Hiroyuki Shindo

4 paper cards in Mova's library · 2016–2017

Hiroyuki Shindo wrote 4 of the papers Mova reads, in 2016–2017, most of them on Dependency parsing, Named entity recognition, Treebanks; often with Yuji Matsumoto, Akihiko Kato, Go Inoue.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Joint Prediction of Morphosyntactic Categories for Fine-Grained Arabic Part-of-Speech Tagging Exploiting Tag Dictionary Information (2017)
A fine-grained Arabic POS tag is a conjunction of values in up to 14 morphosyntactic categories (gender, case, mood, proclitics, enclitic and others), so the number of possible tags is very large.
English Multiword Expression-aware Dependency Parsing Including Named Entities (2017)
In Penn-style treebanks, multiword expressions (MWEs) and named entities are annotated independently of the syntax, so their spans often cross the phrase structure, and dependency trees converted from them disagree with the MWE spans.
Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts (2016)
Earlier joint parsers for disfluent speech were trained and tested on human transcripts, but real input is ASR output, which adds recognition errors on top of disfluencies.
Construction of an English Dependency Corpus incorporating Compound Function Words (2016)
Penn Treebank annotation does not mark multiword expressions, and merging the nodes of a multiword unit in a word-based dependency tree can give a node with two heads or a cycle.