Feature Structure Unification Syntactic Parser 2.0

L-R Feature
Structure Unification
Syntactic Parser
Richard Caneba
RPI Cognitive Science Department
Human-Level Intelligence Laboratory

Intuitions
• An interpretive grammar views syntax as finding the most
appropriate sequence of head and dependency relationship
between phrases and words.
• Language understanding occurs (roughly) left to right
• Syntactic trees have a flat structure, that gives no syntactic
preferences to sequences of adjunctive modifiers of the same
category (adjectives, adverbs, modifying prepositional
phrases)
• We can infer a number of things immediately from the
perception of a weird, although by no means all things

Intuitions cont’d
• There are many patterns that exist in natural language, that
can be deterministic in some cases, and must be
defeasible/probabilistic in others.
• Reliably deterministic:
• [Det N] => NP[Det N]
• [Adj N] => NP[Adj N]
• Defeasible:
• *V NP NP…+ (<1.0)> VP*V NP NP…+
• *V NP NP…+ (<1.0)> VP*V NP*NP…+…+
• Make an attempt to do search ONLY if there is a genuine
ambiguity as to what the next step in a L-R parse should be
• Second object/Relative clause modifier in ditransitive context
• Prepositional phrase attachment

Feature Structure Unification
• A traditional challenge with the HPSG theory of grammar is
that, in order to preserve the recursiveness of their grammar
rules, they were required to have a “right-branching”
structure that posited additional feature structure nodes for
each dependency-head relationship the theory posits
• This is to some extent slightly cognitively unrealistic:
• Posits an unecessary amount of structure for a syntactic parse
• Intuitively there is no syntactic distinction that should be made
between sequences of adjuncts (it’s hard to tell the difference
between “the angry green dog” and the “green angry dog.”

Lexical Representation of
Syntax
• Each word posits a sequence of head-dependency
relationships that form a “phrasal chain.”
• These chains are based on the notion that we can infer
immediately some head-dependency relationships based on
the syntactic category of the word.
• Roughly, each node in a chain is of three types (not explicitly
defined in the lexicon, but nonetheless present):
• Word Level (WordUtteranceEvent)
• Dependency Level (PhraseUtteranceEvent)
• HeadLevel (PhraseUtteranceEvent)

Lexical Representation of
Syntax
• Let’s do a quick example to show the lexical syntactic
representation:
• “the angry dog”
• With part-of-speech tags, that is:
• [Det the][Adj angry][N dog].
• The representation in di-graph form:

Lexical Representation of Syntax
PhraseUtteranceEvents

WordUtteranceEvents
Syntactic Entry for a Common Noun

CandType CandType Verb
Preposition

PartOf IsA
Noun
CandType PartOf
Noun

IsA Specifier IsA
Determiner CommonNoun
Phon

dog


WordUtteranceEvents
Syntactic Entry for an Adjective

CandType IsA Noun
Noun

PartOf
IsA
Adjective
Phon

angry

NOTE: will need to posit a dependency layer, to account for adverbs that
modify the adjective i.e. “really big”.


WordUtteranceEvents
Syntactic Entry for a Determiner

CandType CandType Verb
Preposition

PartOf
CandType IsA
Noun Noun
PartOf

IsA
Determiner
Phon

the

Grammar Rules
• In our example, we will need to have at least two rules:
• One that unifies the structures posited by the determiner to the
structures posited by the common noun
• One that unifies the structures posited by adjective, either to the
determiner or the noun
• Let’s consider this from L-R:
• First, unify the Det-NP-XP structure chain to the Adj-NP structure
chain
• Next, unify that resulting structure chain to the N-NP-XP structure
chain

Grammar Rules
• Determiner-Adjective Rule

CandType
Preposition
Verb

PartOf CandType
Noun
CandType Noun

IsA

PartOf
Noun IsA Noun
PartOf

IsA Adjective
IsA
Determiner

Phon
Phon

the angry

Grammar Rules

CandType Same
Preposition
Verb

PartOf CandType
Noun
CandType Noun

IsA

PartOf
Noun IsA Noun
PartOf

IsA Adjective
IsA
Determiner

Phon
Phon

the angry

Grammar Rules

CandType CandType
Verb Preposition

PartOf
Noun IsA CandType Noun

IsA IsA Adjective
Determiner

Phon
Phon

the angry

Grammar Rules
• We would like to allow for anywhere from 0-infinite number
of adjectives to stand between the determiner and the noun
that selects the determiner as its specifier.
• We can achieve this by explicitly stating that whenever a Det
chain and an Adj chain are unified, it’s exposed as a
determiner on the right wall of the growing parse, as opposed
to an adjective.

Grammar Rules
• Determiner-Adjective Resulting Structure

CandType CandType
Verb Preposition

PartOf
Noun IsA CandType Noun

IsA IsA Adjective
Determiner

Phon
Phon

the angry

Grammar Rules
• Determiner-Adjective Resulting Structure + NP

CandType CandType
Verb CandType
Preposition Verb

PartOf
Preposition

PartOf
Noun

IsA CandType
Noun Noun

Noun

PartOf
IsA IsA
IsA Adjective CommonNoun
Determiner

Phon
Phon
Phon

the angry dog

Grammar Rules
• Expose the resulting structure from the Det-Adj unification as
just the Det structure:

XP XP

NP NP

Det Adj Spr N

Grammar Rules

Border

XP XP
Frontier

NP NP

Det Adj Spr N

Grammar Rules

Border

XP XP
Same Frontier

NP NP
Same

Det Adj Spr N

Grammar Rules
 
<constraint shouldFalsify="false"> <constraint shouldFalsify="false">
Border(?ba, ?t0, ?w)^ Border(?ba, ?t0, ?w)^
Border(?bb, ?t0, ?w)^ Border(?bb, ?t0, ?w)^
Frontier(?fa, ?t1, ?w)^ Frontier(?fa, ?t1, ?w)^
Frontier(?fb, ?t1, ?w)^ Frontier(?fb, ?t1, ?w)^
Meets(?t0, ?t1, E, ?w)^ Meets(?t0, ?t1, E, ?w)^
PartOf(?ba, ?bb, E, ?w)^ PartOf(?ba, ?bb, E, ?w)^
PartOf(?fa, ?fb, E, ?w)^ PartOf(?fa, ?fb, E, ?w)^
IsA(?ba, Determiner, E, ?w)^ IsA(?ba, Determiner, E, ?w)^
IsA(?bb, Noun, E, ?w)^ IsA(?bb, Noun, E, ?w)^
IsA(?fa, Adjective, E, ?w)^ Specifier(?fa, ?spr, E, ?w)^
IsA(?fb, Noun, E, ?w) IsA(?spr, Determiner, E, ?w)^
==> IsA(?fb, Noun, E, ?w)^
Same(?bb, ?fb, E, ?w)^ Heard(?wue, E, ?w)^
Border(?ba, ?t1, ?w)^ IsA(?wue, WordUtteranceEvent, ?t1, ?w)
</constraint> ==>
Same(?ba, ?spr, E, ?w)^
Same(?bb, ?fb, E, ?w)^
Border(?wue, ?t1, ?w)^
_NPSPR(?ba, ?bb, ?fa, ?fb, E, ?w)
</constraint>

Grammar Rules

*send+ *john+ *a+ *message+ *that+ *says+ *“hi”+.

Grammar Rules

[V send] [N john] [Det a] [N message] [RelP that] [V says] [Q “hi”+.

Grammar Rules

XP XP XP NP XP

VP NP NP NP VP VP NP


Grammar Rules

VP

NP

VP

NP

NP


Grammar Rules
• Benefits of this feature-structure unification parse:
• Captures the intuition that when we hear a word, and posit its feature structure, we can infer the
existence of not only the word’s direct feature structure (usually generated by lexical rules) but also
the existence of additional structures and their head/dependency relationships, and some definition
of the values in the structure.
• Ambiguities (i.e. the head of an NP) are resolved from L-R through lazy definitions and unificiation of
under-defined structures to well-defined structures in terms of particular features.
• Posits no more additional structures in the parse tree than is necessary in order to reflect a parse,
whereas theories like HPSG posited by a large number of structures in a branching tree in order to
preserve the recursivity of its grammar rules.
• However, we have shown that with feature structure unification, at least in theory, we can preserve
recursivity of many of the rules without requiring a left or right branching structure.
• All of the necessary structure to build a parse are known from the beginning.

Grammar Rules!
• The future:
• Ungrammaticality: when objects aren’t where they are supposed to be, search for a likely head-
dependency relationship
• Missing arguments: “Car is big.”
• Extra words (rare to have full content words be considered extra, but occurs in natural language: “I saw the, um,
car.”)
• Dependents out of order: “Give the car me.”
• Dangling dependent: “
• Will require a good branch and bound system, that only performs search when what is expected/predicted
reasonably is violated.
• Give a feature-structure unification account of garden path sentence
• Should be fairly natural given the L-R predictive nature of the parser
• Attach a semantic representation that generates word-sense based on head-dependency
relationships.
• Syntax should be closely tied to semantics, in that both serve to help compute each other to varying degrees.
• Examine discourse from a syntactic perspective, and syntax from a discourse perspective, and use to
disambiguate simultaneously:

Notes on Theory (boring)
• By having a lexical representation that is closely tied to the syntax, a number of advantages
fall out:
• Parsimony: by allowing a lot of information to be loosely defined/undefined at the lexical
level, we do not need to posit additional lexical entries to cover all possible configurations of
a phrases arguments in the entry, nor do we need an excessive number of lexical rules to
generate these representations.
• Generativity: a word’s sense is at least in part generated by its relationship to its dependents
and head, and the semantic/syntactic type that these dependents/heads have in theory can
compute a words sense on the fly (inspired by GL theory from Pustejovsky).
• Context embedding: by tying your theory of the lexicon closely to syntactic theory, you move
towards embedding your lexical representation in a cognitive system that is closely tied to the
way words are ACTUALLY used.

Lexical Mosaics
• Thus, we can see that the sense of words comes from a number of
different locations:
• Memory
• Syntactic context
• Pragmatic/Discourse factors
• It is the hope for future research to tie these together in an
organized way to give a theory on lexical representation that is tied
closely to these factors, in a computable and tractable manner.
• Early goals:
• Compute word senses from syntactic context + memory (very
difficult)
• Use syntactic context to disambiguate lexical ambiguity
• Use generative word sense to disambiguate syntactic ambiguity
• Simultaneously attempt to give a computational account of lexical
memory, syntactic parsing, and pragmatic/discourse.

Feature Structure Unification Syntactic Parser 2.0

More Related Content

What's hot (20)

Viewers also liked (7)

Similar to Feature Structure Unification Syntactic Parser 2.0 (7)

Recently uploaded (20)

Feature Structure Unification Syntactic Parser 2.0