Mamoru Komachi

Kenichiro Ando, Takashi Okumura, Mamoru Komachi et al.

Automated summarization of clinical texts can reduce the burden of medical professionals. "Discharge summaries" are one promising application of the summarization, because they can be generated from daily inpatient records. Our preliminary experiment suggests that 20-31% of the descriptions in discharge summaries overlap with the content of the inpatient records. However, it remains unclear how the summaries should be generated from the unstructured source. To decompose the physician's summarization process, this study aimed to identify the optimal granularity in summarization. We first defined three types of summarization units with different granularities to compare the performance of the discharge summary generation: whole sentences, clinical segments, and clauses. We defined clinical segments in this study, aiming to express the smallest medically meaningful concepts. To obtain the clinical segments, it was necessary to automatically split the texts in the first stage of the pipeline. Accordingly, we compared rule-based methods and a machine learning method, and the latter outperformed the formers with an F1 score of 0.846 in the splitting task. Next, we experimentally measured the accuracy of extractive summarization using the three types of units, based on the ROUGE-1 metric, on a multi-institutional national archive of health records in Japan. The measured accuracies of extractive summarization using whole sentences, clinical segments, and clauses were 31.91, 36.15, and 25.18, respectively. We found that the clinical segments yielded higher accuracy than sentences and clauses. This result indicates that summarization of inpatient records demands finer granularity than sentence-oriented processing. Although we used only Japanese health records, it can be interpreted as follows: physicians extract "concepts of medical significance" from patient records and recombine them ...

Kenichiro Ando, Mamoru Komachi, Takashi Okumura et al.

During the patient's hospitalization, the physician must record daily observations of the patient and summarize them into a brief document called "discharge summary" when the patient is discharged. Automated generation of discharge summary can greatly relieve the physicians' burden, and has been addressed recently in the research community. Most previous studies of discharge summary generation using the sequence-to-sequence architecture focus on only inpatient notes for input. However, electric health records (EHR) also have rich structured metadata (e.g., hospital, physician, disease, length of stay, etc.) that might be useful. This paper investigates the effectiveness of medical meta-information for summarization tasks. We obtain four types of meta-information from the EHR systems and encode each meta-information into a sequence-to-sequence model. Using Japanese EHRs, meta-information encoded models increased ROUGE-1 by up to 4.45 points and BERTScore by 3.77 points over the vanilla Longformer. Also, we found that the encoded meta-information improves the precisions of its related terms in the outputs. Our results showed the benefit of the use of medical meta-information.

Taichi Aida, Mamoru Komachi, Toshinobu Ogiso et al.

Understanding the temporal evolution of sets of vectors is a fundamental challenge across various domains, including ecology, crime analysis, and linguistics. For instance, ecosystem structures evolve due to interactions among plants, herbivores, and carnivores; the spatial distribution of crimes shifts in response to societal changes; and word embedding vectors reflect cultural and semantic trends over time. However, analyzing such time-varying sets of vectors is challenging due to their complicated structures, which also evolve over time. In this work, we propose a novel method for modeling the distribution underlying each set of vectors using infinite-dimensional Gaussian processes. By approximating the latent function in the Gaussian process with Random Fourier Features, we obtain compact and comparable vector representations over time. This enables us to track and visualize temporal transitions of vector sets in a low-dimensional space. We apply our method to both sociological data (crime distributions) and linguistic data (word embeddings), demonstrating its effectiveness in capturing temporal dynamics. Our results show that the proposed approach provides interpretable and robust representations, offering a powerful framework for analyzing structural changes in temporally indexed vector sets across diverse domains.

Hwichan Kim, Jun Suzuki, Tosho Hirasawa et al.

Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. A distinctive characteristic of MLLMs is their high-quality translation capabilities, indicating an acquired proficiency in aligning between languages. This study explores how to enhance the zero-shot performance of MLLMs in non-English languages by leveraging their alignment capability between English and non-English languages. To achieve this, we first analyze the behavior of MLLMs when performing translation and reveal that there are large magnitude features that play a critical role in the translation process. Inspired by these findings, we retain the weights associated with operations involving the large magnitude features and prune other weights to force MLLMs to rely on these features for tasks beyond translation. We empirically demonstrate that this pruning strategy can enhance the MLLMs' performance in non-English language.

Ayako Sato, Hwichan Kim, Zhousi Chen et al.

