Coreference
Resolution
USING HOBBS‟S ALGORITHM
Hemant Kumar (10579)
Babul Bhanu (10545)
Pratheek Adidela (10583)
Shekhar Kumar (09562)
Contents


What is coreference resolution



Anaphoric and Cataphoric references



Direct and indirect anaphora



Hobbs‟s algorithm



Hobb‟s algorithm for Hindi



Problems in implementation



Applications
What is Coreference Resolution


In computational linguistics, Coreference resolution is a well-studied
problem in discourse. To derive the correct interpretation of text, or
even to estimate the relative importance of various mentioned
subjects, pronouns and other referring expressions must be
connected to the right individuals.



There are two types of references: When the reader must look back
to the previous context,
Coreference
is
called
anaphoric
reference. When the reader must look forward, it is cataphoric
reference.
Anaphoric and Cataphoric
references


Cataphora
In linguistics, cataphora is used to first insert an expression or word
that co-refers with a later expression in the discourse. An example
of strict, sentence-internal cataphora in English is the following
sentence
“When he arrived home, John went to sleep.”



Anaphora
In linguistics, anaphora is the use of an expression the interpretation
of which depends upon another expression in context (its
antecedent or postcedent).In the sentence
“Sally arrived, but nobody saw her”
the pronoun „her‟ is anaphoric, referring back to Sally.
Hobbs‟s algorithm


Hobbs‟s algorithm is mainly focused on “surface parse tree”. By this is
means that the tree that exhibits the grammatical structure of the
sentences (its division into subject, verb, objects, adverbials, etc.)
without permuting or omitting any of the words in a sentence.



The naïve algorithm traverses the surface parse tree in a particular
order looking for a noun phrase of the correct gender and number.
Hobbs‟s algorithm for Hindi


Pronouns in Hindi exhibit a great deal of ambiguity.



Pronouns in the first, second and third person do not convey any
information about the gender



Redefined the grammar for Hindi
EXAMPLE 1
Non-Reflexive
pronoun

S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
Previous
sentence

S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
uske

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

EXAMPLE 2
Reflexive pronoun

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
S1

VP2

NP_erg(SUB)

Nbar

Noun
Mr.Smith

Postp
ne

NP2_acc(DO)

Nbar

Postp
ko

Noun
Driver
Pronoun_poss
apne

VP1

VP

PP_loc

NP1(PO)

postp
mein
Nbar

Noun
truck

Verb
dekha
Challenges in implementation


Parts of speech tagger



Richness of word database



In Hindi the gender of noun is identified by using verbs
Applications


English – Hindi machine translation



Machine learning
THANK YOU

Co reference resolution