scispace - formally typeset
Patent

Method for computerized information retrieval using shallow linguistic analysis

Julian M. Kupiec
TLDR
In this paper, a computerized method for retrieving documents from a text corpus in response to a user-supplied natural language input string, e.g., a question, is presented.
Abstract: 
A computerized method for retrieving documents from a text corpus in response to a user-supplied natural language input string, e.g., a question. An input string is accepted and analyzed to detect phrases therein. A series of queries based on the detected phrases is automatically constructed through a sequence of successive broadening and narrowing operations designed to generate an optimal query or queries. The queries of the series are executed to retrieve documents, which are then ranked and made available for output to the user, a storage device, or further processing. In another aspect the method is implemented in the context of a larger two-phase method, of which the first phase comprises the method of the invention and the second phase of the method comprises answer extraction.

read more

Citations
More filters
Patent

Intelligent Automated Assistant

Thomas R. Gruber, +7 more
TL;DR: In this article, an intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions.
Patent

Computer system with user-controlled relevance ranking of search results

Sangam Pant, +4 more
TL;DR: A computer system for performing searches on a collection of information includes a mechanism through which results from a search query are ranked according to user specified relevance factors to allow the user to control how the search results are presented.
Patent

Natural language information retrieval system and method

Elizabeth D. Liddy, +3 more
TL;DR: In this article, 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.
Patent

Using context information to facilitate processing of commands in a virtual assistant

Thomas R. Gruber, +4 more
TL;DR: In this article, a virtual assistant uses context information to supplement natural language or gestural input from a user, which helps to clarify the user's intent and reduce the number of candidate interpretations of user's input, and reduces the need for the user to provide excessive clarification input.
Patent

Full text query and search systems and methods of use

Yuanhua Tang, +2 more
TL;DR: The Shannon Information score as discussed by the authors is a ranking system that uses p-values to represent the likelihood that a hit is due to random matches, and users can specify the parameters that determine hits and their ranking based on phrase matches and sentence similarities.
References
More filters
Proceedings ArticleDOI

Automatic acquisition of hyponyms from large text corpora

Marti A. Hearst
TL;DR: A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.

Five papers on Wordnet

George A. Miller
Patent

An iterative technique for phrase query formation and an information retrieval system employing same

Jan O Pedersen, +5 more
TL;DR: In this paper, an information retrieval system and method are provided in which an operator inputs one or more query words which are used to determine a search key for searching through a corpus of documents, and which returns any matches between the search key and the corpora of documents as a phrase containing the word data matching the query word(s), a non-stop (content) word next adjacent to the matching word data, and all intervening stop-words between the matching data and the next adjacent nonstop word.
Journal ArticleDOI

Robust part-of-speech tagging using a hidden Markov model

Julian M. Kupiec
- 01 Jul 1992 - 
TL;DR: A system for part-of-speech tagging is described, based on a hidden Markov model which can be trained using a corpus of untagged text, which results in a model that correctly tags approximately 96% of the text.
Patent

Database retrieval system having a natural language interface

Steven Shwartz, +4 more
TL;DR: In this paper, an expert system accesses structural and semantic description information in the knowledge base and, in accordance with predefined rules, identifies database elements from said information that are necessary to satisfy the query represented by the internal meaning representation.