1 ai@azusa pacific university sheldon liang, ph d computer science department
TRANSCRIPT
1
AI@Azusa Pacific University
Sheldon Liang, Ph DComputer Science Department
2
AI@Azusa Pacific University
Sense, Communicate, Actuate
3
Natural? Natural?
Natural Language? Refers to the language spoken by people, e.g. English,
Chinese, Swahili, as opposed to artificial languages, like C++, Java, etc.
Natural Language Processing Applications that deal with natural language in a way
or another and it is the subfield of Artificial Intelligence
Computational Linguistics Doing linguistics on computers More on the linguistic side than NLP, but closely related
Natural Language? Refers to the language spoken by people, e.g. English,
Chinese, Swahili, as opposed to artificial languages, like C++, Java, etc.
Natural Language Processing Applications that deal with natural language in a way
or another and it is the subfield of Artificial Intelligence
Computational Linguistics Doing linguistics on computers More on the linguistic side than NLP, but closely related
AI@Azusa Pacific University
4
What is Artificial Intelligence?What is Artificial Intelligence?
The use of computer programs and programming techniques to cast light on the principles of intelligence in general and human thought in particular (Boden)
AI is the study of how to do things which at the moment people do better (Rich & Knight)
AI is the science of making machines do things that would require intelligence if done by men. (Minsky)
The use of computer programs and programming techniques to cast light on the principles of intelligence in general and human thought in particular (Boden)
AI is the study of how to do things which at the moment people do better (Rich & Knight)
AI is the science of making machines do things that would require intelligence if done by men. (Minsky)
AI@Azusa Pacific University
5
Why Natural Language Processing?Why Natural Language Processing?
kJfmmfj mmmvvv nnnffn333 Uj iheale eleee mnster vensi credur Baboi oi cestnitze Coovoel2^ ekk; ldsllk lkdf vnnjfj? Fgmflmllk mlfm kfre xnnn!
kJfmmfj mmmvvv nnnffn333 Uj iheale eleee mnster vensi credur Baboi oi cestnitze Coovoel2^ ekk; ldsllk lkdf vnnjfj? Fgmflmllk mlfm kfre xnnn!
AI@Azusa Pacific University
6
Computers Lack Knowledge!Computers Lack Knowledge!
Computers “see” text in English the same you have seen the previous text!
People have no trouble understanding language Common sense knowledge Reasoning capacity Experience
Computers have No common sense knowledge No reasoning capacity
Unless we teach them!
Computers “see” text in English the same you have seen the previous text!
People have no trouble understanding language Common sense knowledge Reasoning capacity Experience
Computers have No common sense knowledge No reasoning capacity
Unless we teach them!
AI@Azusa Pacific University
7
Why Natural Language Processing?Why Natural Language Processing?
Huge amounts of data Internet = at least 8
billion pagesIntranet
Applications for processing large amounts of texts
Require NLP expertise
Huge amounts of data Internet = at least 8
billion pagesIntranet
Applications for processing large amounts of texts
Require NLP expertise
Classify text into categories Index and search large texts Automatic translation Speech understanding
Understand phone conversations Information extraction
Extract useful information from resumes
Automatic summarization Condense 1 book into 1 page
Question answering Knowledge acquisition Text generations / dialogs
Classify text into categories Index and search large texts Automatic translation Speech understanding
Understand phone conversations Information extraction
Extract useful information from resumes
Automatic summarization Condense 1 book into 1 page
Question answering Knowledge acquisition Text generations / dialogs
AI@Azusa Pacific University
8
Where does it fit in the CS taxonomy?Where does it fit in the CS taxonomy?
