T. Glushkova

Artificial Intelligence · 2022

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 18 citations into it
• Evaluation & Benchmarks — 16 citations into it
• Natural Language Processing — 14 citations into it

Whom T. Glushkova trusts

Their strongest outbound trust, strongest first, inferred from their citations.

1. Ondrej Bojar (in Evaluation & Benchmarks)
2. Chi-kiu (羅致翹) Lo (in Evaluation & Benchmarks)
3. Maja Popovic (in Artificial Intelligence)

Papers from T. Glushkova's perspective

Ordered by how strongly the researchers T. Glushkova trusts endorse each paper. Same corpus, a different order for every researcher.

1. Bleu: a Method for Automatic Evaluation of Machine Translation
2. Results of the WMT17 Metrics Shared Task
3. BLEURT: Learning Robust Metrics for Text Generation
4. Results of the WMT18 Metrics Shared Task: Both characters and embeddings achieve good performance
5. COMET: A Neural Framework for MT Evaluation
6. BERTScore: Evaluating Text Generation with BERT
7. Results of the WMT20 Metrics Shared Task
8. chrF: character n-gram F-score for automatic MT evaluation
9. Continuous Measurement Scales in Human Evaluation of Machine Translation
10. Rethinking embedding coupling in pre-trained language models

Their papers

• COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task (2022) — 503 citations