A Hierarchical Neural Network for Information Extraction of Product Attribute and Condition Sentences

no code implementations • WS 2016 • Yukinori Homma, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka, Hisako Asano, Yoshihiro Matsuo

This paper describes a hierarchical neural network we propose for sentence classification to extract product information from product documents.

Attribute General Classification +4

Towards an Entertaining Natural Language Generation System: Linguistic Peculiarities of Japanese Fictional Characters

no code implementations • WS 2016 • Chiaki Miyazaki, Toru Hirano, Ryuichiro Higashinaka, Yoshihiro Matsuo

Text Generation

Analyzing Post-dialogue Comments by Speakers -- How Do Humans Personalize Their Utterances in Dialogue? --

no code implementations • WS 2016 • Toru Hirano, Ryuichiro Higashinaka, Yoshihiro Matsuo

Name Translation based on Fine-grained Named Entity Recognition in a Single Language

no code implementations • LREC 2016 • Kugatsu Sadamitsu, Itsumi Saito, Taichi Katayama, Hisako Asano, Yoshihiro Matsuo

We propose named entity abstraction methods with fine-grained named entity labels for improving statistical machine translation (SMT).

named-entity-recognition Named Entity Recognition +3

Discourse Relation Recognition by Comparing Various Units of Sentence Expression with Recursive Neural Network

no code implementations • PACLIC 2015 • Atsushi Otsuka, Toru Hirano, Chiaki Miyazaki, Ryo Masumura, Ryuichiro Higashinaka, Toshiro Makino, Yoshihiro Matsuo

Relation Sentence +1

Automatic conversion of sentence-end expressions for utterance characterization of dialogue systems

no code implementations • PACLIC 2015 • Chiaki Miyazaki, Toru Hirano, Ryuichiro Higashinaka, Toshiro Makino, Yoshihiro Matsuo

Sentence

Classification and Acquisition of Contradictory Event Pairs using Crowdsourcing

no code implementations • WS 2015 • Yu Takabatake, Hajime Morita, Daisuke Kawahara, Sadao Kurohashi, Ryuichiro Higashinaka, Yoshihiro Matsuo

Classification General Classification +1

Towards an open-domain conversational system fully based on natural language processing

no code implementations • COLING 2014 • Ryuichiro Higashinaka, Kenji Imamura, Toyomi Meguro, Chiaki Miyazaki, Nozomi Kobayashi, Hiroaki Sugiyama, Toru Hirano, Toshiro Makino, Yoshihiro Matsuo

Open-Domain Question Answering Task-Oriented Dialogue Systems

Learning to Generate Coherent Summary with Discriminative Hidden Semi-Markov Model

no code implementations • COLING 2014 • Hitoshi Nishikawa, Kazuho Arita, Katsumi Tanaka, Tsutomu Hirao, Toshiro Makino, Yoshihiro Matsuo

Combinatorial Optimization Document Summarization +2

Morphological Analysis for Japanese Noisy Text based on Character-level and Word-level Normalization

no code implementations • COLING 2014 • Itsumi Saito, Kugatsu Sadamitsu, Hisako Asano, Yoshihiro Matsuo

Morphological Analysis Part-Of-Speech Tagging

Constructing a Corpus of Japanese Predicate Phrases for Synonym/Antonym Relations

no code implementations • LREC 2014 • Tomoko Izumi, Tomohide Shibata, Hisako Asano, Yoshihiro Matsuo, Sadao Kurohashi

We construct a large corpus of Japanese predicate phrases for synonym-antonym relations.

Binary Classification General Classification +1

Extraction of Daily Changing Words for Question Answering

no code implementations • LREC 2014 • Kugatsu Sadamitsu, Ryuichiro Higashinaka, Yoshihiro Matsuo

This paper proposes a method for extracting Daily Changing Words (DCWs), words that indicate which questions are real-time dependent.

BIG-bench Machine Learning Question Answering +1

A Pilot Study of Readability Prediction with Reading Time

no code implementations • WS 2013 • Hitoshi Nishikawa, Toshiro Makino, Yoshihiro Matsuo

Document Summarization Information Retrieval +1

Creating an Extended Named Entity Dictionary from Wikipedia

no code implementations • COLING 2012 • Ryuichiro Higashinaka, Kugatsu Sadamitsu, Kuniko Saito, Toshiro Makino, Yoshihiro Matsuo

Text Summarization Model based on Redundancy-Constrained Knapsack Problem

no code implementations • COLING 2012 • Hitoshi Nishikawa, Tsutomu Hirao, Toshiro Makino, Yoshihiro Matsuo

Text Summarization

Entity Set Expansion using Interactive Topic Information

no code implementations • PACLIC 2012 • Kugatsu Sadamitsu, Kuniko Saito, Kenji Imamura, Yoshihiro Matsuo

Relation Extraction Topic Models

Constructing a Class-Based Lexical Dictionary using Interactive Topic Models

no code implementations • LREC 2012 • Kugatsu Sadamitsu, Kuniko Saito, Kenji Imamura, Yoshihiro Matsuo

This paper proposes a new method of constructing arbitrary class-based related word dictionaries on interactive topic models; we assume that each class is described by a topic.

Topic Models