Computers & Applications
Artificial Intelligence AlgorithmsDatabases Networking
Robotics SearchNatural Language Processing
InformationRetrieval
Machine Translation
Language Analysis
Semantics Parsing
AI@Azusa Pacific University
9
Situating NLPSituating NLP
computer science
psychology/cognitive science
linguistics
math/statistics
philosophy
communication
NLP
AI@Azusa Pacific University
10
Theoretical foundationsmath: statistics, calculus, algebra,
modelingcomputational paradigms: connectionist,
rule-based, cognitively plausiblelinguistics: LFG, HPSG, GB, OT, CG, etc.architectures: stacks, automata,
networks, compilers
AI@Azusa Pacific University
11
Some areas of researchSome areas of research
Corpora, tools, resources, standards Language/grammar engineering Machine (assisted) translation, tools Language modeling Lexicography Speech
Corpora, tools, resources, standards Language/grammar engineering Machine (assisted) translation, tools Language modeling Lexicography Speech
AI@Azusa Pacific University
12
Linguistics Essentials
AI@Azusa Pacific University
13
The Description of Language Language = Words and Rules Dictionary (vocabulary) + Grammar Dictionary set of words defined in the language open (dynamic) Traditional paper based Electronic machine readable dictionaries; can be obtained from paper-based Grammar set of rules which describe what is allowable in a language Classic Grammars meant for humans who know the language definitions and rules are mainly supported by examples no (or almost no) formal description tools; cannot be programmed Explicit Grammar (CFG, Dependency Grammars, Link Grammars,...) formal description can be programmed & tested on data (texts)
AI@Azusa Pacific University
14
Linguistics Levels of AnalysisLinguistics Levels of Analysis
SpeechWritten language
Phonology: sounds / letters / pronunciationMorphology: the structure of wordsSyntax: how these sequences are structuredSemantics: meaning of the strings
Interaction between levels where each level has an input and an output.
SpeechWritten language
Phonology: sounds / letters / pronunciationMorphology: the structure of wordsSyntax: how these sequences are structuredSemantics: meaning of the strings
Interaction between levels where each level has an input and an output.
AI@Azusa Pacific University
15
Phonetics/OrthographyInput:
acoustic signal (phonetics) / text (orthography) Output:
phonetic alphabet (phonetics) / text (orthography)
Deals with:Phonetics:
consonant & vowel (& others) formation in the vocal tract
classification of consonants, vowels, ... in relation to frequencies, shape & position of the tongue and various muscles
intonation Orthography: normalization, punctuation, etc.
AI@Azusa Pacific University
16
Phonology -- pronunciation
Input: sequence of phones/sounds (in a phonetic alphabet); or
“normalized” text (sequence of (surface) letters in one language’s alphabet) [NB: phones vs. phonemes]
Output: sequence of phonemes (~ (lexical) letters; in an
abstract alphabet) Deals with:
relation between sounds and phonemes (units which might have some function on the upper level)
e.g.: [u] ~ oo (as in book), [æ] ~ a (cat); i ~ y (flies)
AI@Azusa Pacific University
17
Morphology -- the structure of words Input: sequence of phonemes (~ (lexical) letters)
Output:sequence of pairs (lemma, (morphological) tag)
Deals with:composition of phonemes into word forms and
their underlying lemmas (lexical units) + morphological categories (inflection, derivation, compounding)
e.g. quotations ~ quote/V + -ation(der.V->N) + NNS.
AI@Azusa Pacific University
18
...and Beyond Input:
sentence structure (tree): annotated nodes (autosemantic lemmas, (morphosyntactic) tags, deep functions)
Output:logical form, which can be evaluated (true/false)
Deals with:assignment of objects from the real world to the
nodes of the sentence structuree.g.: (I/Sg/Pat/t (see/Perf/Pred/t) Tom/Sg/Ag/f) ~
see(Mark-Twain[SSN:...],Tom-Sawyer[SSN:...])
