Sequence-to-sequence attentional-based neural network architectures have been shown to provide a powerful model for machine translation and speech recognition. Recently, several works have attempted to extend the models for end-to-end speech translation task. However, the usefulness of these models were only investigated on language pairs with similar syntax and word order (e.g., English-French or English-Spanish). In this work, we focus on end-to-end speech translation tasks on syntactically distant language pairs (e.g., English-Japanese) that require distant word reordering.
To guide the encoder-decoder attentional model to learn this difficult problem, we propose a structured-based curriculum learning strategy.
Unlike conventional curriculum learning that gradually emphasizes difficult data examples, we formalize learning strategies from easier network structures to more difficult network structures. Here, we start the training with end-to-end encoder-decoder for speech recognition or text-based machine translation task then gradually move to end-to-end speech translation task. The experiment results show that the proposed approach could provide significant improvements in comparison with the one without curriculum learning.
Stanford University（斯坦福大学）；Rakuten Institute of Technology（乐天技术研究所）；Google Brain（谷歌大脑）
In this paper we describe the Japanese-English Subtitle Corpus (JESC). JESC is a large Japanese-English parallel corpus covering the underrepresented domain of conversational dialogue. It consists of more than 3.2 million examples, making it the largest freely available dataset of its kind. The corpus was assembled by crawling and aligning subtitles found on the web. The assembly process incorporates a number of novel preprocessing elements to ensure high monolingual fluency and accurate bilingual alignments. We summarize its contents and evaluate its quality using human experts and baseline m…
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…
For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often needs discourse context, in some cases, the local context within a sentence gives clues to the inference of the zero pronoun. In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. We show that the proposed method significa…
Indian Institute of Technology, Ropar（印度理工学院罗帕尔分校）；CSIR-Central Scientific Instruments Organisation（CSIR中央科学仪器组织）；Academy of Scientific and Innovative Research（科学与创新研究院）；Tokai Gakuen University（东海学园大学）；Tokyo Institute of Technology（东京工业大学）
Moral psychology is a domain that deals with moral identity, appraisals and emotions. Previous work has primarily focused on moral development and the associated role of culture. Knowing that language is an inherent element of a culture, we used the social media platform Twitter to compare moral behaviors of Japanese tweets with English tweets. The five basic moral foundations, i.e., Care, Fairness, Ingroup, Authority and Purity, along with the associated emotional valence were compared between English and Japanese tweets. The tweets from Japanese users depicted relatively higher Fairness, Ing…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社通信科学实验室）
Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Although there are billions of parallel sentences for a few language pairs, effectively dealing with most language pairs is difficult due to a lack of publicly available parallel corpora. This paper creates a large parallel corpus for English-Japanese, a language pair for which only limited resources are available, compared to such resource-rich languages as English-German. It introduces a new web-based English-Japanese par…
English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
Tokyo Metropolitan University（东京都立大学）
神经机器翻译（NMT）最近在机器翻译领域变得流行。然而，NMT在翻译中存在着重词或漏词的问题。为了解决这个问题，Tu et al.（2017）提出了一种使用反向翻译的NMT编码器-解码器-重建器框架。在这种方法中，他们以与Bahdanau等人（2015）相同的方式选择了最佳的前向翻译模型，然后训练了一个双向翻译模型作为微调。他们的实验表明，它提供了显着提高BLEU分数在汉英翻译任务。我们证实，我们的重新实施也表现出同样的趋势，并重申了问题的重复和遗漏的单词在翻译的英日任务太多。此外，我们通过将其与前向翻译和后向翻译的联合训练模型进行比较来评估预训练的有效性。
Magical Number Seven Plus or Minus Two: Syntactic Structure Recognition in Japanese and English Sentences
George A.米勒说，人类在短期记忆中只有七块，正负两块。我们计算了在日语句子依存结构分析的每一步中，其修饰语不确定的bunsetsus（短语）的数量，因此必须存储在短期记忆中。这个数字大约小于9，也就是7加2的上限。我们也得到了类似的结果与英语句子的假设下，人类认识到一系列的话，如名词短语（NP），作为一个单位。这表明，如果我们假设人类在日语和英语中的认知单位分别是文色和NP，分析将支持米勒的$7 \pm 2$理论。
Graduate School of Informatics, Kyoto University（京都大学信息学研究科）
In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English. JASS focuses on masking and reordering Japanese linguistic units known as bunsetsu, whereas ENSS is proposed based on phrase structure masking and reordering tasks. Experiments on ASPEC Japanese--English & Japanese--Chinese, Wikipedia Japanese--Chinese, News English-…
We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically different languages. We also draw parallels between artificial neural attention and human attention and show that neural attention focuses on word endings as it has been theorised for human attention. Finally, we investigate how two visually grounded monolingual models can be used to perform cross-lingual speech-to-speech retrieval. For both langua…
Graduate School of Information Science and Technology, Osaka University（大阪大学信息科学与技术研究生院）；Institute for Datability Science, Osaka University（大阪大学数据可用性科学研究所）
The word order between source and target languages significantly influences the translation quality in machine translation. Preordering can effectively address this problem. Previous preordering methods require a manual feature design, making language dependent design costly. In this paper, we propose a preordering method with a recursive neural network that learns features from raw inputs. Experiments show that the proposed method achieves comparable gain in translation quality to the state-of-the-art method but without a manual feature design.
Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main methods and data sets focus on SL evaluation. To address the first issue, we present a document-aligned Japanese-English conversation corpus, including balanced, high-quality business conversation data for tuning and testing. As for the second issue, we manually identify the main areas where SL MT fails to produce adequate translations in lack of context. We then …
Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?
Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）；Center for Data Science, New York University（纽约大学数据科学中心）；Facebook AI Research, Facebook Inc.（Facebook 公司人工智能研究院）
University of Georgia（佐治亚大学）；Kyoto University（京都大学）；Osaka University（大阪大学）
Multimodal neural machine translation (NMT) has become an increasingly important area of research over the years because additional modalities, such as image data, can provide more context to textual data. Furthermore, the viability of training multimodal NMT models without a large parallel corpus continues to be investigated due to low availability of parallel sentences with images, particularly for English-Japanese data. However, this void can be filled with comparable sentences that contain bilingual terms and parallel phrases, which are naturally created through media such as social networ…
Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a parallel corpus for English-Japanese, for which the amount of publicly available parallel corpora is still limited. We constructed the parallel corpus by broadly crawling the web and automatically aligning parallel sentences. Our collected corpus, called JParaCrawl, amassed over 8.7 million sentence pairs. We show how it includes a broader range of domains and how a neural machi…
Neural machine translation (NMT) has a drawback in that can generate only high-frequency words owing to the computational costs of the softmax function in the output layer. In Japanese-English NMT, Japanese predicate conjugation causes an increase in vocabulary size. For example, one verb can have as many as 19 surface varieties. In this research, we focus on predicate conjugation for compressing the vocabulary size in Japanese. The vocabulary list is filled with the various forms of verbs. We propose methods using predicate conjugation information without discarding linguistic information. Th…
The purpose of this work is to contribute toward the larger goal of creating a Quantum Natural Language Processing (QNLP) translator program. This work contributes original diagrammatic representations of the Japanese language based on prior work that accomplished on the English language based on category theory. The germane differences between the English and Japanese languages are emphasized to help address English language bias in the current body of research. Additionally, topological principles of these diagrams and many potential avenues for further research are proposed. Why is this end…
The University of Tokyo（东京大学）；Keio University（庆应义塾大学）
Natural Language Inference (NLI) and Semantic Textual Similarity (STS) are widely used benchmark tasks for compositional evaluation of pre-trained language models. Despite growing interest in linguistic universals, most NLI/STS studies have focused almost exclusively on English. In particular, there are no available multilingual NLI/STS datasets in Japanese, which is typologically different from English and can shed light on the currently controversial behavior of language models in matters such as sensitivity to word order and case particles. Against this background, we introduce JSICK, a Jap…
Research & Development Center（研发中心）；LXPER, Inc.（LXPER公司）；University of Pennsylvania（宾夕法尼亚大学）
Automatic readability assessment is one of the most important applications of Natural Language Processing (NLP) in education. Since automatic readability assessment allows the fast selection of appropriate reading material for readers at all levels of proficiency, it can be particularly useful for the English education of English as Foreign Language (EFL) students around the world. Most readability assessment models are developed for the native readers of English and have low accuracy for texts in the non-native English Language Training (ELT) curriculum. We introduce LXPER Index, which is a r…
