Elamur Research⌕
☰
home / authors / Xuanli He

Xuanli He

Xuanli He has 2 papers in our library, in 2018–2025, most of them on Speech act theory, Language models & pretraining, Dialogue systems; often with Andiswa Bukula, David Ifeoluwa Adelani, En-Shiun Annie Lee.

2 papers in our library · 2018–2025

OpenAlex · h-index 13 · 62 works · 808 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 139 times in our library · 4 more in our library without a page yet · ⭐ Paper Star rank #5250

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University College LondonLondon · United Kingdom2022–2026 · 46 paperscurrent🎓Monash UniversityMelbourne · Australia2018–2023 · 17 papers🎓The University of MelbourneMelbourne · Australia2017–2022 · 5 papers🏢AmazonSeattle · United States2021–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 4 Artificial Intelligence · 2 works Arts and Humanities · 2 works Computer Science · 2 works Language and Linguistics · 2 works

🧭 Topics 5 Evaluation & benchmarks · 1 work Language models & pretraining · 1 work Dialogue systems · 1 work Speech & spoken language · 1 work Speech act theory · 1 work

 Works by year

2020s

20251 paperIrokoBench: A New Benchmark for African Languages in the Age of Large Language Models

2010s

20181 paperExploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation

 Papers

The most cited first (OpenAlex and our library).

  1. IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models (2025 · 69 citations)
    Large language models are usually tested in English and a few other well-resourced languages. When African languages are tested at all, it is mostly on simple classification, so we know little about how well models reason or recall knowledge in them. The authors built IrokoBench to fill this gap. Professional…
  2. Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation (2018 · 3 citations)
    Dialogue Act (DA) classification usually assumes human (oracle) transcripts. A real spoken dialogue system only has noisy ASR output, and it also meets speakers it never heard in training. The authors build an online multimodal DA tagger. A CNN over MFCC frames feeds a speech LSTM, a word-embedding LSTM encodes the…

All works

6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. IrokoBench: A New Benchmark for African Languages in the Age of Large Language ModelsDavid Ifeoluwa Adelani, Jessica Ojo, Israel Abebe Azime, et al.Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) · 69 citations
  2. Generate, Annotate, and Learn: NLP with Synthetic Text · original ↗ · no summary yet · Transactions of the Association for Computational LinguisticsXuanli He et al.2022 · 68 citations
  3. AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages · original ↗ · no summary yet · Proceedings of the 2024 Conference of the North American Chapter of the…Jiayi Wang et al.2024 · 39 citations
  4. Rethinking Round-Trip Translation for Machine Translation Evaluation · original ↗ · no summary yet · Findings of the Association for Computational Linguistics: ACL 2023Terry Yue Zhuo et al.2023 · 20 citations
  5. Can Knowledge Graphs Simplify Text? · original ↗ · no summary yet · arXiv:2308.06975Anthony Colas et al.2023 · 8 citations
  6. Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain AdaptationXuanli He, Quan Tran, William Havard, et al.Annual Workshop of the Australasian Language Technology Association (ALTA) · 3 citations

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 139 times (of the 141,840 papers whose bibliographies we read); 15 citing papers with a page here →.

Updated

↑ back to top

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