fear finder
Embed Size (px)
DESCRIPTION
reverse dictionary appTRANSCRIPT

FearFinderAndroid NLP Project
Parinita & Ashley GillLing 575, CLMA, University of Washington,
Seattle
June 2nd, 2010

• Initial Proposal
• App Introduction
• NLP Techniques
• App Walk-through
• Possible Applications
2
Agenda

• 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

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

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

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

App Walk Through
7

App Walk Through
8

App Walk Through
9

App Walk Through
10

App Walk Through
11

App Walk Through
12

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

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