Proceedings of the 6th Workshop on Asian Translation
Overview of the 6th Workshop on Asian Translation (D19-52)
Copied to clipboard
Toshiaki Nakazawa, Nobushige Doi, Shohei Higashiyama, Chenchen Ding, Raj Dabre, Hideya Mino, Isao Goto, Win Pa Pa, Anoop Kunchukuttan, Yusuke Oda, Shantipriya Parida, Ondřej Bojar, Sadao Kurohashi
| Challenge: | The 6th workshop on Asian translation (WAT2019) was held in hong kong, hongkong, and hong kong. |
| Approach: | They present the results of the shared tasks from the 6th workshop on Asian translation (WAT2019) 25 teams participated in the shared task and 10 research paper submissions were accepted . |
| Outcome: | The results of the 6th workshop on Asian translation (WAT2019) include JaEn, JaZh scientific paper translation subtasks, Ja'En, ja'Ko, Ja’En patent translation sub tasks, Hi'En and My'En patent subtask and Ru'Ja news commentary translation task. |
Compact and Robust Models for Japanese-English Character-level Machine Translation (D19-52)
Copied to clipboard
| Challenge: | In recent years, neural machine translation (NMT) has made a great progress, and its translation quality has far surpassed the conventional statistical machine translation. |
| Approach: | They propose a character-level translation model which is mid-gated and multi-attention model for Japanese-English translation and propose to train them using a relatively narrow beam of width 4 or 5 . |
| Outcome: | The proposed models can translate the word containing Katakana by coining out a close word, and the model can produce tolerable results for noised sentences. |
Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation (D19-52)
Copied to clipboard
| Challenge: | In the Japanese language different levels of honorific speech are used to convey respect, deference, humility, formality and social distance. |
| Approach: | They propose a method for controlling the level of formality of Japanese output . they use heuristics to identify honorific verb forms to classify Japanese sentences . |
| Outcome: | The proposed model can produce Japanese translations in different honorific speech styles for the same English input sentence. |
Designing the Business Conversation Corpus (D19-52)
Copied to clipboard
| Challenge: | Existing parallel corpora for machine translation of written text and monologues are limited. |
| Approach: | They propose to introduce a Japanese-English business conversation parallel corpus into machine translation training scenarios and show how it improves machine translation quality. |
| Outcome: | The proposed corpus is used in a Japanese-English business conversation training scenario and shows how it performs. |
English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning (D19-52)
Copied to clipboard
| Challenge: | Multi-modal translation is an emerging task of the MT community, where visual features of image combine with textual features of parallel source-target text to translate sentences. |
| Approach: | They propose to use convolutional neural net-works and visual geometry to extract image features and attention-based Neural MachineTranslation (NMT) system for translation. |
| Outcome: | The proposed multi-modal translation system improves translation quality and improves the quality of the captions of the images. |
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English (D19-52)
Copied to clipboard
Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita
| Challenge: | Using cleaned and normalized noisy monolingual data, supervised neural and statistical machine translation systems performed among the best for the four translation directions. |
| Approach: | They present supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks. |
| Outcome: | The proposed systems performed among the best for the four translation directions. |
NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT (D19-52)
Copied to clipboard
| Challenge: | In this paper, we describe our submissions for the following tasks: English–Tamil translation and Russian–Japanese translation. |
| Approach: | They propose to use multilingual domain adaptation and back-translation to improve translations in Russian–Japanese and English–Tamil. |
| Outcome: | The proposed techniques perform better in Russian–Japanese and English–Tamil translation tasks. |
KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019 (D19-52)
Copied to clipboard
Cheoneum Park, Young-Jun Jung, Kihoon Kim, Geonyeong Kim, Jae-Won Jeon, Seongmin Lee, Junseok Kim, Changki Lee
| Challenge: | We submitted our transformer-based neural machine translation system to the translation tasks of the 6th workshop on Asian Translation (WAT 2019). |
| Approach: | They propose a transformer-based neural machine translation system for Chinese-Japanese, English-Japanese, and Korean->Japanoise translation tasks. |
| Outcome: | The proposed system performed well on the two translation tasks and was ranked first in terms of the BLEU scores in all the JPC2 subtasks. |
English-Myanmar Supervised and Unsupervised NMT: NICT’s Machine Translation Systems at WAT-2019 (D19-52)
Copied to clipboard
| Challenge: | NICT participated in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (My) - English task in both translation directions. |
| Approach: | They present the participation of the NICT in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (Burmese) - English task in both translation directions. |
| Outcome: | The proposed systems perform the third in English-to-Myanmar and the second in Myanmar-to English according to BLEU score. |
UCSMNLP: Statistical Machine Translation for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | UCSMNLP submitted to WAT 2019 Translation Tasks focusing on Myanmar-English translation. |
