Papers by Tom Kocmi

8 papers
AI-Assisted Human Evaluation of Machine Translation (2025.naacl-long)

Copied to clipboard

Challenge: Annotation metrics are misaligned with the ideal measure of text quality and human evaluation remains the most accurate, reliable, and ultimate standard.
Approach: They propose an annotation protocol that helps annotators mark erroneous parts of the translation and assign a final score.
Outcome: The proposed protocol reduces the time per span annotation by half . the method reduces annotation budget by 25% with filtering of examples that the AI deems to be likely to be correct.
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies (2024.acl-long)

Copied to clipboard

Challenge: a decade ago a single metric, BLEU, governed progress in machine translation research.
Approach: They investigate the "dynamic range" of a number of modern machine translation metrics to provide a collective understanding of differences in scores . they use a large dataset to discover deltas at which metrics achieve system-level differences that are meaningful to humans .
Outcome: The proposed method is more stable than statistical p-values in regards to testset size.
Estimating Machine Translation Difficulty (2025.findings-emnlp)

Copied to clipboard

Challenge: Despite the high-quality outputs, it is difficult to distinguish between state-of-the-art models and identify areas for future improvement.
Approach: They propose a new metric to evaluate difficulty estimators and use it to assess both baselines and novel approaches.
Outcome: The proposed models outperform both heuristic-based methods and LLM-as-a-judge approaches, with sentinel-src achieving the best performance.
SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window (2024.naacl-short)

Copied to clipboard

Challenge: prevailing evaluation methods for machine translation metrics are at the sentence-level . but there are many linguistic phenomena that cannot be translated without context .
Approach: They propose a metric that leverages a moving window that slides over a document to feed it into a quality estimation model.
Outcome: The proposed metric obtains significantly higher pairwise system accuracy than its sentence-level baseline.
SumeCzech: Large Czech News-Based Summarization Dataset (L18-1)

Copied to clipboard

Challenge: Summarization of documents is a well-studied NLP task, but only a few datasets are available for Czech.
Approach: They propose to use a Czech news-based summarization dataset to evaluate document summarizing . they propose a language-agnostic variant of the ROUGE metric to enable automatic evaluation .
Outcome: The proposed dataset contains more than a million Czech news articles . the proposed approach is strong abstractive and language-agnostic .
Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References (2024.naacl-long)

Copied to clipboard

Challenge: Existing evaluation benchmarks with limited references may not accurately reflect the quality of the model’s hypotheses.
Approach: They propose a method to enrich evaluation benchmarks by diversifying the expression of a single reference into multiple high-quality ones to cover the semantic space of the reference sentence as much as possible.
Outcome: The proposed method can enhance evaluation benchmarks by diversifying the expression of reference into multiple high-quality ones to cover the semantic space of the reference sentence as much as possible.
Poor Man’s Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference (2023.eacl-main)

Copied to clipboard

Challenge: State-of-the-art machine translation quality estimation systems have been achieving remarkable correlations with human judgements yet they require human annotations, which are expensive and computationally heavy.
Approach: They propose a problem where one predicts automated metric scores without the reference.
Outcome: The proposed model can estimate automated metrics at the sentence-level without the reference.
Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Recent research shows that large language models (LLMs) perform poorly at segment level.
Approach: They propose a new prompting method that emulates the commonly accepted human evaluation framework . they will release their code and scripts to facilitate the community .
Outcome: The proposed method is based on the human evaluation framework MQM and produces explainable and reliable MT evaluations at both the system and segment level.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations