Gregor Leusch

Evaluation & Benchmarks · 2000–2006

A researcher in the Science corpus: 2 papers; trusts 5 researchers and is trusted by 20 researchers here, as inferred from the citation graph.

Subfields

• Evaluation & Benchmarks — 5 citations into it; #983 of 3,147 by trust here, #2,369 by citations
• Natural Language Processing — 5 citations into it; #1,922 of 5,688 by trust here, #3,897 by citations

Whom Gregor Leusch trusts overall

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

1. Donald Ervin Knuth
2. Satanjeev Banerjee
3. Chin-Yew Lin
4. Matthew G. Snover
5. Franz Joseph Och
6. Alon Lavie
7. Christoph Tillmann
8. Bonnie J. Dorr

Who trusts Gregor Leusch overall

1. Ondrej Bojar
2. Qingsong Ma
3. M. V. Koroteev
4. Alon Lavie
5. Yvette Graham
6. Franz Joseph Och
7. Maja Popovic
8. Miloš Stanojević
9. Nicola Ueffing
10. Asli Celikyilmaz

Papers from Gregor Leusch's perspective

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

1. Bleu: a Method for Automatic Evaluation of Machine Translation
2. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments
3. ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation
4. Automatic evaluation of machine translation quality using n-gram co-occurrence statistics
5. Accelerated DP based search for statistical translation
6. A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION
7. The Stanford GraphBase - a platform for combinatorial computing
8. GloVe: Global Vectors for Word Representation
9. A personal communication
10. Minimum Error Rate Training in Statistical Machine Translation

Their papers

• An Evaluation Tool for Machine Translation: Fast Evaluation for MT Research (2000) — 355 citations
• CDER: Efficient MT Evaluation Using Block Movements (2006) — 155 citations