using link grammar and wordnet on fact extraction for the travel domain

10
Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Upload: felicia-goodman

Post on 31-Dec-2015

23 views

Category:

Documents


0 download

DESCRIPTION

Using Link Grammar and WordNet on Fact Extraction for the Travel Domain. Problem Statement. Extract facts from English sentences Reasoning can be done on extracted facts How to extract facts? Using the connectivity feature of Link Grammar to associate relations between extracted facts - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Using Link Grammar and WordNet on Fact Extraction

for the Travel Domain

Page 2: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Problem Statement

Extract facts from English sentences Reasoning can be done on extracted facts How to extract facts?

Using the connectivity feature of Link Grammar to associate relations between extracted facts

Using WordNet to associate semantic meanings to extracted facts

Page 3: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

WordNet

What is WordNet? Developed by the Cognitive Science Laboratory

at Princeton University Synonym sets of nouns, verbs and adjectives Various semantic relations connect the synonym

sets car is_a motor vehicle breathe entails inhale present and absent are antonyms

Page 4: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

An example of is_a hierarchy airplane, aeroplane, plane --   => heavier-than-air craft

      => aircraft          => craft              => vehicle                   => conveyance, transport                        => artifact, artefact                            => object, physical object                                => entity                                    => whole, whole thing, unit                                        => object, physical object                                             => entity

Page 5: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Fact Extraction

Prerequisites: knowledge base for travel objects

plane is_a transportation ticket is_a document

knowledge base for geographic locations Input: a simple English sentence related to

the travel domain Output: facts extracted from Link Grammar

output and association with WordNet

Page 6: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Example

John took a plane from Paris to Baghdad.

actor(e1,john) parameter(e1,from,paris)

parameter(e1,to,baghdad)

place(paris) place(baghdad)

event(e1,took)

object(e1,plane)

Page 7: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Associate WordNet Sense

For object(e1,plane), the word “plane” exists in the travel object knowledge base. plane is_a transportation

Stem the word transportation => transport. For event(e1,took), do WordNet search on “took”

and parse the search result to match the word transport.

There is a match in the parsing, so associate event(e1,took) to sense 11 as event(e1,took,11).

Page 8: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Associate WordNet Sense

There is a match in the parsing, so associate event(e1,took) to sense 11 as event(e1,took,11).

Page 9: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Extracted Facts

John took a plane from Paris to Baghdad. actor(e1,john) parameter(e1,from,paris) parameter(e1,to,baghdad) place(paris) place(baghdad) object(e1,plane) event(e1,took,11)

Page 10: Using Link Grammar and WordNet on Fact Extraction for the Travel Domain

Future Work

Currently only utilizes the noun and verb parts of WordNet.

Expand current work by utilizing the adjective part of WordNet and the semantic relations.

Work on more examples to generalize the algorithm.