dependency parsing ， framenet, semantic role labeling, semantic parsing heng ji [email protected]...

DEPENDENCY PARSING， FRAMENET,SEMANTIC ROLE LABELING, SEMANTIC PARSING

Heng Ji

[email protected] 17, 2014

Acknowledgement: FrameNet slides from Charles Fillmore;Semantic Parsing Slides from Rohit Kate and Yuk Wah Wong

Outline

• Dependency Parsing• Formal definition• Dynamic programming • Supervised Classification

• Semantic Role Labeling• Propbank• Automatic SRL• FrameNet

• Semantic Parsing

Semantic Parsing• “Semantic Parsing” is, ironically, a semantically

ambiguous term• Semantic role labeling• Finding generic relations in text• Transforming a natural language sentence into its meaning

representation

Semantic Parsing• Semantic Parsing: Transforming natural language (NL)

sentences into computer executable complete meaning representations (MRs) for domain-specific applications

• Realistic semantic parsing currently entails domain dependence

• Example application domains• ATIS: Air Travel Information Service• CLang: Robocup Coach Language • Geoquery: A Database Query Application

• Interface to an air travel database [Price, 1990]

• Widely-used benchmark for spoken language understanding

ATIS: Air Travel Information Service

Air-TransportationShow: (Flight-Number)Origin: (City "Cleveland")Destination: (City "Dallas")

May I see all the flights from Cleveland to

Dallas? NA 1439, TQ 23, …

Semantic Parsing Query

CLang: RoboCup Coach Language• In RoboCup Coach competition teams compete to

coach simulated players [http://www.robocup.org]

• The coaching instructions are given in a computer language called CLang [Chen et al. 2003]

Simulated soccer field

CLang

If the ball is in our goal area then player 1 should intercept it.

(bpos (goal-area our) (do our {1} intercept))

Semantic Parsing

Geoquery: A Database Query Application

• Query application for U.S. geography database containing about 800 facts [Zelle & Mooney, 1996]

Which rivers run through the states bordering Texas?

Queryanswer(traverse(next_to(stateid(‘texas’))))

Semantic Parsing

Arkansas, Canadian, Cimarron, Gila, Mississippi, Rio Grande …

Answer

What is the meaning of “meaning”?• Representing the meaning of natural language is

ultimately a difficult philosophical question• Many attempts have been made to define generic formal

semantics of natural language • Can they really be complete?• What can they do for us computationally?• Not so useful if the meaning of Life is defined as Life’

• Our meaning representation for semantic parsing does something useful for an application

• Procedural Semantics: The meaning of a sentence is a formal representation of a procedure that performs some action that is an appropriate response• Answering questions• Following commands

Meaning Representation Languages• Meaning representation language (MRL) for an

application is assumed to be present

• MRL is designed by the creators of the application to suit the application’s needs independent of natural language

• CLang was designed by RoboCup community to send formal coaching instructions to simulated players

• Geoquery’s MRL was based on the Prolog database

Engineering Motivation for Semantic Parsing• Applications of domain-dependent semantic parsing

• Natural language interfaces to computing systems• Communication with robots in natural language• Personalized software assistants• Question-answering systems

• Machine learning makes developing semantic parsers for specific applications more tractable

• Training corpora can be easily developed by tagging natural-language glosses with formal statements

Cognitive Science Motivation for Semantic Parsing• Most natural-language learning methods require

supervised training data that is not available to a child• No POS-tagged or treebank data

• Assuming a child can infer the likely meaning of an utterance from context, NL-MR pairs are more cognitively plausible training data

Distinctions from Other NLP Tasks: Deeper Semantic Analysis• Information extraction involves shallow semantic analysis

Show the long email Alice sent me yesterday

Sender Sent-to Type Time

Alice Me Long 7/10/2010

Distinctions from Other NLP Tasks: Deeper Semantic Analysis• Semantic role labeling also involves shallow semantic

analysis

sender recipient

theme


Distinctions from Other NLP Tasks: Deeper Semantic Analysis• Semantic parsing involves deeper semantic analysis to

understand the whole sentence for some application


Semantic Parsing

Distinctions from Other NLP Tasks: Final Representation• Part-of-speech tagging, syntactic parsing, SRL etc.

generate some intermediate linguistic representation, typically for latter processing; in contrast, semantic parsing generates a final representation


determiner adjective noun noun verb pronoun nounverb

verb phrasenoun phrasenoun phraseverb phrase

sentence

noun phrase

sentence

Distinctions from Other NLP Tasks: Computer Readable Output• The output of some NLP tasks, like question-answering,

summarization and machine translation, are in NL and meant for humans to read

• Since humans are intelligent, there is some room for incomplete, ungrammatical or incorrect output in these tasks; credit is given for partially correct output