AI@Azusa Pacific University
19
Phonology
(Surface Lexical) Correspondence “symbol-based” (no complex structures) Ex.: (stem-final change)
lexical: b a b y + s (+ denotes start of ending) surface: b a b i e s (phonetic-related: bb0s)
Arabic: (interfixing, inside-stem doubling) lexical: kTb+uu+CVCCVC (CVCC...vowel/consonant
pattern) surface: kuttub
AI@Azusa Pacific University
20
Phonology Examples
German (umlaut) (satz ~ sentence) lexical: s A t z + e (A denotes “umlautable” a) surface: s ä t z e (phonetic: zæc, vs. zac)
Turkish (vowel harmony) lexical: e v + l A r (~house) surface: e v l e r
AI@Azusa Pacific University
21
Morphology: Morphemes & Order
Scientific study of forms of words Grouping of phonemes into morphemes
sequence deliverables deliver, able and s (3 units)
could as well be some “ID” numbers: e.g. deliver ~ 23987, s ~ 12, able ~ 3456
Morpheme Combination certain combinations/sequencing possible, other
not:deliver+able+s, but not able+derive+s; noun+s,
but not noun+ingtypically fixed (in any given language)
AI@Azusa Pacific University
22
The Dictionary (or Lexicon)
Repository of information about words:Morphological:
description of morphological “behavior”: inflection patterns/classes
Syntactic:Part of Speechrelations to other words:
subcategorization (or “surface valency frames”)Semantic:
semantic featuresframes
...and any other! (e.g., translation)
AI@Azusa Pacific University
23
AI@Azusa Pacific University
Sense, Communicate, Actuate
24
(Surface) Syntax Input:
sequence of pairs (lemma, (morphological) tag)
Output: sentence structure (tree) with annotated nodes (all
lemmas, (morphosyntactic) tags, functions), of various forms
Deals with: the relation between lemmas & morphological categories
and the sentence structure uses syntactic categories such as Subject, Verb, Object,... e.g.: I/PP1 see/VB a/DT dog/NN ~ ((I/sg)SB ((see/pres)V (a/ind
dog/sg)OBJ)VP)S
AI@Azusa Pacific University
25
Issues in SyntaxIssues in Syntax
“the dog ate my homework” - Who did what?
1. Identify the part of speech (POS)Dog = noun ; ate = verb ; homework = nounEnglish POS tagging: 95%Can be improved! Part of speech tagging on other languages almost
inexistent
2. Identify collocations
mother in law, hot dog
Compositional versus non-compositional collocates
“the dog ate my homework” - Who did what?
1. Identify the part of speech (POS)Dog = noun ; ate = verb ; homework = nounEnglish POS tagging: 95%Can be improved! Part of speech tagging on other languages almost
inexistent
2. Identify collocations
mother in law, hot dog
Compositional versus non-compositional collocates
AI@Azusa Pacific University
26
Issues in SyntaxIssues in Syntax
Shallow parsing:“the dog chased the bear”“the dog” “chased the bear”subject - predicateIdentify basic structuresNP-[the dog] VP-[chased the bear]Shallow parsing on new languagesShallow parsing with little training
data
Shallow parsing:“the dog chased the bear”“the dog” “chased the bear”subject - predicateIdentify basic structuresNP-[the dog] VP-[chased the bear]Shallow parsing on new languagesShallow parsing with little training
data
AI@Azusa Pacific University
27
Issues in SyntaxIssues in SyntaxFull parsing: John loves MaryFull parsing: John loves Mary
Current precisions: 85-88%
Help figuring out (automatically) questions like: Who did what and when?
AI@Azusa Pacific University
28
Meaning (semantics) Input:
sentence structure (tree) with annotated nodes (lemmas, (morphosyntactic) tags, surface functions)
Output: sentence structure (tree) with annotated nodes (semantic
lemmas, (morpho-syntactic) tags, deep functions)
Deals with: relation between categories such as “Subject”, “Object”
and (deep) categories such as “Agent”, “Effect”; adds other cat’s
e.g. ((I)SB ((was seen)V (by Tom)OBJ)VP)S ~ (I/Sg/Pat/t (see/Perf/Pred/t) Tom/Sg/Ag/f)
AI@Azusa Pacific University
29
Issues in SemanticsIssues in Semantics
Understand language! How?“plant” = industrial plant“plant” = living organism
Words are ambiguousImportance of semantics?
Machine Translation: wrong translationsInformation Retrieval: wrong informationAnaphora Resolution: wrong referents
Understand language! How?“plant” = industrial plant“plant” = living organism
Words are ambiguousImportance of semantics?
Machine Translation: wrong translationsInformation Retrieval: wrong informationAnaphora Resolution: wrong referents
AI@Azusa Pacific University
30
The sea is at the home for billions of factories and animalsThe sea is home to million of plants and
animalsEnglish French [commercial MT
system]Le mer est a la maison de billion des
usines et des animauxFrench English
The sea is at the home for billions of factories and animalsThe sea is home to million of plants and
animalsEnglish French [commercial MT
system]Le mer est a la maison de billion des
usines et des animauxFrench English
Why Semantics?Why Semantics?
AI@Azusa Pacific University
31
Issues in SemanticsIssues in Semantics
How to learn the meaning of words? From dictionaries:
plant, works, industrial plant -- (buildings for carrying on industrial labor; "they built a large plant to manufacture automobiles")plant, flora, plant life -- (a living organism lacking the power of locomotion)
They are producing about 1,000 automobiles in the new plant
The sea flora consists in 1,000 different plant speciesThe plant was close to the farm of animals.
How to learn the meaning of words? From dictionaries:
plant, works, industrial plant -- (buildings for carrying on industrial labor; "they built a large plant to manufacture automobiles")plant, flora, plant life -- (a living organism lacking the power of locomotion)
They are producing about 1,000 automobiles in the new plant
The sea flora consists in 1,000 different plant speciesThe plant was close to the farm of animals.
AI@Azusa Pacific University
32
Issues in SemanticsIssues in Semantics
Learn from annotated examples:Assume 100 examples containing “plant”
previously tagged by a humanTrain a learning algorithmPrecisions in the range 60%-70%-(80%)How to choose the learning algorithm?How to obtain the 100 tagged examples?
Learn from annotated examples:Assume 100 examples containing “plant”
previously tagged by a humanTrain a learning algorithmPrecisions in the range 60%-70%-(80%)How to choose the learning algorithm?How to obtain the 100 tagged examples?
AI@Azusa Pacific University
33
Issues in Learning SemanticsIssues in Learning SemanticsLearning?
Assume a (large) amount of annotated data = training
Assume a new text not annotated = testLearn from previous experience (training) to
classify new data (test)Decision trees, memory based learning,
neural networksMachine Learning
Which one performs best?
Learning?Assume a (large) amount of annotated data =
trainingAssume a new text not annotated = test
Learn from previous experience (training) to classify new data (test)
Decision trees, memory based learning, neural networksMachine Learning
Which one performs best?
AI@Azusa Pacific University
34
Issues in SemanticsIssues in Semantics
Automatic annotation of dataActive learning
Identify only the hard examples
Co-trainingIdentify the examples where several techniques
agree on the semantic tag
Collecting from Web usersOpen Mind Word Expert
Automatic annotation of dataActive learning
Identify only the hard examples
Co-trainingIdentify the examples where several techniques
agree on the semantic tag
Collecting from Web usersOpen Mind Word Expert
AI@Azusa Pacific University
35
Problems faced by Natural Language-Understanding
Systems
AI@Azusa Pacific University
36
Key NLP problem: ambiguityKey NLP problem: ambiguity
AI@Azusa Pacific University
Human Language is highly ambiguous at all levels
• acoustic levelrecognize speech vs. wreck a nice beach
• morphological levelsaw: to see (past), saw (noun), to saw (present, inf)
• syntactic levelI saw the man on the hill with a telescope
• semantic levelOne book has to be read by every student
37
Key NLP problem: AmbiguityKey NLP problem: Ambiguity
AI@Azusa Pacific University
Human Language is highly ambiguous at all levels
• acoustic levelrecognize speech vs. wreck a nice beach
• morphological levelsaw: to see (past), saw (noun), to saw (present, inf)
• syntactic levelI saw the man on the hill with a telescope
• semantic levelOne book has to be read by every student
38
Language ModelLanguage Model
AI@Azusa Pacific University
A formal model about languageTwo types
Non-probabilisticAllows one to compute whether a certain
sequence (sentence or part thereof) is possible
Often grammar based Probabilistic
Allows one to compute the probability of a certain sequence
Often extends grammars with probabilities
A formal model about languageTwo types
Non-probabilisticAllows one to compute whether a certain
sequence (sentence or part thereof) is possible
Often grammar based Probabilistic
Allows one to compute the probability of a certain sequence
