Skip to Content
Download the full-sized PDF of Contradection - Detecting Contradictions in Text
Download the full sized image

Actions

Download  |  Analytics  |  Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

Contradection - Detecting Contradictions in Text Open Access

Language structures may come in a variety of forms, but are always received sequentially as meaning unfolds to the interpreter. Large bodies of text can create a myriad of relationships and concepts, often making it difficult to detect contradictions between elements that are far apart. This work explores the combination of deterministic and non-deterministic solutions for detecting relationships within syntactic structures, mapping those relationships, and determining if a negation in those relationships is 'decidable'. Using word vectors, one goal is to optimally map object-attribute relationships such that we may apply the Kullback-Leibler divergence to an attribute plane in the vector space. A proper divergence will allow give value to a cosine similarity function of object-attribute pairs whereby negative cosine will suggest a possible contradiction. Different parsing methods are expected to affect mapping and evaluation outcomes. The work aims to compare deterministic parsing, such as based on lexical and grammar structures, along with multinomial logistic regression in language modeling and stochastic semantic analysis for deriving relationship values; and to furthermore experiment using logical deductions to create predicate logic, through which the system may re-deduce to determine a logical coherence level. High coherence levels may be used to isolate confident relationships between objects and attributes to be compared with qualities inferred on those objects throughout the input text.

Descriptions

Author
Houssami, Rami
GW Unit
Center for Intelligent Systems Research
Date Created
2017
Type of Work
Poster
Rights
Attribution-ShareAlike 3.0 United States

Keyword
Research Days 2017
Detecting contradiction
NLP
NLU
Natural language understanding
Word vectors
Contradiction
Vector space
Identifier
Contributor
Publisher
Language
Location
Related URL
Previous Publication Information
Permanent Link
https://scholarspace.library.gwu.edu/files/2n49t179j

File Details

Depositor
Barrett Matthews
Date Uploaded
Date Modified
2017-05-02T17:27:41+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 622228
Last modified: 2017:05:02 13:27:48-04:00
Filename: Contradetcion - Rami Houssami (updated).pdf
Original checksum: 215a338db6a7b2da5a0c006b0b8d9e2d
Well formed: true
Valid: true
File title: PowerPoint Presentation
File author: ramibh4
Page count: 1
File language: en-US
Activity of users you follow
User Activity Date