Tom Kocmi | DeepAI

AI Chat

Featured Co-authors

Ondřej Bojar
71 publications
Mrinmaya Sachan
61 publications
Ondřej Dušek
41 publications
Gabriel Stanovsky
36 publications
Wangchunshu Zhou
29 publications
Matt Post
27 publications
Marcin Junczys-Dowmunt
26 publications
Vilém Zouhar
17 publications
Vikas Raunak
16 publications
David Mareček
14 publications
Dominik Macháček
13 publications

∙ 09/16/2023

SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window

Reference-based metrics that operate at the sentence level typically out...

0 Vikas Raunak, et al. ∙

∙ 02/28/2023

Large Language Models Are State-of-the-Art Evaluators of Translation Quality

We describe GEMBA, a GPT-based metric for assessment of translation qual...

0 Tom Kocmi, et al. ∙

∙ 01/21/2023

Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Machine translation quality estimation (QE) predicts human judgements of...

0 Vilém Zouhar, et al. ∙

∙ 10/20/2022

Searching for a higher power in the human evaluation of MT

In MT evaluation, pairwise comparisons are conducted to identify the bet...

0 Johnny Tian-Zheng Wei, et al. ∙

∙ 02/25/2022

The Reality of Multi-Lingual Machine Translation

Our book "The Reality of Multi-Lingual Machine Translation" discusses th...

10 Tom Kocmi, et al. ∙

∙ 07/22/2021

To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation

Automatic metrics are commonly used as the exclusive tool for declaring ...

0 Tom Kocmi, et al. ∙

∙ 04/21/2021

On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

Recent studies emphasize the need of document context in human evaluatio...

0 Roman Grundkiewicz, et al. ∙

∙ 02/17/2021

THEaiTRE 1.0: Interactive generation of theatre play scripts

We present the first version of a system for interactive generation of t...

0 Rudolf Rosa, et al. ∙

∙ 10/22/2020

CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20

This paper presents a description of CUNI systems submitted to the WMT20...

0 Ivana Kvapilíková, et al. ∙

∙ 10/12/2020

Gender Coreference and Bias Evaluation at WMT 2020

Gender bias in machine translation can manifest when choosing gender inf...

0 Tom Kocmi, et al. ∙

∙ 07/06/2020

Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords

We present a new release of the Czech-English parallel corpus CzEng 2.0 ...

0 Tom Kocmi, et al. ∙

∙ 06/25/2020

THEaiTRE: Artificial Intelligence to Write a Theatre Play

We present THEaiTRE, a starting project aimed at automatic generation of...

0 Rudolf Rosa, et al. ∙

∙ 01/06/2020

Exploring Benefits of Transfer Learning in Neural Machine Translation

Neural machine translation is known to require large numbers of parallel...

17 Tom Kocmi, et al. ∙

∙ 09/24/2019

Transfer Learning across Languages from Someone Else's NMT Model

Neural machine translation is demanding in terms of training time, hardw...

0 Tom Kocmi, et al. ∙

∙ 09/02/2018

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Transfer learning has been proven as an effective technique for neural m...

0 Tom Kocmi, et al. ∙

∙ 06/18/2018

SubGram: Extending Skip-gram Word Representation with Substrings

Skip-gram (word2vec) is a recent method for creating vector representati...

0 Tom Kocmi, et al. ∙

∙ 11/24/2017

An Exploration of Word Embedding Initialization in Deep-Learning Tasks

Word embeddings are the interface between the world of discrete units of...

0 Tom Kocmi, et al. ∙

∙ 07/29/2017

Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

We examine the effects of particular orderings of sentence pairs on the ...

0 Tom Kocmi, et al. ∙

∙ 01/12/2017

LanideNN: Multilingual Language Identification on Character Window

In language identification, a common first step in natural language proc...

0 Tom Kocmi, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world