• In contrast, the output of semantic parsing is in formal language and is meant for computers to read; it is critical to get the exact output, strict evaluation with no partial credit

Distinctions from Other NLP Tasks• Shallow semantic processing

• Information extraction• Semantic role labeling

• Intermediate linguistic representations• Part-of-speech tagging• Syntactic parsing• Semantic role labeling

• Output meant for humans• Question answering• Summarization• Machine translation

Relations to Other NLP Tasks:Word Sense Disambiguation• Semantic parsing includes performing word sense

disambiguation

Which rivers run through the states bordering Mississippi?

answer(traverse(next_to(stateid(‘mississippi’))))

Semantic Parsing

State? River?State

Relations to Other NLP Tasks:Syntactic Parsing• Semantic parsing inherently includes syntactic parsing but

as dictated by the semantics

our player 2 has

the ball

our player(_,_) 2 bowner(_)

null null

null

bowner(_) player(our,2)

bowner(player(our,2))

MR: bowner(player(our,2))

A semantic derivation:

Relations to Other NLP Tasks:Syntactic Parsing• Semantic parsing inherently includes syntactic parsing but

as dictated by the semantics

our player 2 has

the ball

PRP$-our NN-player(_,_) CD-2 VB-bowner(_)

null null

null

VP-bowner(_)NP-player(our,2)

S-bowner(player(our,2))

MR: bowner(player(our,2))

A semantic derivation:

Relations to Other NLP Tasks:Machine Translation• The MR could be looked upon as another NL [Papineni et

al., 1997; Wong & Mooney, 2006]



Relations to Other NLP Tasks:Natural Language Generation• Reversing a semantic parsing system becomes a natural

language generation system [Jacobs, 1985; Wong & Mooney, 2007a]



Semantic Parsing NL Generation

Relations to Other NLP Tasks• Tasks being performed within semantic parsing

• Word sense disambiguation• Syntactic parsing as dictated by semantics

• Tasks closely related to semantic parsing• Machine translation• Natural language generation

Dependency Grammars• In CFG-style phrase-structure grammars the main focus is

on constituents.• But it turns out you can get a lot done with just binary

relations among the words in an utterance.• In a dependency grammar framework, a parse is a tree

where • the nodes stand for the words in an utterance• The links between the words represent dependency relations

between pairs of words.• Relations may be typed (labeled), or not.

Dependency Relations

Dependency Parse

They hid the letter on the shelf

Dependency Parsing• The dependency approach has a number of advantages

over full phrase-structure parsing.• Deals well with free word order languages where the constituent

structure is quite fluid• Parsing is much faster than CFG-bases parsers• Dependency structure often captures the syntactic relations

needed by later applications• CFG-based approaches often extract this same information from trees

anyway.

Dependency Parsing• There are two modern approaches to dependency parsing

• Optimization-based approaches that search a space of trees for the tree that best matches some criteria

• Shift-reduce approaches that greedily take actions based on the current word and state.

Phrase Structure Tree

Dependency Grammar

• Syntactic structure consists of lexical items, linked by binary asymmetric relations called dependencies

• Interested in grammatical relations between individual words (governing & dependent words)

• Does not propose a recursive structure• Rather a network of relations

• These relations can also have labels

Draw the dependency tree

• Red figures on the screens indicated falling stocks

Dependency Tree

Dependency Tree Example

• Phrasal nodes are missing in the dependency structure when compared to constituency structure.

Dependency Tree with Labels

Comparison• Dependency structures explicitly represent

• Head-dependent relations (directed arcs)• Functional categories (arc labels)• Possibly some structural categories (parts-of-speech)

• Phrase structure explicitly represent • Phrases (non-terminal nodes)• Structural categories (non-terminal labels)• Possibly some functional categories (grammatical functions)

Learning DG over PSG

• Dependency Parsing is more straightforward• Parsing can be reduced to labeling each token wi with wj

• Direct encoding of predicate-argument structure• Fragments are directly interpretable

• Dependency structure independent of word order• Suitable for free word order languages (like Indian languages)

Dependency Tree• Formal definition

• An input word sequence w1…wn

• Dependency graph D = (W,E) where• W is the set of nodes i.e. word tokens in the input seq.• E is the set of unlabeled tree edges (wi, wj) (wi, wj є W).

• (wi, wj) indicates an edge from wi (parent) to wj (child).

• Task of mapping an input string to a dependency graph satisfying certain conditions is called dependency parsing

Well-formedness• A dependency graph is well-formed iff

• Single head: Each word has only one head.

• Acyclic: The graph should be acyclic.

• Connected: The graph should be a single tree with all the words in the sentence.

• Projective: If word A depends on word B, then all words between A and B are also subordinate to B (i.e. dominated by B).

Dependency Parsing

• Dependency based parsers can be broadly categorized into • Grammar driven approaches

• Parsing done using grammars.

• Data driven approaches• Parsing by training on annotated/un-annotated data.

Dependency Parsing

• Dependency based parsers can be broadly categorized into • Grammar driven approaches

• Parsing done using grammars.

• Data driven approaches• Parsing by training on annotated/un-annotated data.

• These approaches are not mutually exclusive

Covington’s Incremental Algorithm• Incremental parsing in O(n2) time by trying to link

each new word to each preceding one [Covington 2001]:

PARSE(x = (w1, . . . ,wn))1. for i = 1 up to n

2. for j = i − 1 down to 1

3. LINK(wi , wj )

Covington’s Incremental Algorithm• Incremental parsing in O(n2) time by trying to link

each new word to each preceding one [Covington 2001]:

PARSE(x = (w1, . . . ,wn))1. for i = 1 up to n2. for j = i − 1 down to 1

3. LINK(wi , wj )

• Different conditions, such as Single-Head and Projectivity, can be incorporated into the LINK operation.

Dynamic Programming

• Basic Idea: Treat dependencies as constituents.• Use, e.g. , CYK parser (with minor modifications)

Dynamic Programming Approaches

• Original version [Hays 1964] (grammar driven) • Link grammar [Sleator and Temperley 1991] (grammar driven)• Bilexical grammar [Eisner 1996] (data driven)• Maximum spanning tree [McDonald 2006] (data driven)

Eisner 1996• Two novel aspects:

• Modified parsing algorithm• Probabilistic dependency parsing

• Time requirement: O(n3) • Modification: Instead of storing subtrees, store spans

• Span: Substring such that no interior word links to any word outside the span.

• Idea: In a span, only the boundary words are active, i.e. still need a head or a child

• One or both of the boundary words can be active

Example

Red figures on the screen indicated falling stocks_ROOT_

Example

Spans:


indicated falling stocksRed figures

Assembly of correct parse


Red figures

Start by combining adjacent words to minimal spans

figures on on the



Combine spans which overlap in one word; this word must be governed by a word in the left or right span.

on the the screen+ → on the screen




figures on + →on the screen figures on the screen




Invalid span

Red figures on the screen




+ → indicated falling stocksfalling stocksindicated falling

Classifier-Based Parsing• Data-driven deterministic parsing:

• Deterministic parsing requires an oracle.• An oracle can be approximated by a classifier.• A classifier can be trained using treebank data.

• Learning algorithms:• Support vector machines (SVM) [Kudo and Matsumoto 2002,

Yamada and Matsumoto 2003,Isozaki et al. 2004, Cheng et al. 2004, Nivre et al. 2006]

• Memory-based learning (MBL) [Nivre et al. 2004, Nivre and Scholz 2004]

• Maximum entropy modeling (MaxEnt) [Cheng et al. 2005]

Feature Models• Learning problem:

• Approximate a function from parser states, represented by feature vectors to parser actions, given a training set of gold standard derivations.

• Typical features:• Tokens and POS tags of :

• Target words• Linear context (neighbors in S and Q)• Structural context (parents, children, siblings in G)

• Can not be used in dynamic programming algorithms.

Feature Models

Dependency Parsers for download

• MST parser by Ryan McDonald• Malt parser by Joakim Nivre• Stanford parser

Outline




62

What is PropBank:From Sentences to Propositions

Powell met Zhu Rongji

Proposition: meet(Powell, Zhu Rongji)Powell met with Zhu Rongji

Powell and Zhu Rongji met

Powell and Zhu Rongji had a meeting

. . .When Powell met Zhu Rongji on Thursday they discussed the return of the spy plane.

meet(Powell, Zhu) discuss([Powell, Zhu], return(X, plane))

debate

consult

joinwrestle

battle

meet(Somebody1, Somebody2)

63

Capturing semantic roles

• Faisal broke [ ARG1 Tom’s chair].

• [ARG1 Monica’s chair] was broken by Lucian.

• [ARG1 Nitin’s chair] broke into pieces when it fell down.