"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenomenon where certain evaluation scores are generated disproportionately often, leading reduced evaluation performance. This study investigates the cause of this bias. Given that most evaluator LLMs are aligned through instruction tuning and preference tuning, and that prior research suggests alignment reduces output diversity, we hypothesize that numerical bias arises from alignment. To test this, we compare outputs from pre- and post-alignment LLMs, and observe that alignment indeed increases numerical bias. We also explore mitigation strategies for post-alignment LLMs, including temperature scaling, distribution calibration, and score range adjustment. Among these, score range adjustment is most effective in reducing bias and improving performance, though still heuristic. Our findings highlight the need for further work on optimal score range selection and more robust mitigation strategies.

Ritsu Sakabe, Hwichan Kim, Tosho Hirasawa et al.

Computational humor is a frontier for creating advanced and engaging natural language processing (NLP) applications, such as sophisticated dialogue systems. While previous studies have benchmarked the humor capabilities of Large Language Models (LLMs), they have often relied on single-dimensional evaluations, such as judging whether something is simply ``funny.'' This paper argues that a multifaceted understanding of humor is necessary and addresses this gap by systematically evaluating LLMs through the lens of Oogiri, a form of Japanese improvisational comedy games. To achieve this, we expanded upon existing Oogiri datasets with data from new sources and then augmented the collection with Oogiri responses generated by LLMs. We then manually annotated this expanded collection with 5-point absolute ratings across six dimensions: Novelty, Clarity, Relevance, Intelligence, Empathy, and Overall Funniness. Using this dataset, we assessed the capabilities of state-of-the-art LLMs on two core tasks: their ability to generate creative Oogiri responses and their ability to evaluate the funniness of responses using a six-dimensional evaluation. Our results show that while LLMs can generate responses at a level between low- and mid-tier human performance, they exhibit a notable lack of Empathy. This deficit in Empathy helps explain their failure to replicate human humor assessment. Correlation analyses of human and model evaluation data further reveal a fundamental divergence in evaluation criteria: LLMs prioritize Novelty, whereas humans prioritize Empathy. We release our annotated corpus to the community to pave the way for the development of more emotionally intelligent and sophisticated conversational agents.

Satoru Katsumata, Mamoru Komachi

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).

Masamune Kobayashi, Masato Mita, Mamoru Komachi

Large Language Models (LLMs) have been reported to outperform existing automatic evaluation metrics in some tasks, such as text summarization and machine translation. However, there has been a lack of research on LLMs as evaluators in grammatical error correction (GEC). In this study, we investigate the performance of LLMs in GEC evaluation by employing prompts designed to incorporate various evaluation criteria inspired by previous research. Our extensive experimental results demonstrate that GPT-4 achieved Kendall's rank correlation of 0.662 with human judgments, surpassing all existing methods. Furthermore, in recent GEC evaluations, we have underscored the significance of the LLMs scale and particularly emphasized the importance of fluency among evaluation criteria.

Hajime Kiyama, Taichi Aida, Mamoru Komachi et al.

The meanings and relationships of words shift over time. This phenomenon is referred to as semantic shift. Research focused on understanding how semantic shifts occur over multiple time periods is essential for gaining a detailed understanding of semantic shifts. However, detecting change points only between adjacent time periods is insufficient for analyzing detailed semantic shifts, and using BERT-based methods to examine word sense proportions incurs a high computational cost. To address those issues, we propose a simple yet intuitive framework for how semantic shifts occur over multiple time periods by leveraging a similarity matrix between the embeddings of the same word through time. We compute a diachronic word similarity matrix using fast and lightweight word embeddings across arbitrary time periods, making it deeper to analyze continuous semantic shifts. Additionally, by clustering the similarity matrices for different words, we can categorize words that exhibit similar behavior of semantic shift in an unsupervised manner.

Masamune Kobayashi, Masato Mita, Mamoru Komachi

Metrics are the foundation for automatic evaluation in grammatical error correction (GEC), with their evaluation of the metrics (meta-evaluation) relying on their correlation with human judgments. However, conventional meta-evaluations in English GEC encounter several challenges including biases caused by inconsistencies in evaluation granularity, and an outdated setup using classical systems. These problems can lead to misinterpretation of metrics and potentially hinder the applicability of GEC techniques. To address these issues, this paper proposes SEEDA, a new dataset for GEC meta-evaluation. SEEDA consists of corrections with human ratings along two different granularities: edit-based and sentence-based, covering 12 state-of-the-art systems including large language models (LLMs), and two human corrections with different focuses. The results of improved correlations by aligning the granularity in the sentence-level meta-evaluation, suggest that edit-based metrics may have been underestimated in existing studies. Furthermore, correlations of most metrics decrease when changing from classical to neural systems, indicating that traditional metrics are relatively poor at evaluating fluently corrected sentences with many edits.

