Search Results for author: Mamoru Komachi

Found 95 papers, 20 papers with code

TMUOU Submission for WMT20 Quality Estimation Shared Task

no code implementations WMT (EMNLP) 2020 Akifumi Nakamachi, Hiroki Shimanaka, Tomoyuki Kajiwara, Mamoru Komachi

We introduce the TMUOU submission for the WMT20 Quality Estimation Shared Task 1: Sentence-Level Direct Assessment.

Korean-to-Japanese Neural Machine Translation System using Hanja Information

no code implementations AACL (WAT) 2020 Hwichan Kim, Tosho Hirasawa, Mamoru Komachi

In this paper, we describe our TMU neural machine translation (NMT) system submitted for the Patent task (Korean→Japanese) of the 7th Workshop on Asian Translation (WAT 2020, Nakazawa et al., 2020).

Machine Translation Translation

TMU NMT System with Japanese BART for the Patent task of WAT 2021

no code implementations ACL (WAT) 2021 Hwichan Kim, Mamoru Komachi

In this paper, we introduce our TMU Neural Machine Translation (NMT) system submitted for the Patent task (Korean Japanese and English Japanese) of 8th Workshop on Asian Translation (Nakazawa et al., 2021).

Fine-tuning Machine Translation +1

Modeling Text using the Continuous Space Topic Model with Pre-Trained Word Embeddings

no code implementations ACL 2021 Seiichi Inoue, Taichi Aida, Mamoru Komachi, Manabu Asai

In this study, we propose a model that extends the continuous space topic model (CSTM), which flexibly controls word probability in a document, using pre-trained word embeddings.

Document Classification Word Embeddings

Neural Combinatory Constituency Parsing

1 code implementation Findings (ACL) 2021 Zhousi Chen, Longtu Zhang, Aizhan Imankulova, Mamoru Komachi

We propose two fast neural combinatory models for constituency parsing: binary and multi-branching.

Constituency Parsing

Comparison of Grammatical Error Correction Using Back-Translation Models

no code implementations NAACL 2021 Aomi Koyama, Kengo Hotate, Masahiro Kaneko, Mamoru Komachi

Therefore, GEC studies have developed various methods to generate pseudo data, which comprise pairs of grammatical and artificially produced ungrammatical sentences.

Grammatical Error Correction Translation

Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction

no code implementations COLING 2020 Kengo Hotate, Masahiro Kaneko, Mamoru Komachi

In this study, we propose a beam search method to obtain diverse outputs in a local sequence transduction task where most of the tokens in the source and target sentences overlap, such as in grammatical error correction (GEC).

Grammatical Error Correction

Cross-lingual Transfer Learning for Grammatical Error Correction

no code implementations COLING 2020 Ikumi Yamashita, Satoru Katsumata, Masahiro Kaneko, Aizhan Imankulova, Mamoru Komachi

Cross-lingual transfer learning from high-resource languages (the source models) is effective for training models of low-resource languages (the target models) for various tasks.

Cross-Lingual Transfer Grammatical Error Correction +1

Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions

1 code implementation EAMT 2020 YuTing Zhao, Mamoru Komachi, Tomoyuki Kajiwara, Chenhui Chu

In contrast, we propose the application of semantic image regions for MNMT by integrating visual and textual features using two individual attention mechanisms (double attention).

Machine Translation Translation

Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition

no code implementations ACL 2020 Hwichan Kim, Tosho Hirasawa, Mamoru Komachi

The primary limitation of North Korean to English translation is the lack of a parallel corpus; therefore, high translation accuracy cannot be achieved.

Machine Translation Tokenization +1

English-to-Japanese Diverse Translation by Combining Forward and Backward Outputs

no code implementations WS 2020 Masahiro Kaneko, Aizhan Imankulova, Tosho Hirasawa, Mamoru Komachi

We introduce our TMU system that is submitted to The 4th Workshop on Neural Generation and Translation (WNGT2020) to English-to-Japanese (En→Ja) track on Simultaneous Translation And Paraphrase for Language Education (STAPLE) shared task.

Machine Translation Translation

Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner's Error Tendency

no code implementations ACL 2020 Yujin Takahashi, Satoru Katsumata, Mamoru Komachi

To address the limitations of language and computational resources, we assume that introducing pseudo errors into sentences similar to those written by the language learners is more efficient, rather than incorporating random pseudo errors into monolingual data.

Grammatical Error Correction

Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020

no code implementations23 Jun 2020 Tosho Hirasawa, Zhishen Yang, Mamoru Komachi, Naoaki Okazaki

Video-guided machine translation as one of multimodal neural machine translation tasks targeting on generating high-quality text translation by tangibly engaging both video and text.

Machine Translation Translation

Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Model

1 code implementation24 May 2020 Satoru Katsumata, Mamoru Komachi

In this study, we explore the utility of bidirectional and auto-regressive transformers (BART) as a generic pretrained encoder-decoder model for GEC.