Often extends grammars with probabilities
39
Example of Bad Language ModelExample of Bad Language Model
AI@Azusa Pacific University
40
Example of Bad Language ModelExample of Bad Language Model
AI@Azusa Pacific University
41
Example of Bad Language ModelExample of Bad Language Model
AI@Azusa Pacific University
42
A Good Language ModelA Good Language Model
AI@Azusa Pacific University
Non-Probabilistic“I swear to tell the truth” is possible“I swerve to smell de soup” is
impossibleProbabilistic
P(I swear to tell the truth) ~ .0001P(I swerve to smell de soup) ~ 0
Non-Probabilistic“I swear to tell the truth” is possible“I swerve to smell de soup” is
impossibleProbabilistic
P(I swear to tell the truth) ~ .0001P(I swerve to smell de soup) ~ 0
43
Language Model ApplicationLanguage Model Application
AI@Azusa Pacific University
Spelling correctionMobile phone textingSpeech recognitionHandwriting recognitionDisabled users…
Spelling correctionMobile phone textingSpeech recognitionHandwriting recognitionDisabled users…
44
Speech & Text segmentationSpeech & Text segmentation
In spoken language, sounds representing succesive letters blend into each other
This makes the conversion of the analog signal to discrete characters very difficult
Regarding Text Segmentation , Some written languages like chinese, japanese and thai don’t have signal word boundaries.
So any significant text parsing requires identifying word boundaries, which is often a non-trivial tasks
In spoken language, sounds representing succesive letters blend into each other
This makes the conversion of the analog signal to discrete characters very difficult
Regarding Text Segmentation , Some written languages like chinese, japanese and thai don’t have signal word boundaries.
So any significant text parsing requires identifying word boundaries, which is often a non-trivial tasks
AI@Azusa Pacific University
45
Word sense disambiguationWord sense disambiguation
Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory usually comes from a dictionary or
thesaurus. Knowledge intensive methods, supervised learning,
and (sometimes) bootstrapping approaches Word sense discrimination is the problem of dividing the
usages of a word into different meanings, without regard to any particular existing sense inventory. Unsupervised techniques
Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory usually comes from a dictionary or
thesaurus. Knowledge intensive methods, supervised learning,
and (sometimes) bootstrapping approaches Word sense discrimination is the problem of dividing the
usages of a word into different meanings, without regard to any particular existing sense inventory. Unsupervised techniques
AI@Azusa Pacific University
46
Word sense disambiguationComputers versus HumansWord sense disambiguationComputers versus Humans
Polysemy – most words have many possible meanings.
A computer program has no basis for knowing which one is appropriate, even if it is obvious to a human…
Ambiguity is rarely a problem for humans in their day to day communication, except in extreme cases…
Polysemy – most words have many possible meanings.
A computer program has no basis for knowing which one is appropriate, even if it is obvious to a human…
Ambiguity is rarely a problem for humans in their day to day communication, except in extreme cases…
AI@Azusa Pacific University
47
Word sense disambiguationAmbiguity for a Computer Word sense disambiguationAmbiguity for a Computer
The fisherman jumped off the bank and into the water.
The bank down the street was robbed! Back in the day, we had an entire bank of
computers devoted to this problem. The bank in that road is entirely too steep and is
really dangerous. The plane took a bank to the left, and then
headed off towards the mountains.
The fisherman jumped off the bank and into the water.
The bank down the street was robbed! Back in the day, we had an entire bank of
computers devoted to this problem. The bank in that road is entirely too steep and is
really dangerous. The plane took a bank to the left, and then
headed off towards the mountains.
AI@Azusa Pacific University
48
Syntactic ambiguitySyntactic ambiguity
There are often multiple possible parse trees for a given sentence.
Choosing the most appropriate one usually requires semantic and contextual information.
Specific problem components here are:1. Sentence boundary disambiguation
2. Imperfect input
3. Foreign or regional accents etc.
There are often multiple possible parse trees for a given sentence.
Choosing the most appropriate one usually requires semantic and contextual information.