SUBJ

SUBJ

SUBJ

64

A TreeBanked SentenceS

VBD

NP VP

NP

working

gave

NPDT JJ NN

NNS NNVBG

Leeway

The Supreme Court

states

“Non Terminal” (130969 ARGs)

“Terminal”(4246 ARGs)

65

The Same Sentence, PropBankedS

VBD

NP/ARG0 VP

NP/ARG2

working

gave

NP/ARG1DT JJ NN

NNS NNVBG

Leeway/ARG0

The Supreme Court

states

Predicate Predicate

66

Core Arguments

• Arg0 = agent• Arg1 = direct object / theme / patient• Arg2 = indirect object / benefactive / instrument /

attribute / end state• Arg3 = start point / benefactive / instrument /

attribute• Arg4 = end point

67

Secondary ArgMs• LOC - where at?• DIR - where to?• MNR - how?• PRP -why?• REC - himself, themselves, each other• PRD -this argument refers to or modifies another• ADV –others• TMP - when?• TPC – topic• ADV –others

68

Distributions of Argument Types

91519

11662821670

3944255373560028378876

18703

11120744502

10100

2630873465103251814187 ARG0

ARG1

ARG2

ARG3

ARG4

ARG5

EXT

DIR

LOC

TMP

REC

PRD

CORE Types

ARGM Types

69

How to Use PropBank: Train a Semantic Role Labeling System

• (CONLL 04, CONLL 05 and) Our Goal: Given a list of (3073) target verbs the system should be able to tag the possible nodes with semantic role labels (Ji et al., 2005)

70

Predicate Features: Lexical

• Head Word, Head Pos of (-2,-1,0,1,2) window of Predicate

• Predicate is a Transitive verb or not

• Predicate Voice (Passive or not)• Verb itself: must be in its past particle form• Passive Context

--Immediately following the verb "be" --Postmodifying a noun in a reduced relative clause, "The building damaged by fire".

• Encoding Conjunction feature of Predicate POS_Passive Context

71

Predicate Sub-Categorization FeatureS

VBD

NP/ARG0 VP

NP/ARG2

working

gave

NP/ARG1DT JJ NN

NNS NNVBG

Leeway/ARG0

The Supreme Court

states

VP->VBD-NP-NP

The Phrase structure rule expanding the predicate’s grandparent

72

S

VBD

NP/ARG0 VP

NP/ARG2

working

gave

NP/ARG1DT JJ NN

NNS NNVBG

Leeway/ARG0

The Supreme Court

states

vbd_NNS_VBG_NN, v_NNS_VBG_NN, gave_NNS_VBG_NN, vbd_NP_NP, v_NP_NP, gave_NP_NP

Consider the predicate as a “Pivot”, and its grandparent’s children are defined in relation to it.

Predicate Pivot Features

73

Argument Features: Lexical/Syntactic

• Head Word, Head Pos, Phrase Type of (-2,-1,0,1,2) window words, Begin Word, Last Word, Left Sister, Right Sister, Parent of Argument

(Head of PP replaced by head word of NP inside it)

• Head Pos, Phrase Type of GrandParent• Suffix1, Suffix2, Suffix3• Preceding, Succeeding Node’s Label• Length (Span)• Level from Leaves• Beginning Letter of Phrase Type (for generalization)• Punctuation before/after• If it includes a Preposition or not, and Prep POS

74

Path: NP S VP VBD gave PartialPath: NP S InterPath: S VP VBD PredPathArgPathLens: 3_1 CollapsedPath (delete nodes between clauses): NP S VP VBD gave PathSOnly(Replace all the non-clause nodes with "*“): NP S * * gave PathSRemain(only keep clause nodes): NP S gavePathNGrams: NP|S|VP, S|VP|VBD, VP|VBD|gave, VBD|gave|*, gave|*|*PathLen: 4 ArgPhraseType, PathLen: NP, 4 PredHeadWord, PathSRemain: gave, NP S gave

Intervene Feature: PathS

VBD

NP/ARG0 VP

gave

…DT JJ NN

The Supreme Court

75

Directionality: Left SameClause: true Dominate Phrase Type: S Adjacency (Adjacent/not-Adjacent): AdjacentArgPhraseType,Adjacency: NP,AdjacentPositionInClause (Begin, Inside, End): BeginRelPosition (Distance between Spans): 0RelPosition,Directionality: 0, Left RelPosition,Transitive: 0, TrueRelPosition,PredHeadPos,PassiveContext: 0, VBD, FalseRelPosition,ArgPhraseType: 0, NP RelPosition,PredPivotv: 0, v_NNS_VBG_NN

