◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Tom Kocmi

Microsoft, Germany

27 papers hereh-index 243.8k citations58 works total

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

author position
  • sole author1
  • first author15
  • middle author10
  • last author1

Across the 27 of 27 papers where every author was matched, so the position is known.

fields
  • cs.CL26
  • stat.AP1
affiliations
  • Microsoft, Germany
same name
  • Tom Kocmi — 11 papers, h 8

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
20172026
most citedCurriculum Learning and Minibatch Bucketing in Neural Machine Translation

124 citations · 446 across the 25 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

cs.CL2018★ 43 cited

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Tom Kocmi, Ondřej Bojar

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, languag…

cs.CL2018★ 5 cited

SubGram: Extending Skip-gram Word Representation with Substrings

Tom Kocmi, Ondřej Bojar

Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained populari…

◍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.