Transcript Introduction to Semantics and Pragmatics

Introduction to
Semantics and Pragmatics
NLP tends to focus on:
• Syntax
– Grammars, parsers, parse trees, dependency
structures
• Semantics
– Subcategorization frames, semantic classes,
ontologies, formal semantics
• Pragmatics
– Pronouns, reference resolution, discourse
models
LING 2000 - 2006
NLP
2
Semantics and Pragmatics
High-level Linguistics (the good stuff!)
Semantics: the study of meaning that can be
determined from a sentence, phrase or word.
Pragmatics: the study of meaning, as it depends
on context (speaker, situation)
LING 2000 - 2006
NLP
3
Language to Logic
• John went to the book store.
 John  store1, go(John, store1)
• John bought a book.
buy(John,book1)
• John gave the book to Mary.
give(John,book1,Mary)
• Mary put the book on the table.
put(Mary,book1,table1)
LING 2000 - 2006
NLP
4
Semantics
Same event - different sentences
John broke the window with a hammer.
John broke the window with the crack.
The hammer broke the window.
The window broke.
LING 2000 - 2006
NLP
5
Same event - different syntactic frames
John broke the window with a hammer.
SUBJ VERB
OBJ
MODIFIER
John broke the window with the crack.
SUBJ VERB
OBJ
MODIFIER
The hammer broke the window.
SUBJ VERB
OBJ
The window broke.
SUBJ VERB
LING 2000 - 2006
NLP
6
Semantics -predicate arguments
break(AGENT, INSTRUMENT, PATIENT)
AGENT
PATIENT
INSTRUMENT
John broke the window with a hammer.
INSTRUMENT
PATIENT
The hammer broke the window.
PATIENT
The window broke.
Fillmore 68 - The case for case
LING 2000 - 2006
NLP
7
AGENT
PATIENT
INSTRUMENT
John broke the window with a hammer.
SUBJ
OBJ
INSTRUMENT
MODIFIER
PATIENT
The hammer broke the window.
SUBJ
OBJ
PATIENT
The window broke.
SUBJ
LING 2000 - 2006
NLP
8
Natural Language Processing
Applications and Tasks
•
•
•
•
Machine Translation
Question-Answering
Information Retrieval
Information Extraction
CIS 8590 – Fall 2008
NLP
9
Machine Translation
• One of the first applications for computers
– bilingual dictionary > word-word translation
• Good translation requires understanding!
– War and Peace, The Sound and The Fury?
• What can we do? Sublanguages.
– technical domains, static vocabulary
– Meteo in Canada, Caterpillar Tractor Manuals,
Botanical descriptions, Military Messages
LING 2000 - 2006
NLP
10
Example translation
LING 2000 - 2006
NLP
11
Machine Translation
• The Story of the Stone
– =The Dream of the Red Chamber (Cao Xueqin 1792)
• Issues: (“Language Divergences”)
– Sentence segmentation
– Zero-anaphora
– Coding of tense/aspect
– Penetrate -> penetrated
– Stylistic differences across languages
• Bamboo tip plaintain leaf -> bamboos and plantains
– Cultural knowledge
• Curtain -> curtains of her bed
Machine Translation
• Chinese gloss: Dai-yu alone on bed top think-of-with-gratitude Bao-chai
again listen to window outside bamboo tip plantain leaf of on-top rain
sound sigh drop clear cold penetrate curtain not feeling again fall down
tears come
• Hawkes translation: As she lay there alone, Dai-yu’s thoughts turned to
Bao-chai… Then she listened to the insistent rustle of the rain on the
bamboos and plantains outside her window. The coldness penetrated the
curtains of her bed. Almost without noticing it she had begun to cry.
Language Families
Babelfish Demo
http://babelfish.yahoo.com/
Old example:
The spirit is willing, but the flesh is weak.
Question Answering
• What does “door” mean?
• What year was Abraham Lincoln born?
• How many states were in the United States
when Lincoln was born?
• Was there a military draft during the Hoover
administration?
• What do US scientists think about whether
human cloning should be legal?
Modern QA systems
• Still in infancy
• Simple factoid questions beginning to work OK
• Annual government-sponsored “bakeoff”
called TREC
QA Demo
UIUC QA Demo
Qualim QA Demo
Issues in NLP
• Ambiguity!
