--- title: "Xiaohua Liu — author profile and papers" description: "Xiaohua Liu: 2 papers on Elamur Research (2011–2016), h-index 23 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/xiaohua-liu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiaohua-liu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiaohua Liu # Xiaohua Liu Xiaohua Liu works in natural language processing. Their papers here deal with two problems: extracting structured information from short, noisy social-media text, and making neural systems for [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) more faithful to the source. Both papers take an established model and add an explicit mechanism that fills a specific gap, such as missing context or missing memory. The most cited of these papers is [Modeling Coverage for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/tu-2016-modeling-coverage-neural-machine-translation/) (2016). It addresses over-translation and under-translation in attention-based translation, where some source words are repeated and others are skipped. The fix borrows the coverage idea from phrase-based statistical systems. A coverage vector is kept for each source position, updated at every attention step and fed back so that later attention moves toward words not yet handled. The earlier [Recognizing Named Entities in Tweets](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/) (2011) tackles entity recognition on Twitter, where taggers trained on news perform poorly and labelled examples are scarce. A nearest-neighbour classifier first gives each word a provisional label drawn from similar recent tweets. A conditional random field then uses those guesses as extra features. Both models are retrained over time on confidently labelled messages, so the system can adapt as new entities appear. Across the years these papers cover, from 2011 to 2016, the work moves from feature-based sequence labelling of social-media text to neural sequence-to-sequence translation, with attention mechanisms as the newer focus. Co-authors on these papers include [Zhaopeng Tu](https://md.research.elamur.ai/free/en/authors/zhaopeng-tu/), [Zhengdong Lu](https://md.research.elamur.ai/free/en/authors/zhengdong-lu/), [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/), [Hang Li](https://md.research.elamur.ai/free/en/authors/hang-li/), [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/) and [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/). Earlier bylines are mostly from [Microsoft Research Asia](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) and [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/). Others come from [Huawei Technologies](https://md.research.elamur.ai/free/en/companies/huawei-technologies/) and the [Université de Montréal](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/). More recent affiliations include the [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/). Xiaohua Liu has 2 papers in our library, in 2011–2016, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/), [Hang Li](https://md.research.elamur.ai/free/en/authors/hang-li/), [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/). 2 papers in our library · 2011–2016 [OpenAlex](https://openalex.org/A5100370790) · [ORCID](https://orcid.org/0000-0003-0384-5431) · [**h-index 23**](https://openalex.org/authors/A5100370790) · [151 works](https://openalex.org/works?filter=author.id:A5100370790) · [4,000 citations](https://openalex.org/works?filter=author.id:A5100370790&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/xiaohua-liu/#papers) · [🔗 350 citations in our library](https://md.research.elamur.ai/free/en/authors/xiaohua-liu/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #1616](https://md.research.elamur.ai/free/en/paper-stars/page/17/#star-1616) 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=Xiaohua+Liu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiaohua+Liu) · [dblp](https://dblp.org/search?q=Xiaohua+Liu) · [ACL Anthology](https://aclanthology.org/search/?q=Xiaohua+Liu) ## Affiliations [🏢**Microsoft Research Asia** Beijing · China 2007–2021 · 21 papers](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) · [🎓**Harbin Institute of Technology** Harbin · China 2010–2021 · 14 papers](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) · [🏢**Huawei Technologies** Shenzhen · China 2016–2018 · 5 papers](https://md.research.elamur.ai/free/en/companies/huawei-technologies/) · [🎓**Université de Montréal** Montreal · Canada 2014–2015 · 5 papers](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) · [🏢**Microsoft** Redmond · United States 2010–2015 · 4 papers](https://md.research.elamur.ai/free/en/companies/microsoft/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Machine translation (1)](https://md.research.elamur.ai/free/en/topics/machine-translation/) ## Works by year ### 2010s [**2016** 1 paper](https://md.research.elamur.ai/free/en/papers/tu-2016-modeling-coverage-neural-machine-translation/) · [**2011** 1 paper](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/) ## Papers The most cited first (OpenAlex and our library). 1. **[Modeling Coverage for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/tu-2016-modeling-coverage-neural-machine-translation/)** *(2016 · 927 citations)* Attention-based neural machine translation (NMT) does not record which source words it has already handled. 2. **[Recognizing Named Entities in Tweets](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/)** *(2011 · 435 citations)* The paper tackles named entity recognition on Twitter, where messages are short, noisy and ungrammatical. Systems built for news text break down there: Stanford NER, trained on CoNLL03, falls from 90.8% to 45.8% F1 on tweets, and annotated tweet data is scarce. The authors combine two models. First, a K-Nearest… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/) - [Hang Li](https://md.research.elamur.ai/free/en/authors/hang-li/) - [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/) - [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/) - [Zhaopeng Tu](https://md.research.elamur.ai/free/en/authors/zhaopeng-tu/) - [Zhengdong Lu](https://md.research.elamur.ai/free/en/authors/zhengdong-lu/) ## Cited by Papers of our library cite their works 350 times (of the 140,884 papers whose bibliographies we read); [25 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiaohua-liu/cited-by/).