Grammatical Error Correction

Construction of an Evaluation Corpus for Grammatical Error Correction for Learners of Japanese as a Second Language

no code implementations LREC 2020 Aomi Koyama, Tomoshige Kiyuna, Kenji Kobayashi, Mio Arai, Mamoru Komachi

As our corpus has less noise and its annotation scheme reflects the characteristics of the dataset, it is ideal as an evaluation corpus for correcting grammatical errors in sentences written by JSL learners.

Grammatical Error Correction Machine Translation +1

Automated Essay Scoring System for Nonnative Japanese Learners

no code implementations LREC 2020 Reo Hirao, Mio Arai, Hiroki Shimanaka, Satoru Katsumata, Mamoru Komachi

In this study, we created an automated essay scoring (AES) system for nonnative Japanese learners using an essay dataset with annotations for a holistic score and multiple trait scores, including content, organization, and language scores.

Automated Essay Scoring

Towards Multimodal Simultaneous Neural Machine Translation

1 code implementation WMT (EMNLP) 2020 Aizhan Imankulova, Masahiro Kaneko, Tosho Hirasawa, Mamoru Komachi

Simultaneous translation involves translating a sentence before the speaker's utterance is completed in order to realize real-time understanding in multiple languages.

Machine Translation Translation

Japanese-Russian TMU Neural Machine Translation System using Multilingual Model for WAT 2019

no code implementations WS 2019 Aizhan Imankulova, Masahiro Kaneko, Mamoru Komachi

We introduce our system that is submitted to the News Commentary task (Japanese{\textless}-{\textgreater}Russian) of the 6th Workshop on Asian Translation.

Machine Translation Translation

Improving Context-aware Neural Machine Translation with Target-side Context

no code implementations2 Sep 2019 Hayahide Yamagishi, Mamoru Komachi

We propose a weight sharing method wherein NMT saves decoder states and calculates an attention vector using the saved states when translating a current sentence.

Document-level Machine Translation +1

(Almost) Unsupervised Grammatical Error Correction using Synthetic Comparable Corpus

no code implementations WS 2019 Satoru Katsumata, Mamoru Komachi

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation.

Grammatical Error Correction Machine Translation +1

TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track

no code implementations WS 2019 Masahiro Kaneko, Kengo Hotate, Satoru Katsumata, Mamoru Komachi

Thus, it is not straightforward to utilize language representations trained from a large corpus, such as Bidirectional Encoder Representations from Transformers (BERT), in a form suitable for the learner{'}s grammatical errors.

Grammatical Error Correction Re-Ranking

Machine Translation Evaluation with BERT Regressor

no code implementations29 Jul 2019 Hiroki Shimanaka, Tomoyuki Kajiwara, Mamoru Komachi

We introduce the metric using BERT (Bidirectional Encoder Representations from Transformers) (Devlin et al., 2019) for automatic machine translation evaluation.

Machine Translation Translation

Towards Unsupervised Grammatical Error Correction using Statistical Machine Translation with Synthetic Comparable Corpus

no code implementations23 Jul 2019 Satoru Katsumata, Mamoru Komachi

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation.

Grammatical Error Correction Machine Translation +1

Sakura: Large-scale Incorrect Example Retrieval System for Learners of Japanese as a Second Language

no code implementations ACL 2019 Mio Arai, Tomonori Kodaira, Mamoru Komachi

This study develops an incorrect example retrieval system, called Sakura, using a large-scale Lang-8 dataset for Japanese language learners.

Controlling Grammatical Error Correction Using Word Edit Rate

no code implementations ACL 2019 Kengo Hotate, Masahiro Kaneko, Satoru Katsumata, Mamoru Komachi

In this paper, we propose a method for neural grammar error correction (GEC) that can control the degree of correction.

Grammatical Error Correction

Debiasing Word Embeddings Improves Multimodal Machine Translation

no code implementations WS 2019 Tosho Hirasawa, Mamoru Komachi

In this study, we examine various kinds of word embeddings and introduce two debiasing techniques for three multimodal NMT models and two language pairs -- English-German translation and English-French translation.

Multimodal Machine Translation Translation +1

Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection

no code implementations15 Apr 2019 Masahiro Kaneko, Mamoru Komachi

In this work, we investigate the effect of utilizing information not only from the final layer but also from intermediate layers of a pre-trained language representation model to detect grammatical errors.

Grammatical Error Detection

Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information

no code implementations1 Mar 2019 Longtu Zhang, Mamoru Komachi

Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et al., 2018).

Machine Translation Translation

Divide and Generate: Neural Generation of Complex Sentences

no code implementations29 Jan 2019 Tomoya Ogata, Mamoru Komachi, Tomoya Takatani

We propose a task to generate a complex sentence from a simple sentence in order to amplify various kinds of responses in the database.