Intervene Feature: PositionS

VBD

NP/ARG0 VP

gave

…DT JJ NN

The Supreme Court

76

S

VBD

NP/ARG0 VP

NP/ARG2

gave

NP/ARG1DT JJ NN

The Supreme Court

np_v_NP_NP_PP, CUR_v_NP_NP_PP, CUR_gave_NP_NP_PP

Intervene Features: Pivot

Consider the predicate and candidate argument as “Pivots”, and other constituents are defined in relation to them

PP

…

77

Other Features

• PredHeadWord, ArgHeadWord• PredHeadWord, ArgPhraseType• ArgPreposition,Transitive• Frequency of VP, NP, SBAR, CC, “,”, “:”, “”” in the sentence• …• …

Hmm. Haven’t I heard that word “frame” before?

Yes, it’s intended to be seen as a variation on the word as it’s been used in various branches of the cognitive sciences in recent decades.

“Frames” TraditionsLet’s locate “our” notion of frame within the various

traditions in the cognitive sciences that use the words frame or schema (joined, sometimes, with stereotype, script, scenario or idealized cognitive model) which appear to be dealing with essentially the same concept.

These terms are used to denote structured sets of expectations that play a central role in how human beings create or interpret their experiences.

customer

The noun customer is typically defined as ‘someone who buys something in a shop or business.’ That includes everyone I know over the age of 5.

Suppose you overhear somebody say

Sue tends to be rude to customers.

What situation do you imagine?

chicken (mass noun)• The noun chicken, as a count noun, is the name of a well-known

domestic bird. As a mass noun it is defined as ‘the meat of a chicken or chickens’.

• What’s wrong with the following sentence?

The fox that lives near our farm likes chicken. (compare: likes chickens)

• The image you might get is of a fox eating fried chicken, holding a knife and a fork, and a napkin, in its paws.

• The products of the lexical construction that yields mass noun uses of chicken, lamb, duck, turkey, etc., refer to meats prepared as part of human cuisine.

*The wolf that lives near our ranch prefers lamb.

Invoking and Evoking Frames

• People invoke (summon up from their memory) frames, to make sense of their experience, linguistic or otherwise.

• a cognitive act

• Words evoke categories and knowledge structures that shape interpreters’ understanding of a text.

• a cognitive experience

Warning: this not a standard use of these words.

So,

We need to describe words in terms of the “framal” background.

If we don’t understand the frame, we don’t understand

the word,

or why the language needs this word,

or why the speaker chose to use it.

The ideal dictionary should let you

1. Look up a word2. Get a link to a description of the relevant frame, for each of its

meanings, and see the names of the frame’s components3. See a display of its combinatory affordances, its valence

possibilities, both semantic and syntactic4. Find a collection of example sentences illustrating all of its main

combinatory patterns5. Find a list of other words that evoke the same frame6. Link to other semantically related frames

Frame examples: RiskTaking_a_risk:

Protagonist, Action, Harm, Asset1. I’m going to risk a swim in the sea.2. You’ll risk bankruptcy if you make that investment.3. You’re risking your reputation by doing that.4. You’re taking a big risk.

Being_at_risk: Protagonist, Harm, Asset

5. Buildings in California risk destruction by earthquakes.6. Newborns in this hospital run the risk of hypothermia.7. We risk our lives every day.8. I am at risk of stroke.

Frame examples: ExplanationCommunication.explanation:

Speaker, Addressee, Mystery, Account1. The coach explained the problem to the team.

2. The coach explained that they hadn’t learned the maneuvers.

3. What’s your explanation of these facts?

4. The defense lawyer gave an inadequate explanation.

Cognition.explanation: Mystery, Account

5. What can explain these facts?

6. A history of unrestricted logging explains the erosion pattern we see here.

Compare: explain & reveal

In their cognitive senses, as opposed to their meanings as verbs of speaking, the verbs explain and reveal are near-inverses of each other, where the Mystery and the Account in the former correspond to Evidence and Conclusion in the latter.

1. A history of unrestrained logging explains the erosion pattern we see here.

(explains, accounts for)2. The erosion pattern we see here

reveals a history of unrestrained logging.

(reveals, shows, suggests)

state transitionstate transition state

Reading the Pictures

The boxes refer to five-part scenarios consisting of an initial state, a transition, an intermediary state, another transition, and a final state.

The writing under the pictures abbreviates particular role names and gives verbs that evoke instances of the scenario.

The bold borders indicate a profiling of some portion of the event.

X; return, go back, come back

He returned to Hong Kong.He returned Tuesday evening after a week’s trip to Australia.He returned to his home for a few days.

The verb RETURN profiles the time of arrival, but it evokesthe entire frame; other information in the sentences can fill in some of the details of the larger scenario.

A, X; return, replace, put back

I returned your books this morning.

I returned to your desk the books that I had borrowed last week.

After the earthquake we replaced all the books on the shelf.

frame elements• Participants and Sub-events .

• Avenger the one who enacts revenge

• Offender the original offender

• Injured_party the offender’s victim

• Injury the offender’s act

• Punishment the avenger’s act

grammar

• Components of linguistic form for expressing the FEs (defining valence).• Subject• Direct Object• Prepositional marking

(by, for, with, on, at, against)• Subordinate clause marking

(for DOING, by DOING)

Outline




Learning Semantic Parsers

Semantic Parser Learner

Semantic ParserMeaning RepresentationsSentences

Training Sentences &Meaning Representations

Data Collection for ATIS• Air travel planning scenarios (Hirschman, 1992)

You have 3 days for job hunting, and you have arranged job interviews in 2 different cities! Start from City-A and plan the flight and ground transportation itinerary to City-B and City-C, and back home to City-A.

• Use of human wizards:• Subjects were led to believe they were talking to a fully automated

systems• Human transcription and error correction behind the scene

• A group at SRI responsible for database reference answers

• Collected more than 10,000 utterances and 1,000 sessions for ATIS-3

Sample Session in ATIS• may i see all the flights from cleveland to , dallas• can you show me the flights that leave before noon ,

only• could you sh- please show me the types of aircraft

used on these flights

Air-TransportationShow: (Aircraft)Origin: (City "Cleveland")Destination: (City "Dallas")Departure-Time: (< 1200)

Chanel (Kuhn & De Mori, 1995)• Consists of a set of decision trees• Each tree builds part of a meaning representation• Some trees decide whether a given attribute should be

displayed in query results• Some trees decide the semantic role of a given substring

• Each correpsonds to a query constraint

Chanel (Kuhn & De Mori, 1995)show me TIME flights from CITY1 to CITY2 and how much they cost

Tree 1:Display aircraft_code?

Tree 23:Display fare_id?

Tree 114:Display booking_class?

CITY tree:For each CITY: origin, dest, or stop?

TIME tree:For each TIME: arrival or departure?

Display Attributes: {flight_id, fare_id}Constraints: {from_airport = CITY1,to_airport = CITY2, departure_time = TIME}

Statistical Parsing (Miller et al., 1996)

• Find most likely meaning M0, given words W and history H

(M': pre-discourse meaning, T: parse tree)

• Three successive stages: parsing, semantic interpretation, and discourse

• Parsing model similar to Seneff (1992)• Requires annotated parse trees for training

Statistical Parsing (Miller et al., 1996)

When thedo flights that leave from Boston arrive in Atlanta

time/wh-head /det/aux

flight/np-head /comp

departure/vp-head

departure/prep

city/npr

arrival/vp-head

location/prep

city/npr

departure/pp

location/pp

flight/corenp

departure/vp

flight-constraints/rel-clause

flight/np

arrival/vp

/wh-question

Recent Approaches• Different levels of supervision

• Ranging from fully supervised to unsupervised• Advances in machine learning

• Structured learning• Kernel methods

• Grammar formalisms• Combinatory categorial grammars• Sychronous grammars

• Unified framework for handling various phenomena• Spontaneous speech• Discourse• Perceptual context• Generation

Combinatory Categorial Grammar• Highly structured lexical entries• A few general parsing rules (Steedman, 2000; Steedman

& Baldridge, 2005)• Each lexical entry is a word paired with a category

Texas := NPborders := (S \ NP) / NPMexico := NPNew Mexico := NP

Parsing Rules (Combinators)• Describe how adjacent categories are combined• Functional application:

A / B B ⇒ A (>)

B A \ B ⇒ A (<)

Texas borders New Mexico

NP (S \ NP) / NP NP

S \ NP>

<S

CCG for Semantic Parsing• Extend categories with semantic types

• Functional application with semantics:

Texas := NP : texasborders := (S \ NP) / NP : λx.λy.borders(y, x)

A / B : f B : a ⇒ A : f(a) (>)

B : a A \ B : f ⇒ A : f(a) (<)

Sample CCG Derivation


NPtexas

(S \ NP) / NPλx.λy.borders(y, x)

NPnew_mexico

S \ NPλy.borders(y, new_mexico)

>

<S

borders(texas, new_mexico)

