--- title: "Tao Lei — papers and cards" description: "Tao Lei: 2 paper cards in the Research library (2014–2017), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/tao-lei/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/tao-lei/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Tao Lei # Tao Lei 2 paper cards in the Research library · 2014–2017 Tao Lei wrote 2 of the papers Mova reads, in 2014–2017, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Regina Barzilay](https://md.research.elamur.ai/free/en/authors/regina-barzilay/), Amir Globerson, Tianxiao Shen. [OpenAlex](https://openalex.org/A5100707254) · [ORCID](https://orcid.org/0000-0002-3010-8085) · [**h-index 9**](https://openalex.org/authors/A5100707254) · [369 citations](https://openalex.org/authors/A5100707254) · [89 works](https://openalex.org/works?filter=author.id:A5100707254) — openalex-snapshot, 2026-10-14 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Tao+Lei) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Tao+Lei) · [dblp](https://dblp.org/search?q=Tao+Lei) · [ACL Anthology](https://aclanthology.org/search/?q=Tao+Lei) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Tao+Lei) Topics: [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) 1 ## Papers 1. **[Style Transfer from Non-Parallel Text by Cross-Alignment](https://md.research.elamur.ai/free/en/papers/shen-2017-style-transfer-non-parallel-text/)** *(2017)* The paper transfers style between two corpora that share one content distribution but no sentence pairs. An encoder maps a sentence, together with its style label, to a style-free latent content vector; a style-conditioned decoder renders it back. Training aligns populations rather than pairs: sentences transferred… 2. **[Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment](https://md.research.elamur.ai/free/en/papers/tacl-2014-belinkov-exploring-compositional-architectures-word-vector/)** *(2014)* PP attachment chooses which candidate head a prepositional phrase depends on. The paper scores each candidate by composing the word vectors of the head, the preposition and the child in a small neural network, trained on attachment decisions. The English data are the Penn Treebank converted to dependencies (sections… ## Co-authors (5) - [Regina Barzilay](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) ×2 - Amir Globerson - Tianxiao Shen - Tommi Jaakkola - [Yonatan Belinkov](https://md.research.elamur.ai/free/en/authors/yonatan-belinkov/) ## More papers in the library (2) Pages of the Research library: our summary, the ideas, references and who cites each. - [Structured Pruning of Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2020-structured-pruning-large-language-models/) — Ziheng Wang, Jeremy Wohlwend, Tao Lei · 2020 - [Rationalizing Neural Predictions](https://md.research.elamur.ai/free/en/papers/lei-2016-rationalizing-neural-predictions/) — Tao Lei, Regina Barzilay, Tommi Jaakkola · 2016