Search Results for author: Yuji Matsumoto

Found 117 papers, 21 papers with code

Improving Neural Machine Translation on resource-limited pairs using auxiliary data of a third language

no code implementations AMTA 2016 Ander Martinez, Yuji Matsumoto

This article combines three different ideas (splitting words into smaller units, using an extra dataset of a related language pair and using monolingual data) for improving the performance of NMT models on language pairs with limited data.

Machine Translation NMT +1

Coordination Generation via Synchronized Text-Infilling

no code implementations COLING 2022 Hiroki Teranishi, Yuji Matsumoto

Generating synthetic data for supervised learning from large-scale pre-trained language models has enhanced performances across several NLP tasks, especially in low-resource scenarios.

Data Augmentation Sentence Classification +1

Unsupervised Paraphrasing of Multiword Expressions

1 code implementation2 Jun 2023 Takashi Wada, Yuji Matsumoto, Timothy Baldwin, Jey Han Lau

We propose an unsupervised approach to paraphrasing multiword expressions (MWEs) in context.

text similarity

Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?

no code implementations10 Mar 2023 Kenichiro Ando, Mamoru Komachi, Takashi Okumura, Hiromasa Horiguchi, Yuji Matsumoto

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.

Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning

1 code implementation6 Dec 2022 Ukyo Honda, Taro Watanabe, Yuji Matsumoto

Discriminativeness is a desirable feature of image captions: captions should describe the characteristic details of input images.

Image Captioning reinforcement-learning +1

Exploring Optimal Granularity for Extractive Summarization of Unstructured Health Records: Analysis of the Largest Multi-Institutional Archive of Health Records in Japan

no code implementations20 Sep 2022 Kenichiro Ando, Takashi Okumura, Mamoru Komachi, Hiromasa Horiguchi, Yuji Matsumoto

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.

Extractive Summarization

Improved Decomposition Strategy for Joint Entity and Relation Extraction

no code implementations Journal of Natural Language Processing 2021 Van-Hien Tran, Van-Thuy Phi, Akihiko Kato, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto

A recent study (Yu et al. 2020) proposed a novel decomposition strategy that splits the task into two interrelated subtasks: detection of the head-entity (HE) and identification of the corresponding tail-entity and relation (TER) for each extracted head-entity.

Joint Entity and Relation Extraction

Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning

1 code implementation EACL 2021 Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, Yuji Matsumoto

Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the images.

Image Captioning image-sentence alignment

CovRelex: A COVID-19 Retrieval System with Relation Extraction

no code implementations EACL 2021 Vu Tran, Van-Hien Tran, Phuong Nguyen, Chau Nguyen, Ken Satoh, Yuji Matsumoto, Minh Nguyen

This paper presents CovRelex, a scientific paper retrieval system targeting entities and relations via relation extraction on COVID-19 scientific papers.

Relation Extraction Retrieval

Length-controllable Abstractive Summarization by Guiding with Summary Prototype

no code implementations21 Jan 2020 Itsumi Saito, Kyosuke Nishida, Kosuke Nishida, Atsushi Otsuka, Hisako Asano, Junji Tomita, Hiroyuki Shindo, Yuji Matsumoto

Unlike the previous models, our length-controllable abstractive summarization model incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings.

Abstractive Text Summarization

Gated Graph Recursive Neural Networks for Molecular Property Prediction

no code implementations31 Aug 2019 Hiroyuki Shindo, Yuji Matsumoto

Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science.

Drug Discovery Molecular Property Prediction +1

Stochastic Tokenization with a Language Model for Neural Text Classification

no code implementations ACL 2019 Tatsuya Hiraoka, Hiroyuki Shindo, Yuji Matsumoto

To make the model robust against infrequent tokens, we sampled segmentation for each sentence stochastically during training, which resulted in improved performance of text classification.

General Classification Language Modelling +3

Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models

1 code implementation ACL 2019 Takashi Wada, Tomoharu Iwata, Yuji Matsumoto

Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data.

