◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Taro Watanabe

NAIST

16 papers hereh-index 262.1k citations122 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author7
  • last author9

Across the 16 of 16 papers where every author was matched, so the position is known.

fields
  • cs.CL14
  • cs.CV1
  • cs.LG1
affiliations
  • NAIST
Homepage
same name
  • Taro Watanabe — 62 papers, h 10
  • Taro Watanabe — 9 papers, h 4
  • Taro Watanabe — 7 papers, h 3
  • Taro Watanabe — 4 papers, h 3
  • Taro Watanabe — 2 papers, h 1
  • Taro Watanabe — 1 paper

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20182024
most citedArukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation

2 citations · 8 across the 15 of their papers we have counts for

collaborators
Showing 2021Show all

3 papers · 1 filter

cs.LG2021

Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding

Yushi Hirose, Masashi Shimbo, Taro Watanabe

For knowledge graph completion, two major types of prediction models exist: one based on graph embeddings, and the other based on relation path rule induction. They have different…

cs.CL2021★ 1 cited

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

Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto +2

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…

cs.CL2021

User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization

Shohei Higashiyama, Masao Utiyama, Taro Watanabe +1

Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.