nltk.sem.boxer module

An interface to Boxer.

This interface relies on the latest version of the development (subversion) version of C&C and Boxer.

Usage

Set the environment variable CANDC to the bin directory of your CandC installation. The models directory should be in the CandC root directory. For example:

/path/to/candc/
bin/
    candc
    boxer
models/
    boxer/

class nltk.sem.boxer.AbstractBoxerDrs

Bases: object

atoms()

clean()

renumber_sentences(f)

variable_types()

variables()

Returns:

(set<variables>, set<events>, set<propositions>)

class nltk.sem.boxer.Boxer

Bases: object

This class is an interface to Johan Bos’s program Boxer, a wide-coverage semantic parser that produces Discourse Representation Structures (DRSs).

__init__(boxer_drs_interpreter=None, elimeq=False, bin_dir=None, verbose=False, resolve=True)

Parameters:

• boxer_drs_interpreter – A class that converts from the AbstractBoxerDrs object hierarchy to a different object. The default is NltkDrtBoxerDrsInterpreter, which converts to the NLTK DRT hierarchy.

• elimeq – When set to true, Boxer removes all equalities from the DRSs and discourse referents standing in the equality relation are unified, but only if this can be done in a meaning-preserving manner.

• resolve – When set to true, Boxer will resolve all anaphoric DRSs and perform merge-reduction. Resolution follows Van der Sandt’s theory of binding and accommodation.

interpret(input, discourse_id=None, question=False, verbose=False)

Use Boxer to give a first order representation.

Parameters:

• input – str Input sentence to parse

• occur_index – bool Should predicates be occurrence indexed?

• discourse_id – str An identifier to be inserted to each occurrence-indexed predicate.

Returns:

drt.DrtExpression

interpret_multi(input, discourse_id=None, question=False, verbose=False)

Use Boxer to give a first order representation.

Parameters:

• input – list of str Input sentences to parse as a single discourse

• occur_index – bool Should predicates be occurrence indexed?

• discourse_id – str An identifier to be inserted to each occurrence-indexed predicate.

Returns:

drt.DrtExpression

interpret_multi_sents(inputs, discourse_ids=None, question=False, verbose=False)

Use Boxer to give a first order representation.

Parameters:

• inputs – list of list of str Input discourses to parse

• occur_index – bool Should predicates be occurrence indexed?

• discourse_ids – list of str Identifiers to be inserted to each occurrence-indexed predicate.

Returns:

drt.DrtExpression

interpret_sents(inputs, discourse_ids=None, question=False, verbose=False)

Use Boxer to give a first order representation.

Parameters:

• inputs – list of str Input sentences to parse as individual discourses

• occur_index – bool Should predicates be occurrence indexed?

• discourse_ids – list of str Identifiers to be inserted to each occurrence-indexed predicate.

Returns:

list of drt.DrtExpression

set_bin_dir(bin_dir, verbose=False)

class nltk.sem.boxer.BoxerCard

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var, value, type)

renumber_sentences(f)

class nltk.sem.boxer.BoxerDrs

Bases: AbstractBoxerDrs

__init__(refs, conds, consequent=None)

atoms()

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerDrsParser

Bases: DrtParser

Reparse the str form of subclasses of AbstractBoxerDrs

__init__(discourse_id=None)

Parameters:

type_check (bool) – should type checking be performed to their types?

attempt_adjuncts(expression, context)

get_all_symbols()

This method exists to be overridden

get_next_token_variable(description)

handle(tok, context)

This method is intended to be overridden for logics that use different operators or expressions

nullableIntToken()

class nltk.sem.boxer.BoxerEq

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var1, var2)

atoms()

renumber_sentences(f)

class nltk.sem.boxer.BoxerIndexed

Bases: AbstractBoxerDrs

__init__(discourse_id, sent_index, word_indices)

atoms()

class nltk.sem.boxer.BoxerNamed

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var, name, type, sense)

change_var(var)

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerNot

Bases: AbstractBoxerDrs

__init__(drs)

atoms()

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerOr

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, drs1, drs2)

atoms()

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerOutputDrsParser

Bases: DrtParser

__init__(discourse_id=None)

This class is used to parse the Prolog DRS output from Boxer into a hierarchy of python objects.

attempt_adjuncts(expression, context)

get_all_symbols()

This method exists to be overridden

handle(tok, context)

This method is intended to be overridden for logics that use different operators or expressions

handle_condition(tok, indices)

Handle a DRS condition

Parameters:

indices – list of int

Returns:

list of DrtExpression

handle_drs(tok)

parse(data, signature=None)

Parse the expression.

Parameters:

• data – str for the input to be parsed

• signature – dict<str, str> that maps variable names to type strings

Returns:

a parsed Expression

parse_condition(indices)

Parse a DRS condition

Returns:

list of DrtExpression

parse_drs()

parse_index()

parse_variable()

class nltk.sem.boxer.BoxerPred

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var, name, pos, sense)

change_var(var)

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerProp

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var, drs)

atoms()

clean()

referenced_labels()

renumber_sentences(f)

class nltk.sem.boxer.BoxerRel

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, var1, var2, rel, sense)

clean()

renumber_sentences(f)

class nltk.sem.boxer.BoxerWhq

Bases: BoxerIndexed

__init__(discourse_id, sent_index, word_indices, ans_types, drs1, variable, drs2)

atoms()

clean()

renumber_sentences(f)

class nltk.sem.boxer.NltkDrtBoxerDrsInterpreter

Bases: object

__init__(occur_index=False)

interpret(ex)

Parameters:

ex – AbstractBoxerDrs

Returns:

DrtExpression

class nltk.sem.boxer.PassthroughBoxerDrsInterpreter

Bases: object

interpret(ex)

exception nltk.sem.boxer.UnparseableInputException

Bases: Exception