Kenichiro Ando, Satoshi Sekine, Mamoru Komachi

Wikipedia can be edited by anyone and thus contains various quality sentences. Therefore, Wikipedia includes some poor-quality edits, which are often marked up by other editors. While editors' reviews enhance the credibility of Wikipedia, it is hard to check all edited text. Assisting in this process is very important, but a large and comprehensive dataset for studying it does not currently exist. Here, we propose WikiSQE, the first large-scale dataset for sentence quality estimation in Wikipedia. Each sentence is extracted from the entire revision history of English Wikipedia, and the target quality labels were carefully investigated and selected. WikiSQE has about 3.4 M sentences with 153 quality labels. In the experiment with automatic classification using competitive machine learning models, sentences that had problems with citation, syntax/semantics, or propositions were found to be more difficult to detect. In addition, by performing human annotation, we found that the model we developed performed better than the crowdsourced workers. WikiSQE is expected to be a valuable resource for other tasks in NLP.

Hwichan Kim, Sangwhan Moon, Naoaki Okazaki et al.

South and North Korea both use the Korean language. However, Korean NLP research has focused on South Korean only, and existing NLP systems of the Korean language, such as neural machine translation (NMT) models, cannot properly handle North Korean inputs. Training a model using North Korean data is the most straightforward approach to solving this problem, but there is insufficient data to train NMT models. In this study, we create data for North Korean NMT models using a comparable corpus. First, we manually create evaluation data for automatic alignment and machine translation. Then, we investigate automatic alignment methods suitable for North Korean. Finally, we verify that a model trained by North Korean bilingual data without human annotation can significantly boost North Korean translation accuracy compared to existing South Korean models in zero-shot settings.

Daisuke Suzuki, Yujin Takahashi, Ikumi Yamashita et al.

In grammatical error correction (GEC), automatic evaluation is an important factor for research and development of GEC systems. Previous studies on automatic evaluation have demonstrated that quality estimation models built from datasets with manual evaluation can achieve high performance in automatic evaluation of English GEC without using reference sentences.. However, quality estimation models have not yet been studied in Japanese, because there are no datasets for constructing quality estimation models. Therefore, in this study, we created a quality estimation dataset with manual evaluation to build an automatic evaluation model for Japanese GEC. Moreover, we conducted a meta-evaluation to verify the dataset's usefulness in building the Japanese quality estimation model.

Yujin Takahashi, Masahiro Kaneko, Masato Mita et al.

This study investigates how supervised quality estimation (QE) models of grammatical error correction (GEC) are affected by the learners' proficiency with the data. QE models for GEC evaluations in prior work have obtained a high correlation with manual evaluations. However, when functioning in a real-world context, the data used for the reported results have limitations because prior works were biased toward data by learners with relatively high proficiency levels. To address this issue, we created a QE dataset that includes multiple proficiency levels and explored the necessity of performing proficiency-wise evaluation for QE of GEC. Our experiments demonstrated that differences in evaluation dataset proficiency affect the performance of QE models, and proficiency-wise evaluation helps create more robust models.

Zhousi Chen, Longtu Zhang, Aizhan Imankulova et al.

We propose two fast neural combinatory models for constituency parsing: binary and multi-branching. Our models decompose the bottom-up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector composition based on the computed orientations or chunks. These models have theoretical sub-quadratic complexity and empirical linear complexity. The binary model achieves an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec. Both the models with XLNet provide near state-of-the-art accuracies for English. Syntactic branching tendency and headedness of a language are observed during the training and inference processes for Penn Treebank, Chinese Treebank, and Keyaki Treebank (Japanese).

Rob van der Goot, Ibrahim Sharaf, Aizhan Imankulova et al.

The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce xSID, a new benchmark for cross-lingual Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect. To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main tasks with masked language modeling is effective for slots, while machine translation transfer works best for intent classification.

Seiichiro Kondo, Kengo Hotate, Masahiro Kaneko et al.

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages. It is assumed that this issue is caused by insufficient number of long sentences in the training data. Therefore, this study proposes a simple data augmentation method to handle long sentences. In this method, we use only the given parallel corpora as the training data and generate long sentences by concatenating two sentences. Based on the experimental results, we confirm improvements in long sentence translation by the proposed data augmentation method, despite its simplicity. Moreover, the translation quality is further improved by the proposed method, when combined with back-translation.

Aomi Koyama, Kengo Hotate, Masahiro Kaneko et al.

