著者
Masashi Tsubaki Masashi Shimbo Yuji Matsumoto
出版者
一般社団法人 情報処理学会
雑誌
IPSJ Transactions on Bioinformatics (ISSN:18826679)
巻号頁・発行日
vol.10, pp.2-8, 2017 (Released:2017-01-20)
参考文献数
31
被引用文献数
3

Predicting the 3D structure of a protein from its amino acid sequence is an important challenge in bioinformatics. Since directly predicting the 3D structure is hard to achieve, classifying a protein into one of the “folds”, which are pre-defined structural labels in protein databases such as SCOP and CATH, is generally used as an intermediate step to determine the 3D structure. This classification task is called protein fold recognition (PFR), and much research has addressed the problem of either (i) feature extractions from amino acid sequences or (ii) classification methods of the protein folds. In this paper, we propose a new approach for PFR with (i) learning feature representations with unsupervised methods from a large protein database instead of manual feature selection and using external tools. (ii) learning deep neural architectures, recurrent neural networks (RNNs) with long short-term memory (LSTM) units, and re-training the representations instead of fixing the extracted features. On a benchmark dataset, our approach outperforms existing methods that use various physicochemical features.
著者
Shohei Higashiyama Masao Utiyama Eiichiro Sumita Masao Ideuchi Yoshiaki Oida Yohei Sakamoto Isaac Okada Yuji Matsumoto
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.27, no.3, pp.499-530, 2020-09-15 (Released:2020-12-15)
参考文献数
54
被引用文献数
2

Although limited effort has been devoted to exploring neural models in Japanese word segmentation, much effort has been actively applied to Chinese word segmentation because of the ability to minimize effort in feature engineering. In this work, we propose a character-based neural model that makes joint use of word information useful for disambiguating word boundaries. For each character in a sentence, our model uses an attention mechanism to estimate the importance of multiple candidate words that contain the character. Experimental results show that learning attention to proper words leads to accurate segmentations and that our model achieves better performance than existing statistical and neural models on both in-domain and cross-domain Japanese word segmentation datasets.
著者
Van-Hien Tran Hiroki Ouchi Hiroyuki Shindo Yuji Matsumoto Taro Watanabe
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.30, no.2, pp.304-329, 2023 (Released:2023-06-15)
参考文献数
52

Zero-shot relation extraction aims to recognize (new) unseen relations that cannot be observed during training. Due to this point, recognizing unseen relations with no corresponding labeled training instances is a challenging task. Recognizing an unseen relation between two entities in an input instance at the testing time, a model needs to grasp the semantic relationship between the instance and all unseen relations to make a prediction. This study argues that enhancing the semantic correlation between instances and relations is key to effectively solving the zero-shot relation extraction task. A new model entirely devoted to this goal through three main aspects was proposed: learning effective relation representation, designing purposeful mini-batches, and binding two-way semantic consistency. Experimental results on two benchmark datasets demonstrate that our approach significantly improves task performance and achieves state-of-the-art results. Our source code and data are publicly available.
著者
Keita YOKAWA Yuji MATSUMOTO Keina NAGAKITA Yoko SHINNO Kenichiro KUDO Nanami NIGUMA Kosaku SUENOBU Hideyuki YOSHIDA
出版者
The Japan Neurosurgical Society
雑誌
NMC Case Report Journal (ISSN:21884226)
巻号頁・発行日
vol.9, pp.323-328, 2022-12-31 (Released:2022-09-23)
参考文献数
21
被引用文献数
1

