Incremental Prediction of Sentence-final Verbs: Humans versus Machines

no code implementations • CONLL 2016 • Alvin Grissom II, Naho Orita, Jordan Boyd-Graber

Machine Translation Sentence

Predicting Japanese scrambling in the wild

no code implementations • WS 2017 • Naho Orita

Japanese speakers have a choice between canonical SOV and scrambled OSV word order to express the same meaning.

regression Sentence

Modeling Discourse Segments in Lyrics Using Repeated Patterns

no code implementations • COLING 2016 • Kento Watanabe, Yuichiroh Matsubayashi, Naho Orita, Naoaki Okazaki, Kentaro Inui, Satoru Fukayama, Tomoyasu Nakano, Jordan Smith, Masataka Goto

This study proposes a computational model of the discourse segments in lyrics to understand and to model the structure of lyrics.

regression

Toward the automatic extraction of knowledge of usable goods

no code implementations • PACLIC 2016 • Mei Uemura, Naho Orita, Naoaki Okazaki, Kentaro Inui

Natural Language Inference Question Answering

Why discourse affects speakers' choice of referring expressions

no code implementations • IJCNLP 2015 • Naho Orita, Eliana Vornov, Naomi Feldman, Hal Daum{\'e} III

Quantifying the role of discourse topicality in speakers' choices of referring expressions

no code implementations • WS 2014 • Naho Orita, Naomi Feldman, Jordan Boyd-Graber, Eliana Vornov

Topic Models

Automated Generation of Multiple-Choice Cloze Questions for Assessing English Vocabulary Using GPT-turbo 3.5

no code implementations • 4 Mar 2024 • Qiao Wang, Ralph Rose, Naho Orita, Ayaka Sugawara

The VocaTT (vocabulary teaching and training) engine is written in Python and comprises three basic steps: pre-processing target word lists, generating sentences and candidate word options using GPT, and finally selecting suitable word options.

Multiple-choice Part-Of-Speech Tagging +1