| Approach: | They propose to use Name Entity Recognition corpus and bilingual dictionary to build phrase based statistical machine translation system using listwise reranking process and initial distortion weight is changed to improve translation quality. |
| Outcome: | The proposed system outperforms the baseline system in the Myanmar-English translation task. |
NTT Neural Machine Translation Systems at WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | We submitted two systems for scientific paper subtask and timely disclosure subtask . we evaluated the usefulness of incorporating external data from a wide variety of web pages to improve the translation quality. |
| Approach: | They describe two different translation tasks submitted to WAT 2019 . they submitted scientific paper subtasks and timely disclosure subtask . |
| Outcome: | The proposed system performed better on scientific paper and timely disclosure subtasks. |
Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | In addition to the JIJI Corpus, we developed a corpus of 0.22M sentence pairs by manually, translating Japanese news sentences into English content- equivalently. |
| Approach: | They propose to use JIJI Corpus and Equivalent-style sentences to translate Japanese news sentences into English content- equivalently. |
| Outcome: | The proposed translation models achieved the best human evaluation scores in the newswire translation tasks at WAT 2019 . they used the JIJI Corpus, which was provided by the task organizer, and the Equivalent-style translation model to translate Japanese news sentences into English content- equivalently. |
Facebook AI’s WAT19 Myanmar-English Translation Task Submission (D19-52)
Copied to clipboard
Peng-Jen Chen, Jiajun Shen, Matthew Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc’Aurelio Ranzato
| Challenge: | Using back-translation, we can improve generalization by using noisy channel re-ranking and ensembling. |
| Approach: | They propose to use BPE-based transformer models to leverage monolingual data to improve generalization and use noisy channel re-ranking and ensembling to improve results. |
| Outcome: | The proposed system improves on the baseline system trained exclusively on the provided small parallel dataset, and the human evaluation and BLEU score are higher. |
Combining Translation Memory with Neural Machine Translation (D19-52)
Copied to clipboard
| Challenge: | Existing systems that combine translation memory and statistical machine translation (MT) models are able to translate less familiar phrases and sentences without sacrificing quality. |
| Approach: | They propose to combine translation memory and Neural Machine Translation (NMT) models to select final translation outputs when similarity score of a test source sentence exceeds the predefined threshold. |
| Outcome: | The proposed system significantly improves translation performance on the Timely Disclosure corpus, as compared to a standalone NMT system. |
CVIT’s submissions to WAT-2019 (D19-52)
Copied to clipboard
| Challenge: | In this paper, we explore multiway-models for Indian languages. |
| Approach: | They propose to use a Transformer architecture to experiment with multilingual models and methods for low-resource languages. |
| Outcome: | The proposed system is feasible in low-resource languages. |
LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) is a promising approach for low resource languages. |
| Approach: | They propose to use both Recurrent Neural Networks & Transformer architectures to train NMT models. |
| Outcome: | The proposed model outperforms Statistical Machine Translation (SMT) techniques on a low resource Hindi-English language pair. |
Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019 (D19-52)
Copied to clipboard
| Challenge: | NICT-2 neural machine translation system was presented at the 6th Workshop on Asian Translation (WAT-2019) |
| Approach: | They describe a NICT-2 neural machine translation system at the 6th Workshop on Asian Translation . they employ a long warm-up strategy and a self-training strategy that uses multiple back-translations generated by sampling to improve the translation quality. |
| Outcome: | The proposed system improves translation quality and learning rate by using the long warm-up and self-training strategies. |
Supervised neural machine translation based on data augmentation and improved training & inference process (D19-52)
Copied to clipboard
| Challenge: | This paper describes the neural machine translation systems for the shared translation tasks of WAT 2019 . |
| Approach: | They propose a model for translation tasks of WAT 2019 that employs a Transformer model as the baseline and a deep layer model to improve translation quality. |
| Outcome: | The proposed methods can improve translation quality over traditional statistical machine translation (SMT) The proposed models can improve the translation quality of Japanese-English and Japanese-Chinese corpus. |
Sarah’s Participation in WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | Using the Transformer architecture, we trained similar systems across different tasks. |
| Approach: | They presented their results in the 6th Workshop on Asian Translation (WAT) translation task and their submissions to the task. |
| Outcome: | The proposed models perform better on tasks with smaller datasets and with smaller heads on multilingual datasets. |
Our Neural Machine Translation Systems for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | In the last five years, statistical machine translation is gradually fading out in favor of neural machine translation. |