Grammatical error correction (GEC) suffers from a lack of sufficient parallel data. Therefore, GEC studies have developed various methods to generate pseudo data, which comprise pairs of grammatical and artificially produced ungrammatical sentences. Currently, a mainstream approach to generate pseudo data is back-translation (BT). Most previous GEC studies using BT have employed the same architecture for both GEC and BT models. However, GEC models have different correction tendencies depending on their architectures. Thus, in this study, we compare the correction tendencies of the GEC models trained on pseudo data generated by different BT models, namely, Transformer, CNN, and LSTM. The results confirm that the correction tendencies for each error type are different for every BT model. Additionally, we examine the correction tendencies when using a combination of pseudo data generated by different BT models. As a result, we find that the combination of different BT models improves or interpolates the F_0.5 scores of each error type compared with that of single BT models with different seeds.

Hongfei Wang, Michiki Kurosawa, Satoru Katsumata et al.

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.

Shinnosuke Takamichi, Mamoru Komachi, Naoko Tanji et al.

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.

Tosho Hirasawa, Zhishen Yang, Mamoru Komachi et al.

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.

Aizhan Imankulova, Masahiro Kaneko, Tosho Hirasawa et al.

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.

Michiki Kurosawa, Mamoru Komachi

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.

Hayahide Yamagishi, Mamoru Komachi

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.

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. 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.

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. 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.

Tosho Hirasawa, Mamoru Komachi

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.

Masahiro Kaneko, Mamoru Komachi

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.

Hikaru Omori, Mamoru Komachi

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.

Tosho Hirasawa, Hayahide Yamagishi, Yukio Matsumura et al.

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.

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). 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.

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. 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.

Tomonori Kodaira, Mamoru Komachi

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.

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. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.

Satoru Katsumata, Yukio Matsumura, Hayahide Yamagishi et al.

Encoder-decoder models typically only employ words that are frequently used in the training corpus to reduce the computational costs and exclude noise. However, this vocabulary set may still include words that interfere with learning in encoder-decoder models. This paper proposes a method for selecting more suitable words for learning encoders by utilizing not only frequency, but also co-occurrence information, which we capture using the HITS algorithm. We apply our proposed method to two tasks: machine translation and grammatical error correction. For Japanese-to-English translation, this method achieves a BLEU score that is 0.56 points more than that of a baseline. It also outperforms the baseline method for English grammatical error correction, with an F0.5-measure that is 1.48 points higher.

Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi et al.

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. The proposed methods can generate low-frequency words and deal with unknown words. Two methods were considered to introduce conjugation information: the first considers it as a token (conjugation token) and the second considers it as an embedded vector (conjugation feature). The results using these methods demonstrate that the vocabulary size can be compressed by approximately 86.1% (Tanaka corpus) and the NMT models can output the words not in the training data set. Furthermore, BLEU scores improved by 0.91 points in Japanese-to-English translation, and 0.32 points in English-to-Japanese translation with ASPEC.

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. This paper examines the usefulness of universal sentence representations for evaluating the quality of machine translation. Although it is difficult to train sentence representations using small-scale translation datasets with manual evaluation, sentence representations trained from large-scale data in other tasks can improve the automatic evaluation of machine translation. Experimental results of the WMT-2016 dataset show that the proposed method achieves state-of-the-art performance with sentence representation features only.

Yoshiaki Kitagawa, Mamoru Komachi

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.

Yukio Matsumura, Takayuki Sato, Mamoru Komachi

Neural machine translation (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an encoder-decoder-reconstructor framework for NMT using back-translation. In this method, they selected the best forward translation model in the same manner as Bahdanau et al. (2015), and then trained a bi-directional translation model as fine-tuning. Their experiments show that it offers significant improvement in BLEU scores in Chinese-English translation task. 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. In addition, we evaluate the effectiveness of pre-training by comparing it with a jointly-trained model of forward translation and back-translation.

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. 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.

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. We propose to use word embeddings to perform word alignment for segment-level MT evaluation. We performed experiments with three types of alignment methods using word embeddings. We evaluated our proposed methods with various translation datasets. Experimental results show that our proposed methods outperform previous word embeddings-based methods.

Yuya Sakaizawa, Mamoru Komachi

An evaluation of distributed word representation is generally conducted using a word similarity task and/or a word analogy task. There are many datasets readily available for these tasks in English. However, evaluating distributed representation in languages that do not have such resources (e.g., Japanese) is difficult. Therefore, as a first step toward evaluating distributed representations in Japanese, we constructed a Japanese word similarity dataset. To the best of our knowledge, our dataset is the first resource that can be used to evaluate distributed representations in Japanese. Moreover, our dataset contains various parts of speech and includes rare words in addition to common words.

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. A bottleneck in named entity classification, however, is the data problem of sparseness, because new named entities continually emerge, making it rather difficult to maintain a dictionary for named entity classification. Thus, in this paper, we address the problem of named entity classification using matrix factorization to overcome the problem of feature sparsity. Experimental results show that our proposed model, with fewer features and a smaller size, achieves competitive accuracy to state-of-the-art models.