing flow. The method requires no explicit supervision, and can be learned with only a seed dictionary of words that have identical strings. We argue that this formulation has several intuitively attractive properties, …
University of Maryland（马里兰大学）；University of Colorado（科罗拉多大学）；Google Research Zürich（谷歌苏黎世研究中心）
Cross-lingual word embeddings (CLWE) are often evaluated on bilingual lexicon induction (BLI). Recent CLWE methods use linear projections, which underfit the training dictionary, to generalize on BLI. However, underfitting can hinder generalization to other downstream tasks that rely on words from the training dictionary. We address this limitation by retrofitting CLWE to the training dictionary, which pulls training translation pairs closer in the embedding space and overfits the training dictionary. This simple post-processing step often improves accuracy on two downstream tasks, despite low…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical- and high-level representations of the two languages. While cross-lingual pretraining works for similar languages with abundant corpora, it performs poorly in low-resource and distant languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language m…
Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages. They are a crucial component for scaling tasks to multiple languages by transferring knowledge from languages with rich resources to low-resource languages. A common approach to learning cross-lingual embeddings is to train monolingual embeddings separately for each language and learn a linear projection from the monolingual spaces into a shared space, where the mapping relies on a small seed dictionary. While there are high-quality generic seed di…
Due to widespread interest in machine translation and transfer learning, there are numerous algorithms for mapping multiple embeddings to a shared representation space. Recently, these algorithms have been studied in the setting of bilingual dictionary induction where one seeks to align the embeddings of a source and a target language such that translated word pairs lie close to one another in a common representation space. In this paper, we propose a method, Filtered Inner Product Projection (FIPP), for mapping embeddings to a common representation space and evaluate FIPP in the context of bi…
TALP Research Center（TALP研究中心）；Univesitat Politècnica de Catalunya（加泰罗尼亚理工大学）
Out-of-vocabulary words account for a large proportion of errors in machine translation systems, especially when the system is used on a different domain than the one where it was trained. In order to alleviate the problem, we propose to use a log-bilinear softmax-based model for vocabulary expansion, such that given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language. Our model uses only word embeddings trained on significantly large unlabelled monolingual corpora and trains over a fairly small, word-to-word bilingual dict…
We present a method for learning bilingual translation dictionaries between English and Bantu languages. We show that exploiting the grammatical structure common to Bantu languages enables bilingual dictionary induction for languages where training data is unavailable.
China University of Petroleum (East China)（中国石油大学（华东））；JD Explore Academy（京东探索研究院）
For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e.g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e.g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e.g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages. To bridge the above cross-lingual domain and task gaps, we exten…
Why Pretraining Fails to Share Cross-Lingual Knowledge
Weizmann Institute of Science（魏茨曼科学研究所）；Bar-Ilan University（巴伊兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；A*STAR（新加坡科技研究局）；University of Washington（华盛顿大学）；MIT（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
School of Computer Sciences, NISER（国家科学教育与研究学院计算机科学学院）；Homi Bhabha National Institute（霍米·巴巴国家研究所）
Neural Machine Translation (NMT) models have been effective on large bilingual datasets. However, the existing methods and techniques show that the model's performance is highly dependent on the number of examples in training data. For many languages, having such an amount of corpora is a far-fetched dream. Taking inspiration from monolingual speakers exploring new languages using bilingual dictionaries, we investigate the applicability of bilingual dictionaries for languages with extremely low, or no bilingual corpus. In this paper, we explore methods using bilingual dictionaries with an NMT …
Out of vocabulary (OOV) is a problem in the context of Machine Translation (MT) in low-resourced languages. When source and/or target languages are morphologically rich, it becomes even worse. Bilingual list integration is an approach to address the OOV problem. This allows more words to be translated than are in the training data. However, since bilingual lists contain words in the base form, it will not translate inflected forms for morphologically rich languages such as Sinhala and Tamil. This paper focuses on data augmentation techniques where bilingual lexicon terms are expanded based on …
When using a third language to construct a bilingual dictionary, it is necessary to discriminate equivalencies from inappropriate words derived as a result of ambiguity in the third language. We propose a method to treat this by utilizing the structures of dictionaries to measure the nearness of the meanings of words. The resulting dictionary is a word-to-word bilingual dictionary of nouns and can be used to refine the entries and equivalencies in published bilingual dictionaries.
In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude. Unprecedented challenges emerge in this situation compared to previous NMT work, including severe noise in the data and prohibitively long training time. We propose practical solutions to handle these issues and demonstrate that large-scale pretraining significantly improves NMT performance. We are able to push the BLEU score of WMT17 Chinese-English dataset to 32.…
The University of Tokyo（东京大学）；Facebook AI Research（脸书人工智能研究院）
Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora, and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present PARADISE (PARAllel & Denoising Integration in SEquence-to-sequence models), which extends the conventional denoising objective used to train these models by (i) replacing words in the noised sequence according to a multilingual dictionary, and (ii) predicting the reference translation according to a parallel corpus instead of recovering the original sequence. Our e…
A probabilistic model for computer-based generation of a machine translation system on the basis of English-Russian parallel text corpora is suggested. The model is trained using parallel text corpora with pre-aligned source and target sentences. The training of the model results in a bilingual dictionary of words and "word blocks" with relevant translation probability.
