◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Frank Keller

University of Edinburgh

12 papers hereh-index 446.8k citations164 works total

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

author position
  • middle author5
  • last author7

Across the 12 of 12 papers where every author was matched, so the position is known.

fields
  • cs.CL10
  • cs.CV2
affiliations
  • University of Edinburgh
Homepage
same name
  • Frank Keller — 17 papers, h 17
  • Frank Keller — 6 papers, h 1
  • Frank Keller — 6 papers, h 4
  • Frank Keller — 5 papers, h 1
  • Frank Keller — 4 papers, h 3
  • Frank Keller — 1 paper, h 5

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
20162021
most citedTraining object class detectors with click supervision

15 citations · 18 across the 4 of their papers we have counts for

collaborators
Showing 2019Show all

4 papers · 1 filter

cs.CL2019

Movie Plot Analysis via Turning Point Identification

Pinelopi Papalampidi, Frank Keller, Mirella Lapata

According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments within a screenplay: they define the plot structure,…

cs.CL2019★ 2 cited

An Imitation Learning Approach to Unsupervised Parsing

Bowen Li, Lili Mou, Frank Keller

Recently, there has been an increasing interest in unsupervised parsers that optimize semantically oriented objectives, typically using reinforcement learning. Unfortunately, the l…

cs.CL2019

Cross-lingual Visual Verb Sense Disambiguation

Spandana Gella, Desmond Elliott, Frank Keller

Recent work has shown that visual context improves cross-lingual sense disambiguation for nouns. We extend this line of work to the more challenging task of cross-lingual verb sens…

cs.CL2019★ 1 cited

Character-based Surprisal as a Model of Reading Difficulty in the Presence of Error

Michael Hahn, Frank Keller, Yonatan Bisk +1

Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter…

◍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.