arXiv subjects

Mamoru Komachi

Publications and source records attributed to Mamoru Komachi.

At least 37 records · Page 2Linked to original sources

arXiv2020

Chinese Grammatical Correction Using BERT-based Pre-trained Model

In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we verify the effectiveness of two methods that incorporate a BERT-based pre-trained model developed by Cui et al. (2020) into an encoder-decoder model on Chinese grammatical error correction tasks. We also analyze the error type and conclude that sentence-level errors are yet to be addressed.

cs.CL↗

arXiv2020

Towards Multimodal Simultaneous Neural Machine Translation

Simultaneous translation involves translating a sentence before the speaker's utterance is completed in order to realize real-time understanding in multiple languages. This task is significantly more challenging than the general full sentence translation because of the shortage of input information during decoding. To alleviate this shortage, we propose multimodal simultaneous neural machine translation (MSNMT), which leverages visual information as an additional modality. Our experiments with the Multi30k dataset showed that MSNMT significantly outperforms its text-only counterpart in more timely translation situations with low latency. Furthermore, we verified the importance of visual information during decoding by performing an adversarial evaluation of MSNMT, where we studied how models behaved with incongruent input modality and analyzed the effect of different word order between source and target languages.

cs.CL↗

arXiv2020

JSSS: free Japanese speech corpus for summarization and simplification

In this paper, we construct a new Japanese speech corpus for speech-based summarization and simplification, "JSSS" (pronounced "j-triple-s"). Given the success of reading-style speech synthesis from short-form sentences, we aim to design more difficult tasks for delivering information to humans. Our corpus contains voices recorded for two tasks that have a role in providing information under constraints: duration-constrained text-to-speech summarization and speaking-style simplification. It also contains utterances of long-form sentences as an optional task. This paper describes how we designed the corpus, which is available on our project page.

eess.AS↗

arXiv2020

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

Studies on grammatical error correction (GEC) have reported the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining for GEC because of the size of the pseudodata. In this study, we explore the utility of bidirectional and auto-regressive transformers (BART) as a generic pretrained encoder-decoder model for GEC. With the use of this generic pretrained model for GEC, the time-consuming pretraining can be eliminated. We find that monolingual and multilingual BART models achieve high performance in GEC, with one of the results being comparable to the current strong results in English GEC. Our implementations are publicly available at GitHub (https://github.com/Katsumata420/generic-pretrained-GEC).

cs.CL↗

arXiv2020

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

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. In this work, we presented our video-guided machine translation system in approaching the Video-guided Machine Translation Challenge 2020. This system employs keyframe-based video feature extractions along with the video feature positional encoding. In the evaluation phase, our system scored 36.60 corpus-level BLEU-4 and achieved the 1st place on the Video-guided Machine Translation Challenge 2020.

cs.CL↗

arXiv2019

Dynamic Fusion: Attentional Language Model for Neural Machine Translation

Neural Machine Translation (NMT) can be used to generate fluent output. As such, language models have been investigated for incorporation with NMT. In prior investigations, two models have been used: a translation model and a language model. The translation model's predictions are weighted by the language model with a hand-crafted ratio in advance. However, these approaches fail to adopt the language model weighting with regard to the translation history. In another line of approach, language model prediction is incorporated into the translation model by jointly considering source and target information. However, this line of approach is limited because it largely ignores the adequacy of the translation output. Accordingly, this work employs two mechanisms, the translation model and the language model, with an attentive architecture to the language model as an auxiliary element of the translation model. Compared with previous work in English--Japanese machine translation using a language model, the experimental results obtained with the proposed Dynamic Fusion mechanism improve BLEU and Rank-based Intuitive Bilingual Evaluation Scores (RIBES) scores. Additionally, in the analyses of the attention and predictivity of the language model, the Dynamic Fusion mechanism allows predictive language modeling that conforms to the appropriate grammatical structure.

cs.CL↗

arXiv2019

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

In recent years, several studies on neural machine translation (NMT) have attempted to use document-level context by using a multi-encoder and two attention mechanisms to read the current and previous sentences to incorporate the context of the previous sentences. These studies concluded that the target-side context is less useful than the source-side context. However, we considered that the reason why the target-side context is less useful lies in the architecture used to model these contexts. Therefore, in this study, we investigate how the target-side context can improve context-aware neural machine translation. 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. Our experiments show that the target-side context is also useful if we plug it into NMT as the decoder state when translating a previous sentence.

cs.CL↗

arXiv2019

Machine Translation Evaluation with BERT Regressor

We introduce the metric using BERT (Bidirectional Encoder Representations from Transformers) (Devlin et al., 2019) for automatic machine translation evaluation. The experimental results of the WMT-2017 Metrics Shared Task dataset show that our metric achieves state-of-the-art performance in segment-level metrics task for all to-English language pairs.

cs.CL↗

arXiv2019

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

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. We verified our GEC system through experiments on various GEC dataset, includi ng a low resource track of the shared task at Building Educational Applications 2019 (BEA 2019). As a result, we achieved an F_0.5 score of 28.31 points with the test data of the low resource track.

