Search and information retrieval
Project
SffinX: Satori Free-text Facet Ingestion with Nlp eXtraction
=> Mar 2014 : Dec 2015 … SffinX aimed to extract millions of entities, relations and facts from web pages free text for a specific domain, then, mapping them to Satori ontology (MSO). SffinX targeted low…
Project
Named Entity Recognition
=> Jan 2013 : Mar 2014 … In collaboration with Microsoft Office team, we have built a Named Entity Recognition framework out of Wikipedia text. The framework was able to auto-label Wikipedia pages in 3…
Publication
Query-biased summaries for tabular data
Publication
Tightly Coupling Search and Structure
Project
Renlifang/EntityCube
EntityCube is a research prototype and is a test bed for exploring entity mining and search technologies, which automatically summarizes the Web for entities (such as people, locations and organizations) with a substantial presence. The…
Tool
Microsoft Research Sequential Question Answering (SQA) Dataset
Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans. In an effort to explore…