Word Alignment Word Embeddings

Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia

no code implementations EMNLP 2020 Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, Yuji Matsumoto

The embeddings of entities in a large knowledge base (e. g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge.

Coordinate Structures in Universal Dependencies for Head-final Languages

no code implementations WS 2018 Hiroshi Kanayama, Na-Rae Han, Masayuki Asahara, Jena D. Hwang, Yusuke Miyao, Jinho D. Choi, Yuji Matsumoto

This paper discusses the representation of coordinate structures in the Universal Dependencies framework for two head-final languages, Japanese and Korean.

Reduction of Parameter Redundancy in Biaffine Classifiers with Symmetric and Circulant Weight Matrices

1 code implementation PACLIC 2018 Tomoki Matsuno, Katsuhiko Hayashi, Takahiro Ishihara, Hitoshi Manabe, Yuji Matsumoto

Currently, the biaffine classifier has been attracting attention as a method to introduce an attention mechanism into the modeling of binary relations.

Dependency Parsing

Cooperating Tools for MWE Lexicon Management and Corpus Annotation

no code implementations COLING 2018 Yuji Matsumoto, Akihiko Kato, Hiroyuki Shindo, Toshio Morita

Those two tools cooperate so that the words and multi-word expressions stored in Cradle are directly referred to by ChaKi in conducting corpus annotation, and the words and expressions annotated in ChaKi can be output as a list of lexical entities that are to be stored in Cradle.

Management POS

Dynamic Feature Selection with Attention in Incremental Parsing

no code implementations COLING 2018 Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto

One main challenge for incremental transition-based parsers, when future inputs are invisible, is to extract good features from a limited local context.

Dependency Parsing Dialogue Generation +4

Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners

no code implementations ACL 2018 Jun Liu, Hiroyuki Shindo, Yuji Matsumoto

We present a computer-assisted learning system, Jastudy, which is particularly designed for Chinese-speaking learners of Japanese as a second language (JSL) to learn Japanese functional expressions with suggestion of appropriate example sentences.


Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction

1 code implementation ACL 2018 Van-Thuy Phi, Joan Santoso, Masashi Shimbo, Yuji Matsumoto

This paper addresses the tasks of automatic seed selection for bootstrapping relation extraction, and noise reduction for distantly supervised relation extraction.

Relation Extraction Word Sense Disambiguation

A Fast and Easy Regression Technique for k-NN Classification Without Using Negative Pairs

no code implementations11 Jun 2018 Yutaro Shigeto, Masashi Shimbo, Yuji Matsumoto

This paper proposes an inexpensive way to learn an effective dissimilarity function to be used for $k$-nearest neighbor ($k$-NN) classification.

General Classification Metric Learning +1

Interpretable Adversarial Perturbation in Input Embedding Space for Text

2 code implementations8 May 2018 Motoki Sato, Jun Suzuki, Hiroyuki Shindo, Yuji Matsumoto

This paper restores interpretability to such methods by restricting the directions of perturbations toward the existing words in the input embedding space.

Segment-Level Neural Conditional Random Fields for Named Entity Recognition

no code implementations IJCNLP 2017 Motoki Sato, Hiroyuki Shindo, Ikuya Yamada, Yuji Matsumoto

We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking.

Chunking Morphological Tagging +3

Can Discourse Relations be Identified Incrementally?

no code implementations IJCNLP 2017 Frances Yung, Hiroshi Noji, Yuji Matsumoto

Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived.

Discourse Parsing Language Modelling +2

Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information

no code implementations IJCNLP 2017 An Nguyen Le, Ander Martinez, Akifumi Yoshimoto, Yuji Matsumoto

In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure.

Machine Translation Translation

Effective Online Reordering with Arc-Eager Transitions

no code implementations WS 2017 Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto

We present a new transition system with word reordering for unrestricted non-projective dependency parsing.

Transition-Based Dependency Parsing

Adversarial Training for Cross-Domain Universal Dependency Parsing

no code implementations CONLL 2017 Motoki Sato, Hitoshi Manabe, Hiroshi Noji, Yuji Matsumoto

We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique.