Another Sample CCG Derivation


NPtexas

(S \ NP) / NPλx.λy.borders(y, x)

NPmexico

S \ NPλy.borders(y, mexico)

>

<S

borders(texas, mexico)

Probabilistic CCG for Semantic Parsing

• L (lexicon) =

• w (feature weights)

• Features:• fi(x, d): Number of times lexical item i is used in derivation d

• Log-linear model: Pw(d | x) exp(w . f(x, d))• Best derviation: d* = argmaxd w . f(x, d)

• Consider all possible derivations d for the sentence x given the lexicon L

Zettlemoyer & Collins (2005)

Texas := NP : texasborders := (S \ NP) / NP : λx.λy.borders(y, x)Mexico := NP : mexicoNew Mexico := NP : new_mexico

Learning Probabilistic CCG

Lexical Generation

CCG ParserLogical FormsSentences

Training Sentences &Logical Forms

Parameter Estimation

Lexicon L

Feature weights w

Lexical Generation• Input:

• Output lexicon:

Texas borders New Mexicoborders(texas, new_mexico)

Texas := NP : texasborders := (S \ NP) / NP : λx.λy.borders(y, x)New Mexico := NP : new_mexico

Lexical GenerationInput sentence:


Output substrings:

Texas

borders

New

Mexico

Texas borders

borders New

New Mexico

Texas borders New

…

Input logical form:

borders(texas, new_mexico)

Output categories:

NP : texas

NP : new _mexico

(S \ NP) / NP : λx.λy.borders(y, x)

(S \ NP) / NP : λx.λy.borders(x, y)

…

Category RulesInput Trigger Output Category

constant c NP : c

arity one predicate p N : λx.p(x)

arity one predicate p S \ NP : λx.p(x)

arity two predicate p (S \ NP) / NP : λx.λy.p(y, x)

arity two predicate p (S \ NP) / NP : λx.λy.p(x, y)

arity one predicate p N / N : λg.λx.p(x) g(x)

arity two predicate p and constant c

N / N : λg.λx.p(x, c) g(x)

arity two predicate p (N \ N) / NP : λx.λg.λy.p(y, x) g(x)

arity one function f NP / N : λg.argmax/min(g(x), λx.f(x))

arity one function f S / NP : λx.f(x)

Parameter Estimation• Maximum conditional likelihood

• Derivations d are not annotated, treated as hidden variables

• Stochastic gradient ascent (LeCun et al., 1998)• Keep only those lexical items that occur in the highest

scoring derivations of training set

Results• Test for correct logical forms• Precision: # correct / total # parsed sentences• Recall: # correct / total # sentences• For Geoquery, 96% precision, 79% recall• Low recall due to incomplete lexical generation:

• Through which states does the Mississippi run?

Context-Free Semantic Grammar

QUERY What is CITY

CITY the capital CITY

CITY of STATE

STATE Ohio

Ohio

of STATE

QUERY

CITYWhat is

CITYthe capital

Sample SCFG Production

QUERY What is CITY / answer(CITY)

Natural language Formal language

Sample SCFG Derivation

QUERY QUERY



QUERY

CITYWhat is

QUERY

answer ( CITY )


What is the capital of Ohio

Ohio

of STATE

QUERY

CITYWhat is

QUERY

answer ( CITY )

capital ( CITY )

loc_2 ( STATE )

stateid ( 'ohio' )

answer(capital(loc_2(stateid('ohio'))))

CITYthe capital

Another Sample SCFG Derivation

What is the capital of Ohio

Ohio

of RIVER

QUERY

CITYWhat is

QUERY

answer ( CITY )

capital ( CITY )

loc_2 ( RIVER )

riverid ( 'ohio' )

answer(capital(loc_2(riverid('ohio'))))

CITYthe capital

Probabilistic SCFG for Semantic Parsing

• S (start symbol) = QUERY

• L (lexicon) =

• w (feature weights)

• Features:• fi(x, d): Number of times production i is used in derivation d

• Log-linear model: Pw(d | x) exp(w . f(x, d))• Best derviation: d* = argmaxd w . f(x, d)

STATE Ohio / stateid('ohio')


CITY the capital CITY / capital(CITY)

CITY of STATE / loc_2(STATE)

Learning Probabilistic SCFG

Lexical Acquisition

SCFG ParserMeaning RepresentationsSentences

Training Sentences &Meaning Representations

Parameter Estimation

Lexicon L

Feature weights w

Unambiguous CFG forMeaning Representations

Lexical Acquisition• SCFG productions are extracted from word alignments

between training sentences and their meaning representations

( ( true ) ( do our { 1 } ( pos ( half our ) ) ) )

