🧑‍🔬 Ye Qi

🏛️ Affiliations

🎓East China University of Science and TechnologyShanghai · China2007–2025 · 19 paperscurrent🏢Huawei TechnologiesShenzhen · China2024–2025 · 2 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2018 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (2018 · 474 citations)
   Neural MT performs poorly when little parallel data is available. Pre-trained word vectors are widely used in other NLP tasks, but it was unclear when and why they help translation. The authors ran five controlled experiments on a multilingual TED talks corpus. It contains translations into English from three…
2. Hierarchical Document Refinement for Long-context Retrieval-augmented Generation (2025 · 25 citations)
   Retrieval-augmented generation (RAG) often feeds an LLM very long retrieved documents. These texts carry much irrelevant material, which raises inference cost and lowers answer quality. Existing compressors either target short chunks or rank tokens with crude signals such as perplexity, so they ignore how a document…
3. RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation (2025 · 19 citations)
   RetroLLM targets three weaknesses of standard retrieval-augmented generation (RAG): the cost of running a separate retriever, long inputs padded with redundant retrieved chunks, and the fact that retrieval and generation cannot be optimized together.

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)Ye Qi, Devendra Sachan, Matthieu Felix, et al.2018 · 474 citations
2. XNMT: The eXtensible Neural Machine Translation Toolkit ↗Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track) · no summary yetGraham Neubig et al.2018 · 87 citations
3. Hierarchical Document Refinement for Long-context Retrieval-augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Jiajie Jin, Xiaoxi Li, Guanting Dong, et al.2025 · 25 citations
4. RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoxi Li, Jiajie Jin, Yujia Zhou, et al.2025 · 19 citations

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Jiajie Jin ×2
• Xiaoxi Li ×2
• Yongkang Wu ×2
• Zhicheng Dou ×2
• Zhonghua Li ×2
• Devendra Sachan
• Graham Neubig
• Guanting Dong
• Yujia Zhou
• Yutao Zhu
• Yuyao Zhang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2025 ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2018
• Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

🔗 Cited by

Papers of our library cite their works 243 times (of the 149,439 papers whose bibliographies we read); 45 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ye-qi/