cs.CL↗

arXiv2019

Debiasing Word Embeddings Improves Multimodal Machine Translation

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been explored extensively. Further, pretrained word embeddings in high dimensional spaces have been reported to suffer from the hubness problem. Although some debiasing techniques have been proposed to address this problem for other natural language processing tasks, they have seldom been studied for multimodal NMT models. 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. With our optimal settings, the overall performance of multimodal models was improved by up to +1.93 BLEU and +2.02 METEOR for English-German translation and +1.73 BLEU and +0.95 METEOR for English-French translation.

cs.CL↗

arXiv2019

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

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary, and simply using the output of the final layer is not necessarily sufficient. Moreover, to our knowledge, exploiting large language representation models to detect grammatical errors has not yet been studied. 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. We propose a multi-head multi-layer attention model that determines the appropriate layers in Bidirectional Encoder Representation from Transformers (BERT). The proposed method achieved the best scores on three datasets for grammatical error detection tasks, outperforming the current state-of-the-art method by 6.0 points on FCE, 8.2 points on CoNLL14, and 12.2 points on JFLEG in terms of F_0.5. We also demonstrate that by using multi-head multi-layer attention, our model can exploit a broader range of information for each token in a sentence than a model that uses only the final layer's information.

cs.CL↗

arXiv2019

Multi-task Learning for Japanese Predicate Argument Structure Analysis

An event-noun is a noun that has an argument structure similar to a predicate. Recent works, including those considered state-of-the-art, ignore event-nouns or build a single model for solving both Japanese predicate argument structure analysis (PASA) and event-noun argument structure analysis (ENASA). However, because there are interactions between predicates and event-nouns, it is not sufficient to target only predicates. To address this problem, we present a multi-task learning method for PASA and ENASA. Our multi-task models improved the performance of both tasks compared to a single-task model by sharing knowledge from each task. Moreover, in PASA, our models achieved state-of-the-art results in overall F1 scores on the NAIST Text Corpus. In addition, this is the first work to employ neural networks in ENASA.

cs.CL↗

arXiv2019

Multimodal Machine Translation with Embedding Prediction

Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from a shortage of available training data, resulting in poor performance for translating rare words. In NMT, pretrained word embeddings have been shown to improve NMT of low-resource domains, and a search-based approach is proposed to address the rare word problem. In this study, we effectively combine these two approaches in the context of multimodal NMT and explore how we can take full advantage of pretrained word embeddings to better translate rare words. We report overall performance improvements of 1.24 METEOR and 2.49 BLEU and achieve an improvement of 7.67 F-score for rare word translation.

cs.CL↗

arXiv2019

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

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). However, no research has been done to logographic language pairs. This study focuses on Chinese-Japanese UNMT trained by data containing sub-character (ideograph or stroke) level information which is decomposed from character level data. BLEU scores of both character and sub-character level systems were compared against each other and the results showed that despite the effectiveness of UNMT on character level data, sub-character level data could further enhance the performance, in which the stroke level system outperformed the ideograph level system.

cs.CL↗

arXiv2019

Divide and Generate: Neural Generation of Complex Sentences

We propose a task to generate a complex sentence from a simple sentence in order to amplify various kinds of responses in the database. We first divide a complex sentence into a main clause and a subordinate clause to learn a generator model of modifiers, and then use the model to generate a modifier clause to create a complex sentence from a simple sentence. We present an automatic evaluation metric to estimate the quality of the models and show that a pipeline model outperforms an end-to-end model.

cs.CL↗

arXiv2018

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

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. Thus, we propose the use of tree-structured Long Short-Term Memory with an attention mechanism that pays attention to each subtree of the parse tree. Experimental results indicate that our model achieves the state-of-the-art performance in a Japanese sentiment classification task.

cs.CL↗

arXiv2018

The Rule of Three: Abstractive Text Summarization in Three Bullet Points

Neural network-based approaches have become widespread for abstractive text summarization. Though previously proposed models for abstractive text summarization addressed the problem of repetition of the same contents in the summary, they did not explicitly consider its information structure. One of the reasons these previous models failed to account for information structure in the generated summary is that standard datasets include summaries of variable lengths, resulting in problems in analyzing information flow, specifically, the manner in which the first sentence is related to the following sentences. Therefore, we use a dataset containing summaries with only three bullet points, and propose a neural network-based abstractive summarization model that considers the information structures of the generated summaries. Our experimental results show that the information structure of a summary can be controlled, thus improving the performance of the overall summarization.

cs.CL↗

arXiv2018

Long Short-Term Memory for Japanese Word Segmentation

This study presents a Long Short-Term Memory (LSTM) neural network approach to Japanese word segmentation (JWS). Previous studies on Chinese word segmentation (CWS) succeeded in using recurrent neural networks such as LSTM and gated recurrent units (GRU). However, in contrast to Chinese, Japanese includes several character types, such as hiragana, katakana, and kanji, that produce orthographic variations and increase the difficulty of word segmentation. Additionally, it is important for JWS tasks to consider a global context, and yet traditional JWS approaches rely on local features. In order to address this problem, this study proposes employing an LSTM-based approach to JWS. The experimental results indicate that the proposed model achieves state-of-the-art accuracy with respect to various Japanese corpora.

cs.CL↗