International Business Machines Corporation

Brian L Keith

William G Dubyak

Joshua G Hong

Charles Evan Beller

Kristen Maria Summers

Palani Sakthi

Edward Graham Katz

Nicole O'Connor

A method of retrieving information includes obtaining access to a plurality of documents comprising document terms, receiving a lexicon including a plurality of lexical terms, receiving a query, identifying a plurality of search terms in the query by decomposing the query, determining at least one match of the search terms to the lexical terms, determining a plurality of matches of the search terms to the document terms, and scoring each of the documents based on the at least one match to the lexical terms and the matches to the document terms.

Weighting of unobserved terms in a language model for information retrieval using lexical resources

Embodiments are directed to an entity extraction and filtering method that enables a close search of documents to build filters necessary for near real-time monitoring of streaming sources of information. According to an embodiment, the entity extraction and filtering method operates based on the following parameters. First, a detection of an entity of interest warrants flagging an arriving article for analyst attention. Nothing more than a match may be required. The list of entities may be derived by an entity extractor from a corpus of data. Secondly, automatic updates may be utilized, so that exports are automatically updated to the filters. Thirdly, information flowing past the filters may update a static corpus whether or not they are flagged for an analyst or user. This allows for new relationships to be detected and extracted, and the filters subsequently updated.

Leveraging extracted entity and relation data to automatically filter data streams

Embodiments are directed to an entity extraction and filtering system that enables a close search of documents to build filters necessary for near real-time monitoring of streaming sources of information. According to an embodiment, the entity extraction and filtering system operates based on the following parameters. First, a detection of an entity of interest warrants flagging an arriving article for analyst attention. Nothing more than a match may be required. The list of entities may be derived by an entity extractor from a corpus of data. Secondly, automatic updates may be utilized, so that exports are automatically updated to the filters. Thirdly, information flowing past the filters may update a static corpus whether or not they are flagged for an analyst or user. This allows for new relationships to be detected and extracted, and the filters subsequently updated.

Popular trends are predicted by leveraging the language of influencers as found in their electronic publications such as social media, blogs, etc. A list of influencers in a given field is curated along with a lexicon of the field which includes product names and associated modifiers. Natural language processing is performed on the current publications to identify a particular word combination based on syntactic relationships. The current usage frequency of the particular word combination is compared to a historical usage frequency derived from a baseline. If the current usage frequency is significantly higher, an alert is generated indicating that the particular word combination represents a candidate trend. The word combination may be a syntactic n-gram. The current usage frequency is based on a first, recent time window, and the historical usage frequency is based on a second time window preceding the first time window.

Growing community of inventors

Leesburg, VA, United States of America

Brian L Keith