Neural Machine Translation of Logographic Language Using Sub-character Level Information

no code implementations WS 2018 Longtu Zhang, Mamoru Komachi

Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units.

Machine Translation Translation +1

Neural Machine Translation of Logographic Languages Using Sub-character Level Information

no code implementations7 Sep 2018 Longtu Zhang, Mamoru Komachi

Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units.

Machine Translation Translation

TMU System for SLAM-2018

1 code implementation WS 2018 Masahiro Kaneko, Tomoyuki Kajiwara, Mamoru Komachi

We introduce the TMU systems for the second language acquisition modeling shared task 2018 (Settles et al., 2018).

Language Acquisition

Japanese Predicate Conjugation for Neural Machine Translation

no code implementations NAACL 2018 Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi, Mamoru Komachi

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.

Machine Translation Translation

Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations

no code implementations NAACL 2018 Hiroki Shimanaka, Tomoyuki Kajiwara, Mamoru Komachi

Sentence representations can capture a wide range of information that cannot be captured by local features based on character or word N-grams.

Machine Translation Translation

Suggesting Sentences for ESL using Kernel Embeddings

no code implementations WS 2017 Kent Shioda, Mamoru Komachi, Rue Ikeya, Daichi Mochihashi

This method implicitly models latent intent of query and sentences, and alleviates the problem of noisy alignment.

Semantic Textual Similarity

Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language

no code implementations WS 2017 Yuuki Sekizawa, Tomoyuki Kajiwara, Mamoru Komachi

Neural machine translation (NMT) produces sentences that are more fluent than those produced by statistical machine translation (SMT).

Machine Translation Translation

MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting

1 code implementation IJCNLP 2017 Tomoyuki Kajiwara, Mamoru Komachi, Daichi Mochihashi

We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition.

Learning Word Embeddings Semantic Textual Similarity +1

Improving Japanese-to-English Neural Machine Translation by Voice Prediction

no code implementations IJCNLP 2017 Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, Mamoru Komachi

This study reports an attempt to predict the voice of reference using the information from the input sentences or previous input/output sentences.

Machine Translation Translation

Long Short-Term Memory for Japanese Word Segmentation

no code implementations PACLIC 2018 Yoshiaki Kitagawa, Mamoru Komachi

This study presents a Long Short-Term Memory (LSTM) neural network approach to Japanese word segmentation (JWS).

Chinese Word Segmentation

English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor

1 code implementation26 Jun 2017 Yukio Matsumura, Takayuki Sato, Mamoru Komachi

We confirm that our re-implementation also shows the same tendency and alleviates the problem of repeating and missing words in the translation on a English-Japanese task too.

Fine-tuning Machine Translation +1

Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention

no code implementations PACLIC 2018 Ryosuke Miyazaki, Mamoru Komachi

Previous approaches to training syntax-based sentiment classification models required phrase-level annotated corpora, which are not readily available in many languages other than English.

Classification General Classification +1

Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings

no code implementations2 Apr 2017 Junki Matsuo, Mamoru Komachi, Katsuhito Sudoh

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level.

Machine Translation Translation +2

Construction of a Japanese Word Similarity Dataset

2 code implementations LREC 2018 Yuya Sakaizawa, Mamoru Komachi

An evaluation of distributed word representation is generally conducted using a word similarity task and/or a word analogy task.

Word Similarity

Sparse Named Entity Classification using Factorization Machines

no code implementations15 Mar 2017 Ai Hirata, Mamoru Komachi

Named entity classification is the task of classifying text-based elements into various categories, including places, names, dates, times, and monetary values.

Classification General Classification

Disaster Analysis using User-Generated Weather Report

no code implementations WS 2016 Yasunobu Asakura, Masatsugu Hangyo, Mamoru Komachi

Information extraction from user-generated text has gained much attention with the growth of the Web. Disaster analysis using information from social media provides valuable, real-time, geolocation information for helping people caught up these in disasters.

Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings

no code implementations COLING 2016 Tomoyuki Kajiwara, Mamoru Komachi

To obviate the need for human annotation, we propose an unsupervised method that automatically builds the monolingual parallel corpus for text simplification using sentence similarity based on word embeddings.

Machine Translation Sentence Similarity +3

Analysis of English Spelling Errors in a Word-Typing Game

no code implementations LREC 2016 Ryuichi Tachibana, Mamoru Komachi

Therefore, we propose a new correctable word-typing game that is more similar to the actual writing process.

UniDic for Early Middle Japanese: a Dictionary for Morphological Analysis of Classical Japanese

no code implementations LREC 2012 Toshinobu Ogiso, Mamoru Komachi, Yasuharu Den, Yuji Matsumoto

In order to construct an annotated diachronic corpus of Japanese, we propose to create a new dictionary for morphological analysis of Early Middle Japanese (Classical Japanese) based on UniDic, a dictionary for Contemporary Japanese.

Morphological Analysis

Cannot find the paper you are looking for? You can Submit a new open access paper.