Textwise LLC

Syracuse University

Mary E McKenna

David L Snyder

Elizabeth D Liddy

Woojin Paik

Michael L Weiner

Wen Ruan

George B Osborne

Bo Yuan

Theodore G Diamond

Edmund S Yu

Ming Li

Mary Louise Howatt

Maurice J Forrester

Randall Jay Calistri-Yeh

Clinton P Mah

Bhaskaran Balakrishnan

An advertisement placement method and system for relating an advertisement to a dataset based on a trainable semantic vector (TSV) associated with the dataset and respective semantic representations of the advertisements. The trainable semantic vector associated with the dataset is generated based on at least one data point included in the dataset and known relationships between predetermined data points and predetermined categories. A comparison process is performed to determine a similarity between the trainable semantic vector associated with the dataset and the semantic representation associated with each of the plurality of advertisements. The system selectively relates one or more of the advertisements with the dataset based on a result of the comparison process. The selected advertisement or advertisements may be displayed with the dataset.

Advertisement placement method and system using semantic analysis

Techniques for generating sophisticated representations of the contents of both queries and documents in a retrieval system by using natural language processing (NLP) techniques to represent, index, and retrieve texts at the multiple levels (e.g., the morphological, lexical, syntactic, semantic, discourse, and pragmatic levels) at which humans construe meaning in writing. The user enters a query and the system processes the query to generate an alternative representation, which includes conceptual-level abstraction and representations based on complex nominals (CNs), proper nouns (PNs), single terms, text structure, and logical make-up of the query, including mandatory terms. After processing the query, the system displays query information to the user, indicating the system's interpretation and representation of the content of the query. The user is then given an opportunity to provide input, in response to which the system modifies the alternative representation of the query. Once the user has provided desired input, the possibly modified representation of the query is matched to the relevant document database, and measures of relevance generated for the documents. A set of documents is presented to the user, who is given an opportunity to select some or all of the documents, typically on the basis of such documents being of particular relevance. The user then initiates the generation of a query representation based on the alternative representations of the selected document(s).

User interface and other enhancements for natural language information

Natural language information retrieval system and method

Growing community of inventors

Syracuse, NY, United States of America

Mary E McKenna