• Semantics by its dictionary definition is the study of

meaning, and
• parsing is the examination of something in a
minute way, that is, identifying and relating the
pieces of information being parsed
• semantic parsing is the process of identifying
meaning chunks contained in an information
signal in an attempt to transform it into some data
structure that can be manipulated by a computer
to perform higher level tasks
• Because semantics is such a vague term,
• it has been used to represent various depths of
representations,
– from something as basic as identifying domain-specific
relations between entities,
– to the more intermediate task of identifying the roles that
various entities and artifacts play in an event,
– To converting a text to a series of specific logical expressions
• we restrict its interpretation to the study of mapping
naturally occurring text to some representation
• that is amenable to manipulation by computers for the
purpose of achieving some goals
– such as retrieving information, answering a question, populating
a database, or taking an action
 Introduction
• research in language understanding is the identification of a
meaning representation
– to allow reasoning systems to make deductions
– it can be used across many domains with little to no adaptation
• Not clear whether a final, low-level, detailed semantic
representation covering various applications that use some
form of language interface can be achieved or whether an
ontology can be created that can capture the various
granularities and aspects of meanings that are embodied in
such a variety of applications—none has yet been created
• Two compromise approaches have emerged in the natural
language processing community for language understanding
• In the first approach, a specific, rich meaning representation is
created for a limited domain for use by applications that are
restricted to that domain,
– such as air travel reservations, football game simulations, or querying a
geographic database.
– Systems are then crafted to generate output from text in this rich, domain
specific meaning representation
• In the second approach, a related set of intermediate meaning
representations is created,
– going from lowlevel analysis to a midlevel analysis, and
– the bigger understanding task is divided into multiple,
– smaller pieces that are more manageable,
– such as word sense disambiguation followed by predicate argument
structure recognition
– Unlike the first approach, each meaning representation, while covering
only a small part of the overall meaning, is not tied to a specific domain,
and so the data and methods created for it are similarly general purpose
• The task of producing the output of the first type is often
called deep semantic parsing, and the task of producing the
output of the second type is often called shallow semantic
parsing
• the first approach is so specific that porting to every new
domain can require anywhere from a few modifications to
almost reworking the solution from scratch
– the reusability of the representation across domains is very limited
• The problem with the latter approach is that it is
– extremely difficult to construct a general purpose ontology and
create symbols that are shallow enough to be learnable
– but detailed enough to be useful for all possible applications
 Semantic Interpretation
• semantic interpretation, which involves various components that
together let us define a representation of a text that can be fed into a
computer to allow further computational manipulations and search,
which are prerequisite for any language understanding system or
application
• seminal work by Chomsky, Syntactic Structures [ 1 ], which introduced
the concept of a transformational phrase structure grammar
• Shortly after Chomsky’s 1957 book, Katz and Fodor [ 2 ] published the
first work treating semantics within the generative grammar paradigm.
• They found that Chomsky’s transformational grammar was not a
complete description of language because it did not account for
meaning
• A semantic theory should be able to
– Explain sentences having ambiguous meanings
– Resolve the ambiguities of words in context.
– Identify meaningless but syntactically well formed
sentences
– Identify syntactically or transformationally
unrelated paraphrases of a concept having the
same semantic content
 Structural Ambiguity
• Structure refer to the syntactic structure of
sentences
• Means transforming a sentence into its
underlying syntactic representation
• Because syntax and semantics are related,
syntax has become the first stage of
processing followed by various other stages in
the process of semantic interpretation
 Word Sense
• the case that the same word type, or word lemma, is used in
different contexts and with different morphological variants
to represent different entities or concepts in the world.
– For example, nail - part of the human anatomy, the generally
metallic object used to secure other objects
• Humans are adept at identifying, through context, which
sense of the word is intended by the author or speaker
– 1. He nailed the loose arm of the chair with a hammer.
– 2. He bought a box of nails from the hardware store.
– 3. He went to the beauty salon to get his nails clipped.
– 4. He went to get a manicure. His nails had grown very long.
 Entity and Event Resolution
• important component of semantic interpretation -
identification of various entities that are sprinkled across
the discourse using the same or different phrases
• Reconciling what type of entity or event is being
considered, along with disambiguating various ways in
which the same entity is referred to over a discourse, is
critical to creating a semantic representation
• Two predominant tasks have become popular over the
years:
– named entity recognition and coreference resolution.
– These two tasks fall under the umbrella of information extraction
 Predicate-Argument Structure
• Once we have the word senses, entities, and events
identified
• identifying the participants of the entities in these
events
• Resolving the argument structure of the predicates
in a sentence is where we identify which entities
play what part in which event
• this process can be defined as the identification of
who did what to whom, when, where, why, and how
 Meaning Representation
• final process of the semantic interpretation is to
build a semantic representation or meaning
representation that can then be manipulated by
algorithms - deep representation
• due to the lack of deep representation, most studies
in this area have been application dependent, or
dependent on the domain of particular applications
– Which river is the longest?
– answer(x 1, longest(x1 river(x 1)))
• This is a domainspecificapproach
 SYSTEM PARADIGMS
• It is important to get a perspective on the
various primary dimensions on which the
problem of semantic interpretation has been
tackled.
• The following are some approaches that lend
themselves to practical applications
• 1 SYSTEM ARCHITECTURE
• A] Knoledge based: Uses a predefined set of
rules or knoledge base
• B] Unsupervised: Minimal human intervention
• C]Supervised:Manual annotation of some
phenomena
• D]Semi-supervised: Either using machine
generated output or bootstrapping
• 2] Scope
• A]Domain dependent: Specific to a particular
domain
• B]Domain independent: Techniques are
applicable to domains without little or no
change
• 3]Coverage
• A] Shallow:These systems tend to produce an
intermediate representations that can then be
converted to one that a machine can base its
acttions on
• B] Deep: These systems usually create a
terminal representation that is directly
consumed by a machine or application