Daniel Licht

Artificial Intelligence · 2022–2023

A researcher in the Science corpus: 4 papers; trusts 4 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 23 citations into it
• Natural Language Processing — 15 citations into it
• Evaluation & Benchmarks — 7 citations into it

Whom Daniel Licht trusts overall

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

1. Maja Popovic

Papers from Daniel Licht's perspective

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

1. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
2. Bleu: a Method for Automatic Evaluation of Machine Translation
3. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
4. Attention is All you Need (Neural Information Processing Systems)
5. fairseq: A Fast, Extensible Toolkit for Sequence Modeling
6. BLEURT: Learning Robust Metrics for Text Generation
7. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
8. COMET: A Neural Framework for MT Evaluation
9. chrF: character n-gram F-score for automatic MT evaluation
10. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)

Their papers

• No Language Left Behind: Scaling Human-Centered Machine Translation (2022) — 1,884 citations
• Seamless: Multilingual Expressive and Streaming Speech Translation (2023) — 299 citations
• SeamlessM4T: Massively Multilingual&Multimodal Machine Translation (2023) — 202 citations
• Toxicity in Multilingual Machine Translation at Scale (2022) — 33 citations