Di He
Di He has 2 papers in our library, in 2019, most of them on Machine translation, Text generation, Multilingual & cross-lingual NLP; often with Tao Qin, Tie-Yan Liu, Xu Tan.
OpenAlex · ORCID · Wikidata · h-index 14 · 29 works · 1,225 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 200 times in our library · ⭐ Paper Stars ranking: #3955
Affiliations
Concepts, shelves and topics
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 3Research subjects and languages the work is about.Text generation · 1 workMachine translation · 1 workMultilingual & cross-lingual NLP · 1 work
Works by year
2010s
Papers
- Representation Degeneration Problem in Training Natural Language Generation Models (2019 · 180 citations)
The paper identifies a flaw in neural text generators trained by maximum likelihood with weight tying, where the input embedding matrix is shared with the softmax output layer. - Multilingual Neural Machine Translation with Language Clustering (2019 · 172 citations)
Supporting thousands of languages is hard with either extreme: one translation model per language pair is too costly, and a single shared model struggles when its languages are very dissimilar.
Co-authors here
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/di-he/