Specific problem components here are:1. Sentence boundary disambiguation
2. Imperfect input
3. Foreign or regional accents etc.
AI@Azusa Pacific University
49
Syntactic ambiguitySyntactic ambiguity
AI@Azusa Pacific University
50
Statistical NLPStatistical NLP
Statistical NLP uses stochastic, probabilistic and statistical methods to resolve some difficulties of NLP
Methods for disambiguation of an involve the use of corpora & Markov models.
Technology for statistical NLP comes from machine learning and data mining both of which involve learning from data.
Statistical NLP uses stochastic, probabilistic and statistical methods to resolve some difficulties of NLP
Methods for disambiguation of an involve the use of corpora & Markov models.
Technology for statistical NLP comes from machine learning and data mining both of which involve learning from data.
AI@Azusa Pacific University
51
Statistical NLP -- CorpusStatistical NLP -- Corpus
AI@Azusa Pacific University
Corpus: text collection for linguistic purposes
TokensHow many words are contained in Tom Sawyer? 71.370
TypesHow many different words are contained in T.S.? 8.018
Hapax Legomenawords appearing only once
52
Statistical NLP – Word CountsStatistical NLP – Word Counts
AI@Azusa Pacific University
The most frequent words are function words
word freq word freq
the 3332 in 906
and 2972 that 877
a 1775 he 877
to 1725 I 783
of 1440 his 772
was 1161 you 686
it 1027 Tom 679
53
Major Tasks in NLPMajor Tasks in NLP
Speech RecognitionNatural Language GenerationMachine Translation Information Retrieval Information ExtractionText SimplificationAutomatic summarizationForeign Language Reading & writing aid
Speech RecognitionNatural Language GenerationMachine Translation Information Retrieval Information ExtractionText SimplificationAutomatic summarizationForeign Language Reading & writing aid
AI@Azusa Pacific University
54
Speech RecognitionSpeech Recognition
It is the process of converting a speech signal to a sequence of words, by means of an algorithm (as computer program).
Applications are :1. Voice dialing 2. Call routing 3. Simple data entry 4. Preparation of structure documents
It is the process of converting a speech signal to a sequence of words, by means of an algorithm (as computer program).
Applications are :1. Voice dialing 2. Call routing 3. Simple data entry 4. Preparation of structure documents
AI@Azusa Pacific University
55
Natural Language generationNatural Language generation It is a task of generating Natural Language from a
machine representation system such as a knowledge base or a logical form.
Ex: Choose randomly among outputs: – Visitant which came into the place where it will be Japanese has admired that there was Mount Fuji. Top 10 outputs according to bigram probabilities:
– Visitors who came in Japan admire Mount Fuji.– Visitors who came in Japan admires Mount Fuji.– Visitors who arrived in Japan admire Mount Fuji.– A visitor who came in Japan admire Mount Fuji.– The visitor who came in Japan admire Mount Fuji.– Visitors who came in Japan admire Mount Fuji.– The visitor who came in Japan admires Mount Fuji.– Mount Fuji is admired by a visitor who came in Japan.
It is a task of generating Natural Language from a machine representation system such as a knowledge base or a logical form.
Ex: Choose randomly among outputs: – Visitant which came into the place where it will be Japanese has admired that there was Mount Fuji. Top 10 outputs according to bigram probabilities:
– Visitors who came in Japan admire Mount Fuji.– Visitors who came in Japan admires Mount Fuji.– Visitors who arrived in Japan admire Mount Fuji.– A visitor who came in Japan admire Mount Fuji.– The visitor who came in Japan admire Mount Fuji.– Visitors who came in Japan admire Mount Fuji.– The visitor who came in Japan admires Mount Fuji.– Mount Fuji is admired by a visitor who came in Japan.
