C
Cheng Niu
Researcher at Microsoft
Publications - 15
Citations - 536
Cheng Niu is an academic researcher from Microsoft. The author has contributed to research in topics: Supervised learning & Information extraction. The author has an hindex of 10, co-authored 15 publications receiving 526 citations.
Papers
More filters
Proceedings ArticleDOI
Location normalization for information extraction
TL;DR: A hybrid approach for location normalization which combines (i) lexical grammar driven by local context constraints, (ii) graph search for maximum spanning tree and (iii) integration of semi-automatically derived default senses is presented.
Proceedings ArticleDOI
InfoXtract location normalization: a hybrid approach to geographic references in information extraction
TL;DR: This paper presents a refined hybrid approach to geographic references using the authors' information extraction engine InfoXtract, which consists of local pattern matching and discourse co-occurrence analysis as well as default senses.
Journal ArticleDOI
Infoxtract: A customizable intermediate level information extraction engine
TL;DR: InfoXtract is described, a robust, scalable, intermediate-level IE engine that can be ported to various domains, and describes new IE tasks such as synthesis of entity profiles, and extraction of concept-based general events which represent realistic near-term goals focused on deriving useful, actionable information.
Proceedings ArticleDOI
Weakly Supervised Learning for Cross-document Person Name Disambiguation Supported by Information Extraction
TL;DR: A new algorithm using information extraction support in addition to co-occurring words for tracking person entities in a large document pool significantly outperforms the existing algorithm by 25 percentage points in overall F-measure.
Proceedings ArticleDOI
A Bootstrapping Approach to Named Entity Classification Using Successive Learners
TL;DR: A new bootstrapping approach to named entity (NE) classification that only requires a few common noun/pronoun seeds that correspond to the concept for the target NE type, e.g. he/she/man/woman for PERSON NE.