Leptomeningeal metastasis (LM) is a rare but devastating cancer complication. LM occurs when cancer spreads into the leptomeningeal layer or cerebrospinal fluid. Intracranial magnetic resonance (MR) images of LM are characterized by the diffuse enhancement of the leptomeninges along the cerebral sulci, cerebellar folia, and cranial nerves. Here, we report an extremely rare case of LM with an atypical MR image revealing tumor mass confinement to the arachnoid membrane. The case involves an 85-year-old man who was referred to our hospital with a three-day history of dysarthria. Radiological examination revealed a solid lesion with heterogeneous enhancement and a cystic component in the extra-axial region of the right parietal lobe. Upon subsequent general examination, multiple lung cancer metastases were suspected. The patient underwent gross total resection of the brain mass in the right parietal region. Although the tumor slightly adhered to the dura mater, it was sharply demarcated from the surrounding parenchyma and pia mater. Based on pathological examination, the tumor was diagnosed as small cell lung cancer metastasis. This metastatic brain tumor was exclusively confined to the arachnoid membrane and, except for a few blood vessels, the dura mater was not infiltrated by metastatic tumor cells. To our knowledge, this is the first reported case of LM in which the tumor mass is confined only to the arachnoid membrane. Thus, in cases with atypical MR images, a general examination considering the possibility of LM is important for prompt and accurate diagnosis.
著者
Yiran Wang Hiroyuki Shindo Yuji Matsumoto Taro Watanabe
出版者
The Association for Natural Language Processing
雑誌
自然言語処理 (ISSN:13407619)
巻号頁・発行日
vol.29, no.1, pp.23-52, 2022 (Released:2022-03-15)
参考文献数
44
被引用文献数
2

This paper presents a novel method for nested named entity recognition. As a layered method, our method extends the prior second-best path recognition method by explicitly excluding the influence of the best path. Our method maintains a set of hidden states at each time step and selectively leverages them to build a different potential function for recognition at each level. In addition, we demonstrate that recognizing innermost entities first results in better performance than the conventional outermost entities first scheme. We provide extensive experimental results on ACE2004, ACE2005, GENIA, and NNE datasets to show the effectiveness and efficiency of our proposed method.
著者
Atsushi Kawano Kansuke Fukui Yuji Matsumoto Atsushi Terada Akihiro Tominaga Nozomi Nikaido Takashi Tonozuka Kazuhide Totani Nozomu Yasutake
出版者
The Japanese Society of Applied Glycoscience
雑誌
Journal of Applied Glycoscience (ISSN:13447882)
巻号頁・発行日
pp.jag.JAG-2019_0015, (Released:2020-03-06)
被引用文献数
9

According to whole-genome sequencing, Aspergillus niger produces multiple enzymes of glycoside hydrolases (GH) 31. Here we focus on a GH31 α-glucosidase, AgdB, from A. niger. AgdB has also previously been reported as being expressed in the yeast species, Pichia pastoris; while the recombinant enzyme (rAgdB) has been shown to catalyze tranglycosylation via a complex mechanism. We constructed an expression system for A. niger AgdB using Aspergillus nidulans. To better elucidate the complicated mechanism employed by AgdB for transglucosylation, we also established a method to quantify glucosidic linkages in the transglucosylation products using 2D NMR spectroscopy. Results from the enzyme activity analysis indicated that the optimum temperature was 65 °C and optimum pH range was 6.0–7.0. Further, the NMR results showed that when maltose or maltopentaose served as the substrate, α-1,2-, α-1,3-, and small amount of α-1,1-β-linked oligosaccharides are present throughout the transglucosylation products of AgdB. These results suggest that AgdB is an α-glucosidase that serves as a transglucosylase capable of effectively producing oligosaccharides with α-1,2-, α-1,3-glucosidic linkages.
著者
Nozomi Kobayashi Kentaro Inui Yuji Matsumoto
出版者
The Japanese Society for Artificial Intelligence
雑誌
Transactions of the Japanese Society for Artificial Intelligence (ISSN:13460714)
巻号頁・発行日
vol.22, no.2, pp.227-238, 2007 (Released:2007-01-25)
参考文献数
19
被引用文献数
3 17 38

The task of opinion extraction and structurization is the key component of opinion mining, which allow Web users to retrieve and summarize people's opinions scattered over the Internet. Our aim is to develop a method for extracting opinions that represent evaluation of concumer products in a structured form. To achieve the goal, we need to consider some issues that are relevant to the extraction task: How the task of opinion extraction and structurization should be designed, and how to extract the opinions which we defined. We define an opinion unit consisting of a quadruple, that is, the opinion holder, the subject being evaluated, the part or the attribute in which it is evaluated, and the evaluation that expresses positive or negative assessment. In this task, we focus on two subtasks (a) extracting subject/aspect-evaluation relations, and (b) extracting subject/aspect-aspect relations, we approach each extraction task using a machine learning-based method. In this paper, we discuss how customer reviews in web documents can be best structured. We also report on the results of our experiments and discuss future directions.