Back translation (BT) has been widely used and become one of standard techniques for data augmentation in Neural Machine Translation (NMT), BT has proven to be helpful for improving the performance of translation effectively, especially for low-resource scenarios. While most works related to BT mainly focus on European languages, few of them study languages in other areas around the world. In this paper, we investigate the impacts of BT on Asia language translations between the extremely low-resource Chinese and Vietnamese language pair. We evaluate and compare the effects of different sizes of synthetic data on both NMT and Statistical Machine Translation (SMT) models for Chinese to Vietnamese and Vietnamese to Chinese, with character-based and word-based settings. Some conclusions from previous works are partially confirmed and we also draw some other interesting findings and conclusions, which are beneficial to understand BT further.
Hanoi University of Science and Technology（河内理工大学）；FPT Technology Research Institute, FPT University（FPT大学FPT技术研究院）
Machine translation is shifting to an end-to-end approach based on deep neural networks. The state of the art achieves impressive results for popular language pairs such as English - French or English - Chinese. However for English - Vietnamese the shortage of parallel corpora and expensive hyper-parameter search present practical challenges to neural-based approaches. This paper highlights our efforts on improving English-Vietnamese translations in two directions: (1) Building the largest open Vietnamese - English corpus to date, and (2) Extensive experiments with the latest neural models to …
University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
In this paper, we propose a span labeling approach to model n-gram information for Vietnamese word segmentation, namely SPAN SEG. We compare the span labeling approach with the conditional random field by using encoders with the same architecture. Since Vietnamese and Chinese have similar linguistic phenomena, we evaluated the proposed method on the Vietnamese treebank benchmark dataset and five Chinese benchmark datasets. Through our experimental results, the proposed approach SpanSeg achieves higher performance than the sequence tagging approach with the state-of-the-art F-score of 98.31% on…
Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate …
Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation and part of speech tagging rather than solely process word by word from left to right. In this paper, we implement this idea to improve word segmentation and part of speech tagging the Vietnamese language by employing a simplified constituency parser. Our neural model for joint word segmentation and part-of-speech tagging has the architecture of the syllable-…
Northeastern University（东北大学）；NiuTrans Co., Ltd.（小牛翻译股份有限公司）；Institute of Psychology, CAS（中国科学院心理研究所）
Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation (NMT) systems resort to the attention which partially encodes the interaction for efficiency. In this paper, we employ Joint Representation that fully accounts for each possible interaction. We sidestep the inefficiency issue by refining representations with the proposed efficient attention operation. The resulting Reformer models offer a new Sequence-to- Sequen…
Kata.ai Research Team（Kata.ai研究团队）；Kumamoto University（熊本大学）；University of Edinburgh（爱丁堡大学）；Universitas Indonesia（印度尼西亚大学）；Oracle Digital Assistant（甲骨文数字助手）；Brawijaya University（布拉维贾亚大学）
We release our synthetic parallel paraphrase corpus across 17 languages: Arabic, Catalan, Czech, German, English, Spanish, Estonian, French, Hindi, Indonesian, Italian, Dutch, Romanian, Russian, Swedish, Vietnamese, and Chinese. Our method relies only on monolingual data and a neural machine translation system to generate paraphrases, hence simple to apply. We generate multiple translation samples using beam search and choose the most lexically diverse pair according to their sentence BLEU. We compare our generated corpus with the \texttt{ParaBank2}. According to our evaluation, our synthetic …
The University of Edinburgh participated in the WMT19 Shared Task on News Translation in six language directions: English-to-Gujarati, Gujarati-to-English, English-to-Chinese, Chinese-to-English, German-to-English, and English-to-Czech. For all translation directions, we created or used back-translations of monolingual data in the target language as additional synthetic training data. For English-Gujarati, we also explored semi-supervised MT with cross-lingual language model pre-training, and translation pivoting through Hindi. For translation to and from Chinese, we investigated character-bas…
University of Information Technology（信息科技大学）；Vietnam National University（越南国立大学）
Machine reading comprehension (MRC) is a challenging task in natural language processing that makes computers understanding natural language texts and answer questions based on those texts. There are many techniques for solving this problems, and word representation is a very important technique that impact most to the accuracy of machine reading comprehension problem in the popular languages like English and Chinese. However, few studies on MRC have been conducted in low-resource languages such as Vietnamese. In this paper, we conduct several experiments on neural network-based model to under…
FPT University（FPT大学）；Hanoi University of Science（河内科学大学）
Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accu…
Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining
University of Information Technology, Vietnam National University, Ho Chi Minh city（胡志明市越南国立大学信息技术大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
University of Information Technology（信息大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
Over 97 million people speak Vietnamese as their native language in the world. However, there are few research studies on machine reading comprehension (MRC) for Vietnamese, the task of understanding a text and answering questions related to it. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. This dataset comprises over 23,000 human-generated question-answer pairs based on 5,109 passages of 174 Vietnamese articles from Wikipedia. In particul…
University of Information Technology（信息技术大学）；Vietnam National University（越南国家大学）
As biological gender is one of the aspects of presenting individual human, much work has been done on gender classification based on people names. The proposals for English and Chinese languages are tremendous; still, there have been few works done for Vietnamese so far. We propose a new dataset for gender prediction based on Vietnamese names. This dataset comprises over 26,000 full names annotated with genders. This dataset is available on our website for research purposes. In addition, this paper describes six machine learning algorithms (Support Vector Machine, Multinomial Naive Bayes, Bern…
Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel corpora exist. As described in this paper, we propose a corpus augmentation method by segmenting long sentences in a corpus using back-translation and generating pseudo-parallel sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with Japanese-Chinese scientific paper excerpt corpus (ASPEC-JC) show that the method…
Most of the Neural Machine Translation (NMT) models are based on the sequence-to-sequence (Seq2Seq) model with an encoder-decoder framework equipped with the attention mechanism. However, the conventional attention mechanism treats the decoding at each time step equally with the same matrix, which is problematic since the softness of the attention for different types of words (e.g. content words and function words) should differ. Therefore, we propose a new model with a mechanism called Self-Adaptive Control of Temperature (SACT) to control the softness of attention by means of an attention te…
Conversion of Chinese Grapheme-to-Phoneme (G2P) plays an important role in Mandarin Chinese Text-To-Speech (TTS) systems, where one of the biggest challenges is the task of polyphone disambiguation. Most of the previous polyphone disambiguation models are trained on manually annotated datasets, and publicly available datasets for polyphone disambiguation are scarce. In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data. Inspired by the back-translation technique proposed i…
Attention-based sequence-to-sequence model has proved successful in Neural Machine Translation (NMT). However, the attention without consideration of decoding history, which includes the past information in the decoder and the attention mechanism, often causes much repetition. To address this problem, we propose the decoding-history-based Adaptive Control of Attention (ACA) for the NMT model. ACA learns to control the attention by keeping track of the decoding history and the current information with a memory vector, so that the model can take the translated contents and the current informatio…
University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
Question answering (QA) is a natural language understanding task within the fields of information retrieval and information extraction that has attracted much attention from the computational linguistics and artificial intelligence research community in recent years because of the strong development of machine reading comprehension-based models. A reader-based QA system is a high-level search engine that can find correct answers to queries or questions in open-domain or domain-specific texts using machine reading comprehension (MRC) techniques. The majority of advancements in data resources an…
ESTATES PTE LTD（六境私人有限公司）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Beijing Advanced Innovation Center for Language Resources（北京语言资源高精尖创新中心）
While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translati…
CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Amazon（亚马逊）；Salesforce Research（Salesforce 研究院）；Harrisburg University of Science and Technology（哈里斯堡科技大学）
Ahmadu Bello University（艾哈迈德·贝罗大学）；Bayero University（拜罗大学）
Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the backward system - which is trained on the available parallel data and used for the back-translation - has been shown in many studies to affect the performance of the final NMT model. In low resource conditions, the available parallel data is usually not enough to train a backward model that can produce the qualitative synthetic data needed to train a standar…
This paper describes DiDi AI Labs' submission to the WMT2020 news translation shared task. We participate in the translation direction of Chinese->English. In this direction, we use the Transformer as our baseline model, and integrate several techniques for model enhancement, including data filtering, data selection, back-translation, fine-tuning, model ensembling, and re-ranking. As a result, our submission achieves a BLEU score of $36.6$ in Chinese->English.
Facebook AI Research（脸书人工智能研究院）；University College London（伦敦大学学院）
Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English, making training QA systems in other languages challenging. An alternative to building large monolingual training datasets is to develop cross-lingual systems which can transfer to a target language without requiring training data in that language. In order to develop such systems, it is crucial to invest in high quality multilingual evaluation benchmarks to m…
Ahmadu Bello University（艾哈迈杜·贝罗大学）；Bayero University（巴耶罗大学）
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation method has been shown to be unable to efficiently utilize the available huge amount of existing monolingual data because of the inability of translation models to differentiate between the authentic and synthetic parallel data during training. Tagging, or using gates, has been used to enable translation models to distinguish between synthetic and authentic data, …
This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) with several novel and effective variants. In our experiments, we employ data filtering, large-scale synthetic data generation (i.e., back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge transfer), advanced finetuning approaches, and boosted Self-BLEU based model ensemble. Our constrained systems achieve 36.9, 46.9, 27.8 and 3…
Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study
Faculty of Information Technology, Monash University（信息技术学院，莫纳什大学）；Faculty of Medicine, Nursing and Health Sciences, Monash University（医学、护理与健康科学学院，莫纳什大学）；Supportive and Palliative Care Unit, Monash Health（支持与姑息护理单元，莫纳什健康）
VLSP 2023 -- LTER: A Summary of the Challenge on Legal Textual Entailment Recognition
Vietnam Judicial Academy（越南司法学院）；Hanoi Law University（河内法律大学）；Hung Yen University of Technology and Education（兴安工业大学）；Ho Chi Minh City University of Science（胡志明市科学大学）；Japan Advanced Institute of Science and Technology（日本先进科学技术学院）；The Institute of Statistical Mathematics（统计数学研究所）；National Institute of Informatics（情报学研究所）
We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.
Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant problem due to the absence of a standard dataset and evaluation policy. To address this problem, we proposed ViWOZ, a fully-annotated Vietnamese task-oriented dialogue dataset. ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language. The dataset consists of a total of 5,000 dialogues, including 60,946 fully an…
VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
Faculty of Information Technology, Nha Trang University（信息科技学院，纳享大学）；Faculty of Business Administration, Swiss School of Business and Management Geneva（商业管理学院，瑞士商业与管理学校日内瓦）
MultiMed-ST: Large-scale Many-to-many Multilingual Medical Speech Translation
University of Toronto（多伦多大学）；University Health Network（大学健康网络）；Knovel Engineering Lab（Knovel 工程实验室）；Hanoi University of Science and Technology（河内科技大学）；KU Leuven（鲁汶大学）；Eötvös Loránd University（罗兰大学）；HCMC Open University（胡志明市开放大学）；IÉSEG School of Management（IÉSEG 管理学院）；Technische Universität Dortmund（多特蒙德工业大学）；University of Hertfordshire（赫特福德大学）；UC Berkeley（加州大学伯克利分校）；New Jersey Institute of Technology（新泽西理工学院）
BERT-based model for Vietnamese Fact Verification Dataset
Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT)（胡志明市技术大学计算机科学与工程学院）；Vietnam National University Ho Chi Minh City（越南国家大学胡志明市分校）
Transliteration is a task of translating named entities from a language to another, based on phonetic similarity. The task has embraced deep learning approaches in recent years, yet, most ignore the phonetic features of the involved languages. In this work, we incorporate phonetic information into neural networks in two ways: we synthesize extra data using forward and back-translation but in a phonetic manner; and we pre-train models on a phonetic task before learning transliteration. Our experiments include three language pairs and six directions, namely English to and from Chinese, Hebrew an…
SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation
East China Normal University（华东师范大学）；New York University Shanghai（上海纽约大学）；University of Liverpool（利物浦大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Eastern Institute of Technology (Ningbo)（宁波东方理工大学）
Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination
NLP2 CT Lab, Department of Computer and Information Science, University of Macau（澳门大学自然语言处理与计算机实验室，计算机与信息科学系）；Institute of International Language Services Studies, Macau Millennium College（澳门 millennium 学院国际语言服务研究学院）
Cross-Cultural Transfer Learning for Chinese Offensive Language Detection
University of Electronic Science and Technology of China（电子科技大学）；University of Copenhagen（哥本哈根大学）；Huazhong University of Science and Technology（华中科技大学）
PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain
East China Normal University（华东师范大学）；Alibaba Group（阿里巴巴集团）；Holoflow Digital Technology（全息数字技术（杭州）有限公司）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
University of Waterloo（滑铁卢大学）；Penn State University（宾夕法尼亚州立大学）
In-context learning using large language models has recently shown surprising results for semantic parsing tasks such as Text-to-SQL translation. Prompting GPT-3 or Codex using several examples of question-SQL pairs can produce excellent results, comparable to state-of-the-art finetuning-based models. However, existing work primarily focuses on English datasets, and it is unknown whether large language models can serve as competitive semantic parsers for other languages. To bridge this gap, our work focuses on cross-lingual Text-to-SQL semantic parsing for translating non-English utterances in…