HiTZ Center, University of the Basque Country (UPV/EHU)（巴斯克大学 HiTZ 中心）；Facebook AI Research（Facebook 人工智能研究院）
Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing t…
University of Colorado, Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
Past approaches to translate a phrase in a language L1 to a language L2 using a dictionary-based approach require grammar rules to restructure initial translations. This paper introduces a novel method without using any grammar rules to translate a given phrase in L1, which does not exist in the dictionary, to L2. We require at least one L1-L2 bilingual dictionary and n-gram data in L2. The average manual evaluation score of our translations is 4.29/5.00, which implies very high quality.
University of Copenhagen（哥本哈根大学）；Insight Research Centre, National University of Ireland, Galway（爱尔兰国立大学戈尔韦分校洞察研究中心）；Aylien Ltd.（Aylien有限公司）；University of Cambridge（剑桥大学）
Most recent approaches to bilingual dictionary induction find a linear alignment between the word vector spaces of two languages. We show that projecting the two languages onto a third, latent space, rather than directly onto each other, while equivalent in terms of expressivity, makes it easier to learn approximate alignments. Our modified approach also allows for supporting languages to be included in the alignment process, to obtain an even better performance in low resource settings.
Bilingual machine-readable dictionaries are knowledge resources useful in many automatic tasks. However, compared to monolingual computational lexicons like WordNet, bilingual dictionaries typically provide a lower amount of structured information, such as lexical and semantic relations, and often do not cover the entire range of possible translations for a word of interest. In this paper we present Cycles and Quasi-Cycles (CQC), a novel algorithm for the automated disambiguation of ambiguous translations in the lexical entries of a bilingual machine-readable dictionary. The dictionary is repr…
CITIC Grupo LYS（CITIC LYS团队）；Grupo COLE（COLE团队）；Universidade de Vigo（维戈大学）
There has been an increasing interest in learning cross-lingual word embeddings to transfer knowledge obtained from a resource-rich language, such as English, to lower-resource languages for which annotated data is scarce, such as Turkish, Russian, and many others. In this paper, we present the first viability study of established techniques to align monolingual embedding spaces for Turkish, Uzbek, Azeri, Kazakh and Kyrgyz, members of the Turkic family which is heavily affected by the low-resource constraint. Those techniques are known to require little explicit supervision, mainly in the form…
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT training benefit, however, is often limited to many-to-one directions. The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strateg…
Kyoto University（京都大学）；Universitas Islam Riau（伊斯兰廖内大学）
The lack or absence of parallel and comparable corpora makes bilingual lexicon extraction a difficult task for low-resource languages. The pivot language and cognate recognition approaches have been proven useful for inducing bilingual lexicons for such languages. We propose constraint-based bilingual lexicon induction for closely-related languages by extending constraints from the recent pivot-based induction technique and further enabling multiple symmetry assumption cycles to reach many more cognates in the transgraph. We further identify cognate synonyms to obtain many-to-many translation …
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However, parallel data is not readily available for many languages, limiting the applicability of these approaches. We address these drawbacks in our framework which takes advantage of cross-lingual word embeddings trained solely on a high coverage bilingual dictionary. We propose a novel neural network model for joint training from both sources of data based on cross-li…
As patients' access to their doctors' clinical notes becomes common, translating professional, clinical jargon to layperson-understandable language is essential to improve patient-clinician communication. Such translation yields better clinical outcomes by enhancing patients' understanding of their own health conditions, and thus improving patients' involvement in their own care. Existing research has used dictionary-based word replacement or definition insertion to approach the need. However, these methods are limited by expert curation, which is hard to scale and has trouble generalizing to …
Unsupervised Bilingual Dictionary Induction methods based on the initialization and the self-learning have achieved great success in similar language pairs, e.g., English-Spanish. But they still fail and have an accuracy of 0% in many distant language pairs, e.g., English-Japanese. In this work, we show that this failure results from the gap between the actual initialization performance and the minimum initialization performance for the self-learning to succeed. We propose Iterative Dimension Reduction to bridge this gap. Our experiments show that this simple method does not hamper the perform…
This paper proposes approaches to automatically create a large number of new bilingual dictionaries for low-resource languages, especially resource-poor and endangered languages, from a single input bilingual dictionary. Our algorithms produce translations of words in a source language to plentiful target languages using available Wordnets and a machine translator (MT). Since our approaches rely on just one input dictionary, available Wordnets and an MT, they are applicable to any bilingual dictionary as long as one of the two languages is English or has a Wordnet linked to the Princeton Wordn…
Transformer based language models have led to impressive results across all domains in Natural Language Processing. Pretraining these models on language modeling tasks and finetuning them on downstream tasks such as Text Classification, Question Answering and Neural Machine Translation has consistently shown exemplary results. In this work, we propose a Multitask Finetuning methodology which combines the Bilingual Machine Translation task with an auxiliary Causal Language Modeling task to improve performance on the former task on Indian Languages. We conduct an empirical study on three languag…
LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation
Zhejiang University（浙江大学）；School of Engineering, Westlake University（西湖大学工程学院）；Pattern Recognition Center, WeChat AI, Tencent Inc（腾讯公司微信AI模式识别中心）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究所）
Typically, a linearly orthogonal transformation mapping is learned by aligning static type-level embeddings to build a shared semantic space. In view of the analysis that contextual embeddings contain richer semantic features, we investigate a context-aware and dictionary-free mapping approach by leveraging parallel corpora. We illustrate that our contextual embedding space mapping significantly outperforms previous multilingual word embedding methods on the bilingual dictionary induction (BDI) task by providing a higher degree of isomorphism. To improve the quality of mapping, we also explore…
Bilingual dictionaries are expensive resources and not many are available when one of the languages is resource-poor. In this paper, we propose algorithms for creation of new reverse bilingual dictionaries from existing bilingual dictionaries in which English is one of the two languages. Our algorithms exploit the similarity between word-concept pairs using the English Wordnet to produce reverse dictionary entries. Since our algorithms rely on available bilingual dictionaries, they are applicable to any bilingual dictionary as long as one of the two languages has Wordnet type lexical ontology.