| Approach: | They describe a novel Neural Machine Translation (NMT) system for the WAT 2019 translation tasks they focus on. |
| Outcome: | The proposed system improves translation accuracy while replacing absolute position representations with relative positions. |
Japanese-Russian TMU Neural Machine Translation System using Multilingual Model for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | Using parallel corpora of different language pairs as training data is effective for multilingual neural machine translation model in extremely low resource situations. |
| Approach: | They propose to use Japanese-English and English-Russian parallel corpora as training data for their system to improve JapaneseRussian news translation. |
| Outcome: | The proposed system improves translation quality for JapaneseRussian language pairs in low resource situations. |
NLPRL at WAT2019: Transformer-based Tamil – English Indic Task Neural Machine Translation System (D19-52)
Copied to clipboard
| Challenge: | a majority of Asians speak low to medium resource languages . lack of resources poses a challenge, which requires innovative solutions . |
| Approach: | They propose a Neural Machine Translation system for Tamil-English Indic Task . they train a system for both Tamil-to-English and English-to Tamil pairs . |
| Outcome: | The proposed system is based on a Transformer-based architecture and is not very innovative, but can be treated as an incremental step in this direction. |
Idiap NMT System for WAT 2019 Multimodal Translation Task (D19-52)
Copied to clipboard
| Challenge: | In the past few decades, multi-modality has received critical attention in translation studies, although the benefit of visual modality in machine translation is still in debate. |
| Approach: | They propose to use the Transformer model and IITB English-Hindi parallel corpus as additional data sources for the evaluation and challenge test sets. |
| Outcome: | The proposed system outperforms systems that consider visual information in the English-Hindi Multi-Modal Translation task. |
WAT2019: English-Hindi Translation on Hindi Visual Genome Dataset (D19-52)
Copied to clipboard
| Challenge: | A multimodal translation is a task of translating a source language to a target language . a parallel text corpus and images are used to represent the contextual details of the text . |
| Approach: | They compare a multimodal approach to a parallel text corpus and image caption generation approach to translate text in English to Hindi as a part of WAT2019 shared task. |
| Outcome: | The proposed approach improves the translation of English to Hindi in three tasks . the proposed system is based on a neural network and can be used in healthcare, government, disaster management, etc. |
SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task (D19-52)
Copied to clipboard
| Challenge: | Several data sets were provided for the task, but the data was limited and the distance and richness of the language pair were very challenging. |
| Approach: | They describe the SYSTRAN neural MT systems employed for the 6th Workshop on Asian Translation (WAT) they use the neural Transformer architecture learned over the provided resources and perform synthetic data generation experiments which aim at alleviating the data scarcity problem. |
| Outcome: | The proposed systems rank first according to automatic evaluations based on the neural Transformer architecture learned over the provided resources. |
UCSYNLP-Lab Machine Translation Systems for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has achieved stateof-the-art performance on various language pairs. |
| Approach: | They describe the UCSYNLP-Lab submission to WAT 2019 for Myanmar-English translation tasks in both directions. |
| Outcome: | The proposed translation system improves the performance of Myanmar-English translation tasks. |
Sentiment Aware Neural Machine Translation (D19-52)
Copied to clipboard
| Challenge: | Sentiment ambiguous lexicons are used when context is absent in translations . most systems aim to produce one correct translation for a given source sentence . |
| Approach: | They propose a neural machine translation method that preserves sentiment in two sentiment scenarios and a method that embeds sentiment into a sentence. |
| Outcome: | The proposed method outperforms a baseline with sentiment-aware translations in both the BLEU score and translation accuracy. |
Overcoming the Rare Word Problem for low-resource language pairs in Neural Machine Translation (D19-52)
Copied to clipboard
| Challenge: | Despite above approaches can improve the prediction of rare words, they still have challenges which have adverse effects on its effectiveness. |
| Approach: | They propose three ways to address rare-word problem in neural machine translation systems . they propose an algorithm to learn morphology of unknown words for English in supervised way to minimize adverse effect of rare- word problem. |
| Outcome: | The proposed approaches improve accuracy on two low-resource language pairs. |
Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation (D19-52)
Copied to clipboard
| Challenge: | a number of Arabic text diacritizers use diacritics to convey information about meaning of a word . Arabic text to speech (TTS) requires a complex process to determine the correct diacritical for each character . |
| Approach: | They propose to use Arabic diacritization to enhance machine translation models . they propose to build automatic Arabic text diacritics using two approaches . |
| Outcome: | The proposed models are either better or on par with other models, which require language-dependent post-processing steps, unlike ours. |