The goalie should always stay in our half

Extracting SCFG Productions

The

goalie

should

always

stay

in

our

half

RULE (CONDITION DIRECTIVE)

CONDITION (true)

DIRECTIVE (do TEAM {UNUM} ACTION)

TEAM our

UNUM 1

ACTION (pos REGION)

REGION (half TEAM)

TEAM our


TEAM

The

goalie

should

always

stay

in

half


CONDITION (true)


TEAM our

UNUM 1

ACTION (pos REGION)

REGION (half TEAM)

TEAM our / our


TEAM

The

goalie

should

always

stay

in

half


CONDITION (true)


TEAM our

UNUM 1

ACTION (pos REGION)

REGION (half TEAM)


REGION

The

goalie

should

always

stay

in


CONDITION (true)


TEAM our

UNUM 1

ACTION (pos REGION)

REGION TEAM half / (half TEAM)

Output SCFG Productions

TEAM our / our

REGION TEAM half / (half TEAM)

ACTION stay in REGION / (pos REGION)

UNUM goalie / 1

RULE [the] UNUM should always ACTION / ((true) (do our {UNUM} ACTION))

• Phrases can be non-contiguous

Handling Logical Forms with VariablesWong & Mooney (2007b)

FORM state / λx.state(x)

FORM by area / λx.λy.area(x, y)

FORM [the] smallest FORM FORM/ λx.smallest(y, (FORM(x), FORM(x, y))

QUERY what is FORM/ answer(x, FORM(x))

• Operators for variable binding

Unambiguous Supervision for Learning Semantic Parsers• The training data for semantic parsing consists of

hundreds of natural language sentences unambiguously paired with their meaning representations

Unambiguous Supervision for Learning Semantic Parsers• The training data for semantic parsing consists of

hundreds of natural language sentences unambiguously paired with their meaning representations

Which rivers run through the states bordering Texas?answer(traverse(next_to(stateid(‘texas’))))

What is the lowest point of the state with the largest area? answer(lowest(place(loc(largest_one(area(state(all)))))))

What is the largest city in states that border California?answer(largest(city(loc(next_to(stateid( 'california'))))))

……

Shortcomings of Unambiguous Supervision

• It requires considerable human effort to annotate each sentence with its correct meaning representation

• Does not model the type of supervision children receive when they are learning a language• Children are not taught meanings of individual sentences• They learn to identify the correct meaning of a sentence from

several meanings possible in their perceptual context

???

“Mary is on the phone”

Ambiguous Supervision for Learning Semantic Parsers• A computer system simultaneously exposed to perceptual contexts

and natural language utterances should be able to learn the underlying language semantics

• We consider ambiguous training data of sentences associated with multiple potential meaning representations• Siskind (1996) uses this type “referentially uncertain” training data to

learn meanings of words• We use ambiguous training data to learn meanings of sentences

• Capturing meaning representations from perceptual contexts is a difficult unsolved problem • Our system directly works with symbolic meaning representations


???

“Mary is on the phone”???

Ironing(Mommy, Shirt)



Working(Sister, Computer)




Carrying(Daddy, Bag)




Carrying(Daddy, Bag)

Talking(Mary, Phone)

Sitting(Mary, Chair)


Ambiguous Training Example

???



Talking(Mary, Phone)

Sitting(Mary, Chair)

“Mommy is ironing shirt”

Next Ambiguous Training Example

???

Sample Ambiguous Corpus

Daisy gave the clock to the mouse.

Mommy saw that Mary gave the hammer to the dog.

The dog broke the box.

John gave the bag to the mouse.

The dog threw the ball.

ate(mouse, orange)

gave(daisy, clock, mouse)

ate(dog, apple)

saw(mother, gave(mary, dog, hammer))

broke(dog, box)

gave(woman, toy, mouse)

gave(john, bag, mouse)

threw(dog, ball)

runs(dog)

saw(john, walks(man, dog))

Parsing in Watson

Watson English Slot Grammar (ESG) parser

Deep parser which explores the syntactic and logical structure to generate semantic clues

Fig: Slot filling for John sold a fish Fig: Slot Grammer Analysis Structure

John sold a f ish

subjobj

ndet

Slots WS(arg) features

Subj(n) John(1) noun pron

Top sold(2,1,4) verb

Ndet a(3) det indef

Obj(n) fish(4) noun

dependency parsing ， framenet, semantic role labeling, semantic parsing heng ji [email protected]...

Documents