This paper explores the acquisition of conceptual knowledge from bilingual dictionaries (French/English, Spanish/English and English/Spanish) using a pre-existing broad coverage Lexical Knowledge Base (LKB) WordNet. Bilingual nominal entries are disambiguated agains WordNet, therefore linking the bilingual dictionaries to WordNet yielding a multilingual LKB (MLKB). The resulting MLKB has the same structure as WordNet, but some nodes are attached additionally to disambiguated vocabulary of other languages. Two different, complementary approaches are explored. In one of the approaches each entry…
University of California Santa Barbara（加州大学圣巴巴拉分校）；Tencent AI Lab（腾讯人工智能实验室）；The Ohio State University（俄亥俄州立大学）
Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges---it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework.…
Translation ambiguity, out of vocabulary words and missing some translations in bilingual dictionaries make dictionary-based Cross-language Information Retrieval (CLIR) a challenging task. Moreover, in agglutinative languages which do not have reliable stemmers, missing various lexical formations in bilingual dictionaries degrades CLIR performance. This paper aims to introduce a probabilistic translation model to solve the ambiguity problem, and also to provide most likely formations of a dictionary candidate. We propose Minimum Edit Support Candidates (MESC) method that exploits a monolingual…
Institute for Advanced Studies in Basic Sciences（基础科学高等研究院）；Charles University（查理大学）；Shiraz University（设拉子大学）；University of Calabria（卡拉布里亚大学）
Bilingual dictionaries are very important in various fields of natural language processing. In recent years, research on extracting new bilingual lexicons from non-parallel (comparable) corpora have been proposed. Almost all use a small existing dictionary or other resources to make an initial list called the "seed dictionary". In this paper, we discuss the use of different types of dictionaries as the initial starting list for creating a bilingual Persian-Italian lexicon from a comparable corpus. Our experiments apply state-of-the-art techniques on three different seed dictionaries; an existi…
The University of Sydney（悉尼大学）；Peking University（北京大学）；JD Explore Academy, JD.com（京东探索学院，京东集团（注：根据机构含义，JD.com 是京东集团，此处按要求提取到公司级别，学院名称保留英文））
We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from "src$\rightarrow$tgt" to "src+tgt$\rightarrow$tgt+src" without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translat…
The task of bilingual dictionary induction (BDI) is commonly used for intrinsic evaluation of cross-lingual word embeddings. The largest dataset for BDI was generated automatically, so its quality is dubious. We study the composition and quality of the test sets for five diverse languages from this dataset, with concerning findings: (1) a quarter of the data consists of proper nouns, which can be hardly indicative of BDI performance, and (2) there are pervasive gaps in the gold-standard targets. These issues appear to affect the ranking between cross-lingual embedding systems on individual lan…
Facebook AI Research（脸书人工智能研究院）；LIUM, University of Le Mans（勒芒大学语言与信息科学实验室）；Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6（索邦大学、巴黎第六大学、法国国家科学研究中心与巴黎第六大学联合实验室7606、巴黎第六大学计算机科学实验室）
State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised w…
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods. Recent findings have shown that the accuracy and robustness of unsupervised word translation (UWT) can be improved by making use of visual observations, which are universal representations across languages. In this work, we investigate the potential of using not only visual observations but also pretrained language-image models for enabling a more efficient and robust UWT. Specifically, we develop a novel UWT method dubbed Word Alignment using Language-Image Pretraining (WALIP), which…
The University of Sydney（悉尼大学）；Beihang University（北京航空航天大学）；JD Explore Academy, JD.com（京东探索研究院）
We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. Specifically, we update the model parameters with source- and target-side denoising tasks at the early stage and then tune the model normally. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experiments show that DoT consistently improves the neural machine translation performance across 12 bilingual and 16 multilingual directions (data size ranges from 80K to 20M). In addition, we show that DoT can complement existing…
Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector spaces to align them such that similar words are mapped to each other. We show empirically that the per…
