fear finder

14
FearFinder Android NLP Project Parinita & Ashley Gill Ling 575, CLMA, University of Washington, Seattle June 2 nd , 2010

Upload: parinita-thakur-rahi

Post on 11-May-2015

910 views

Category:

Technology


1 download

DESCRIPTION

reverse dictionary app

TRANSCRIPT

Page 1: Fear finder

FearFinderAndroid NLP Project

Parinita & Ashley GillLing 575, CLMA, University of Washington,

Seattle

June 2nd, 2010

Page 2: Fear finder

• Initial Proposal

• App Introduction

• NLP Techniques

• App Walk-through

• Possible Applications

2

Agenda

Page 3: Fear finder

• Drug database – still an issue + plus drug suggestions , not a good advice to give, unless you are an MD

• For proof of concept – we chose a simpler database• On-board processing – Still holds true – loading the dictionaries can be

improved. • Attempts of accessing pre-existing DB not successful – we are using text files

Initial Proposal

3

Page 4: Fear finder

FearFinder

● A reverse dictionary that finds phobia names based on a user's input fear.

● Resources:

– A list of phobias and their meanings

– A subset of WordNet – created by getting the synonyms of the words that occur in the meaning (a Preprocessing step)

App Introduction- FearFinder

4

Page 5: Fear finder

acarophobia- itching; insects that cause itching

Synonyms • insects-dirt ball• insects-louse• insects-worm

• cause-get• cause-grounds• cause-have• cause-induce• cause-lawsuit• cause-movement• cause-reason

• itching-itchiness• itching-itching• itching-rub• itching-scabies• itching-scratch• itching-spoil• itching-urge

NLP Techniques

• cause-causal agency• cause-causal agent• cause-crusade• cause-do• cause-drive• cause-effort• cause-stimulate• cause-suit

• WordNet® is a large lexical database of English.• Nouns, verbs, adjectives and adverbs are grouped into sets of

cognitive synonyms (synsets), each expressing a distinct concept.

• Synsets are interlinked by means of conceptual-semantic and lexical relations.

5

Page 6: Fear finder

47.5 MB

• Wordnet30 –SQLite DB

• The entire Wordnet

• 47.5 MB

284 KB

• ANDROID_WN_DB

• Only words that we need

• 284 KB

176KB

• ANDROID_WN_TXT

• 176 KB +18 KB

NLP Techniques

" select synsetid, w2.lemma from sense left join word as w2 on w2.wordid=sense.wordid where sense.synsetid in"+

" ( select sense.synsetid from word as w1"+

" left join sense on w1.wordid=sense.wordid"+

" where (w1.lemma='"+defword+"' or w1.lemma='"+stem+"') )"+

" and (w2.lemma<>'"+defword+"' or w2.lemma<>'"+stem+"') group by w2.lemma having count(*)=1;");

Extracting Synonyms from WordNet Query for extracting Synonyms

6

Page 7: Fear finder

App Walk Through

7

Page 8: Fear finder

App Walk Through

8

Page 9: Fear finder

App Walk Through

9

Page 10: Fear finder

App Walk Through

10

Page 11: Fear finder

App Walk Through

11

Page 12: Fear finder

App Walk Through

12

Page 13: Fear finder

It is limited by the words that are present in the List. Look up an external site if not found..On-board Processing is not the best way.Too many condition checks hits performance.Using databases will definitely be better, but their size will still be limited.Read from text file and write into a database, instead of a dictionary ?

Issues:

13

Page 14: Fear finder

The same concept can be applied to other domains – all that needs to be changed is the resource list of words and meanings.Install list as requested ..?

DrugsMythological

Creatures

RecipesScientific Names

??

Possible Applications

14