AI@Azusa Pacific University
56
ConclusionConclusion
AI@Azusa Pacific University
Overview of some probabilistic and machine learning methods for NLP
Also very relevant to bioinformatics !Analogy between parsing
A sentenceA biological string (DNA, protein, mRNA,
…)
Overview of some probabilistic and machine learning methods for NLP
Also very relevant to bioinformatics !Analogy between parsing
A sentenceA biological string (DNA, protein, mRNA,
…)
57
AI@Azusa Pacific University
Sense, Communicate, Actuate
58
Machine Translations Machine Translations
Machine Translation or MT is a sub-field of computational linguistics that investigates usage of computer software to translate text or speech from one natural language to another
Machine Translation or MT is a sub-field of computational linguistics that investigates usage of computer software to translate text or speech from one natural language to another
AI@Azusa Pacific University
59
Issues in Machine TranslationsIssues in Machine Translations
Text to Text Machine Translations Speech to Speech Machine Translations Most of the work has addressed pairs of widely
spread languages like English-French, English-Chinese
How to translate text? Learn from previously translated data Need parallel corpora
French-English, Chinese-English have the Hansards
Reasonable translations Chinese-Hindi – no such tools available today!
Text to Text Machine Translations Speech to Speech Machine Translations Most of the work has addressed pairs of widely
spread languages like English-French, English-Chinese
How to translate text? Learn from previously translated data Need parallel corpora
French-English, Chinese-English have the Hansards
Reasonable translations Chinese-Hindi – no such tools available today!
AI@Azusa Pacific University
60
Issues in Machine TranslationsIssues in Machine Translations
How to obtain parallel texts?From the Web! How?From Web users! How?
Once we have the texts, how to get most out of them?Word alignmentsObtain lexiconsImport knowledge from well studied
languages
How to obtain parallel texts?From the Web! How?From Web users! How?
Once we have the texts, how to get most out of them?Word alignmentsObtain lexiconsImport knowledge from well studied
languages
AI@Azusa Pacific University
61
Information Extraction Information Extraction
It’s a type of information retrieval whose goal is to automatically extract structured or semi structured information from unstructured machine readable documents.
Its significance is determined by the growing amount of information available in unstructured form, for instance on the Internet.
It’s a type of information retrieval whose goal is to automatically extract structured or semi structured information from unstructured machine readable documents.
Its significance is determined by the growing amount of information available in unstructured form, for instance on the Internet.
AI@Azusa Pacific University
62
Issues in Information ExtractionIssues in Information Extraction
“There was a group of about 8-9 people close to the entrance on Highway 75”
Who? “8-9 people”Where? “highway 75”Extract informationDetect new patterns:
Detect hacking / hidden information / etc.Gov./mil. puts lots of money put into IE
research
“There was a group of about 8-9 people close to the entrance on Highway 75”
Who? “8-9 people”Where? “highway 75”Extract informationDetect new patterns:
Detect hacking / hidden information / etc.Gov./mil. puts lots of money put into IE
research
AI@Azusa Pacific University
63
Information RetrievalInformation Retrieval
Information Retrieval (IR) is a science of searching
for information in documents, for documents themselves, for metadata or searching with in databases (any kind).
Information Retrieval (IR) is a science of searching
for information in documents, for documents themselves, for metadata or searching with in databases (any kind).
AI@Azusa Pacific University
64
Issues in Information RetrievalIssues in Information Retrieval
Index meaningSearch for plant (=living organism)
should not retrieve texts with plant (=industrial plant)
But should retrieve documents including “flora” or other related terms
Index parsed relations
Index meaningSearch for plant (=living organism)
should not retrieve texts with plant (=industrial plant)
But should retrieve documents including “flora” or other related terms
Index parsed relations
AI@Azusa Pacific University
65
Issues in Information RetrievalIssues in Information Retrieval
Retrieve specific information Question Answering “What is the height of mount Everest?” 11,000 feet Current state-of-the-art 40-50%Improve precision with the use of more common
sense knowledgePerform domain specific question answering
Retrieve specific information Question Answering “What is the height of mount Everest?” 11,000 feet Current state-of-the-art 40-50%Improve precision with the use of more common
sense knowledgePerform domain specific question answering
AI@Azusa Pacific University
66
Issues in Information RetrievalIssues in Information Retrieval
Find information across languages! Cross Language Information Retrieval “What is the minimum age requirement for car
rental in Italy?” Search also Italian texts for “eta minima per
noleggio macchine” Integrate large number of languages Integrate into performant IR engines
Find information across languages! Cross Language Information Retrieval “What is the minimum age requirement for car
rental in Italy?” Search also Italian texts for “eta minima per
noleggio macchine” Integrate large number of languages Integrate into performant IR engines
AI@Azusa Pacific University
67
Automatic SummarizationAutomatic Summarization
It is the creation of a shortened version of a text by a computer program.