• World Knowledge – it’s needed for
understanding, but computers don’t have it
NLP
19
Ambiguity
• Computational linguists are obsessed with
ambiguity
• Ambiguity is a fundamental problem of
computational linguistics
• Resolving ambiguity is a crucial goal
Ambiguity
• Find at least 5 meanings of this sentence:
– I made her duck
Ambiguity
• Find at least 5 meanings of this sentence:
– I made her duck
•
•
•
•
•
•
I cooked waterfowl for her benefit (to eat)
I cooked waterfowl belonging to her
I created the (plaster?) duck she owns
I caused her to quickly lower her head or body
I waved my magic wand and turned her into undifferentiated waterfowl
At least one other meaning that’s inappropriate for gentle company.
Ambiguity is Pervasive
• I caused her to quickly lower her head or body
– Lexical category: “duck” can be a N or V
• I cooked waterfowl belonging to her.
– Lexical category: “her” can be a possessive (“of her”) or dative (“for
her”) pronoun
• I made the (plaster) duck statue she owns
– Lexical Semantics: “make” can mean “create” or “cook”
Ambiguity is Pervasive
• Grammar: Make can be:
– Transitive: (verb has a noun direct object)
• I cooked [waterfowl belonging to her]
– Ditransitive: (verb has 2 noun objects)
• I made [her] (into) [undifferentiated waterfowl]
– Action-transitive (verb has a direct object and
another verb)
– I caused [her] [to move her body]
Ambiguity is Pervasive
• Phonetics!
–
–
–
–
–
–
–
–
–
–
I mate or duck
I’m eight or duck
Eye maid; her duck
Aye mate, her duck
I maid her duck
I’m aid her duck
I mate her duck
I’m ate her duck
I’m ate or duck
I mate or duck
Headlines
• Police Begin Campaign To Run Down Jaywalkers
• Iraqi Head Seeks Arms
• Teacher Strikes Idle Kids
• Miners Refuse To Work After Death
• Juvenile Court To Try Shooting Defendant
LING 2000 - 2006
NLP
26
Kinds of knowledge needed?
• Consider the following interaction with
HAL the computer from 2001: A Space
Odyssey
• Dave: Open the pod bay doors, Hal.
• HAL: I’m sorry Dave, I’m afraid I can’t do
that.
Knowledge needed to build HAL?
• Speech recognition and synthesis
– Dictionaries (how words are pronounced)
– Phonetics (how to recognize/produce each sound of English)
• Natural language understanding
– Knowledge of the English words involved
• What they mean
• How they combine (what is a `pod bay door’?)
– Knowledge of syntactic structure
• I’m I do, Sorry that afraid Dave I’m can’t
What’s needed?
• Dialog and pragmatic knowledge
– “open the door” is a REQUEST (as opposed to a
STATEMENT or information-question)
– It is polite to respond, even if you’re planning to
kill someone.
– It is polite to pretend to want to be cooperative
(I’m afraid I can’t…)
– What is `that’ in `I can’t do that’?
• Even a system to book airline flights needs
much of this kind of knowledge
Eliza: Weizenbaum (1966)
• User: You are like my father in some ways.
• ELIZA: What resemblance do you see
• User: You are not very aggressive but I think you don’t want me to notice
that.
• ELIZA: What makes you think I am not aggressive
• User: You don’t argue with me
• ELIZA: Why do you think I don’t argue with you
• User: You are afraid of me
• ELIZA: Does it please you to believe I am afraid of you
Modern conversational agents
• Switchboard Receptionists
– Implications: need to know how a native or non-native speaker of
English is likely to pronounce a random American name. Eek.
• Airline and other simple dialogue systems
– Lots of fabulously fun pragmatic issues
• Grounding
• Error handling
• In general
– Now that there are commercial installations
– Big incentive to use linguistic or any other kind of knowledge if it
actually improves performance
Well-understood Semantic Tasks
• Named-entity Recognition
• Coreference Resolution
• Semantic Role Labeling
• Sentiment Classification
Entities
Named Entity Tagging: Identify all the proper
names in a text
Sally went to see Up in the Air at the local theater.
Coreference Resolution: Identify all references (aka
‘mentions’) of people, places and things in text,
and determine which mentions are ‘coreferential’.
John stuck his foot in his mouth.
Semantic Role Labeling
Semantic role labeling is computational task of
assigning semantic roles to phrases
B-A0 REL B-A1 I-A1
B-AM I-AM
John broke the window with
a
I-AM
hammer.
Sentiment Classification
Given a review (about a movie, hotel, Amazon
product, etc.), a sentiment classification system
tries to determine what opinions are expressed in
the review.
Coarse-level objective: is the review positive,
negative, or neutral overall?
Fine-grained objective: what are the positive
aspects (according to the reviewer), and what are
the negative aspects?