Dependency Parsing Domain Adaptation

Joint Prediction of Morphosyntactic Categories for Fine-Grained Arabic Part-of-Speech Tagging Exploiting Tag Dictionary Information

no code implementations CONLL 2017 Go Inoue, Hiroyuki Shindo, Yuji Matsumoto

One reason for this is that in the tagging scheme for such languages, a complete POS tag is formed by combining tags from multiple tag sets defined for each morphosyntactic category.

Multi-Task Learning Part-Of-Speech Tagging +3

Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis

no code implementations ACL 2017 Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto

The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates.

English Multiword Expression-aware Dependency Parsing Including Named Entities

no code implementations ACL 2017 Akihiko Kato, Hiroyuki Shindo, Yuji Matsumoto

Because syntactic structures and spans of multiword expressions (MWEs) are independently annotated in many English syntactic corpora, they are generally inconsistent with respect to one another, which is harmful to the implementation of an aggregate system.

Dependency Parsing

Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach

1 code implementation18 Jun 2017 Takuo Hamaguchi, Hidekazu Oiwa, Masashi Shimbo, Yuji Matsumoto

Knowledge base completion (KBC) aims to predict missing information in a knowledge base. In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time.

Knowledge Base Completion Transfer Learning

A* CCG Parsing with a Supertag and Dependency Factored Model

1 code implementation ACL 2017 Masashi Yoshikawa, Hiroshi Noji, Yuji Matsumoto

Our model achieves the state-of-the-art results on English and Japanese CCG parsing.

Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing

1 code implementation EACL 2017 Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto

Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words.

Dependency Parsing

An Algebraic Formalization of Forward and Forward-backward Algorithms

no code implementations22 Feb 2017 Ai Azuma, Masashi Shimbo, Yuji Matsumoto

back propagation) on computation graphs with addition and multiplication, and so on.

Global Pre-ordering for Improving Sublanguage Translation

no code implementations WS 2016 Masaru Fuji, Masao Utiyama, Eiichiro Sumita, Yuji Matsumoto

When translating formal documents, capturing the sentence structure specific to the sublanguage is extremely necessary to obtain high-quality translations.

Machine Translation Translation

Simplification of Example Sentences for Learners of Japanese Functional Expressions

no code implementations WS 2016 Jun Liu, Yuji Matsumoto

Learning functional expressions is one of the difficulties for language learners, since functional expressions tend to have multiple meanings and complicated usages in various situations.

Construction of an English Dependency Corpus incorporating Compound Function Words

no code implementations LREC 2016 Akihiko Kato, Hiroyuki Shindo, Yuji Matsumoto

Nevertheless, this method often leads to the following problem: A node derived from an MWE could have multiple heads and the whole dependency structure including MWE might be cyclic.

Constituency Parsing Dependency Parsing +1

Universal Dependencies for Japanese

no code implementations LREC 2016 Takaaki Tanaka, Yusuke Miyao, Masayuki Asahara, Sumire Uematsu, Hiroshi Kanayama, Shinsuke Mori, Yuji Matsumoto

We present an attempt to port the international syntactic annotation scheme, Universal Dependencies, to the Japanese language in this paper.

Dependency Parsing with LSTMs: An Empirical Evaluation

no code implementations22 Apr 2016 Adhiguna Kuncoro, Yuichiro Sawai, Kevin Duh, Yuji Matsumoto

We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units.

Dependency Parsing

Ridge Regression, Hubness, and Zero-Shot Learning

no code implementations3 Jul 2015 Yutaro Shigeto, Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto

This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space.

regression Zero-Shot Learning

Parsing Chinese Synthetic Words with a Character-based Dependency Model

no code implementations LREC 2014 Fei Cheng, Kevin Duh, Yuji Matsumoto

Synthetic word analysis is a potentially important but relatively unexplored problem in Chinese natural language processing.

Chinese Word Segmentation

Efficient Stacked Dependency Parsing by Forest Reranking

no code implementations TACL 2013 Katsuhiko Hayashi, Shuhei Kondo, Yuji Matsumoto

This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing.

Dependency Parsing

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.