As access to data has increased so has interest in automatic summarization. An example of the use of summarization technology is search engines such as Google.
Technologies that can make a coherent summary, of any kind of text, need to take into account several variables such as length, writing –style and syntax to make a useful summary.
It is the creation of a shortened version of a text by a computer program.
As access to data has increased so has interest in automatic summarization. An example of the use of summarization technology is search engines such as Google.
Technologies that can make a coherent summary, of any kind of text, need to take into account several variables such as length, writing –style and syntax to make a useful summary.
AI@Azusa Pacific University
68
Foreign Language Writing Aid Foreign Language Writing Aid
It is a computer program that assists a non-native language user in their target language.
Assistive operations can be classified into two categories: on-the-fly prompts and post-writing checks.
Assisted aspects of writing include: Lexical syntax, Lexical semantics, idiomatic
expression transfer, etc. On-line dictionaries can also be considered as
a type of foreign language writing aid.
It is a computer program that assists a non-native language user in their target language.
Assistive operations can be classified into two categories: on-the-fly prompts and post-writing checks.
Assisted aspects of writing include: Lexical syntax, Lexical semantics, idiomatic
expression transfer, etc. On-line dictionaries can also be considered as
a type of foreign language writing aid.
AI@Azusa Pacific University
69
Language & speech technology have advanced rapidly in the last decades.
AI@Azusa Pacific University
70
It is EveR-2 Muse, a robot version of a Korean woman in her twenties (Eve+R for robot), can hold a conversation or sing a song, make eye contact, and express anger, sorrow and joy. But according to her creator, most Koreans found her homely in comparison to her predecessor
It is EveR-2 Muse, a robot version of a Korean woman in her twenties (Eve+R for robot), can hold a conversation or sing a song, make eye contact, and express anger, sorrow and joy. But according to her creator, most Koreans found her homely in comparison to her predecessor
AI@Azusa Pacific University
71
Achievements of AI/ NLPAchievements of AI/ NLP Sphinx can recognise continuous speech. Deep Thought is an international grand master chess
player. Without training for each speaker, it operates in near real time using a vocabulary of 1000 words and has 94% word accuracy.
Navlab is a truck that can drive along a road at 55mph in normal traffic.
Carlton and United Breweries use an AI planning system to plan production of their beer.
Natural language interfaces to databases can be obtained on a PC.
Machine Learning methods have been used to build expert systems.
Expert systems are used regularly in finance, medicine, manufacturing, and agriculture
Sphinx can recognise continuous speech. Deep Thought is an international grand master chess
player. Without training for each speaker, it operates in near real time using a vocabulary of 1000 words and has 94% word accuracy.
Navlab is a truck that can drive along a road at 55mph in normal traffic.
Carlton and United Breweries use an AI planning system to plan production of their beer.
Natural language interfaces to databases can be obtained on a PC.
Machine Learning methods have been used to build expert systems.
Expert systems are used regularly in finance, medicine, manufacturing, and agriculture
AI@Azusa Pacific University
72
If this dream comes alive…If this dream comes alive…
Even a person who is ignorant of computer knowledge can interact with it through a colloquial interaction.
Almost all systems will be automated. Many problems will have found a solution. No one needs to learn computer languages any more,
instead they can interact with the computer in their natural (regional) languages themselves.
It would be a matter of jubilance for the world as a whole…..
Even a person who is ignorant of computer knowledge can interact with it through a colloquial interaction.
Almost all systems will be automated. Many problems will have found a solution. No one needs to learn computer languages any more,
instead they can interact with the computer in their natural (regional) languages themselves.
It would be a matter of jubilance for the world as a whole…..
AI@Azusa Pacific University
73
So lets await that wonderful day &
work in this direction….
AI@Azusa Pacific University