NLP for CP
Addressing Constraint Programming with Natural Language Processing
Home
Resources
Publications
Correct
predictions are in
blue
. If we detect only a subset of a labelled sentence, we highlight the caught part as
blue
, the missing part
light blue.
False positives
are in
green
and
false negatives
are in
red
.
Problem Bid_Selection — Constraint detection
Several
bidders
are
bidding
for
a
large
contract
.
The
contract
is
divided
into
many
tasks
.
Some
tasks
are
critical
and
must
be
assigned
to
a
bidder
.
Others
are
not
critical
and
a
penalty
is
charged
if
unassigned
.
Each
bidder
can
bid
for
a
subset
of
tasks
and
each
task
can
be
optional
or
mandatory
in
the
bid
.
An
optional
task
bid
can
be
accepted
separately
,
but
mandatory
task
bids
are
all-or-nothing
:
mandatory
tasks
must
be
all
accepted
or
all
rejected
for
each
bid
.
The
objective
is
to
find
the
cheapest
assignment
of
tasks
to
bidders
.
Problem Bid_Selection — Detection of the decisions and objects to be modeled
Several
bidders
are
bidding
for
a
large
contract
.
The
contract
is
divided
into
many
tasks
.
Some
tasks
are
critical
and
must
be
assigned
to
a
bidder
.
Others
are
not
critical
and
a
penalty
is
charged
if
unassigned
.
Each
bidder
can
bid
for
a
subset
of
tasks
and
each
task
can
be
optional
or
mandatory
in
the
bid
.
An
optional
task
bid
can
be
accepted
separately
,
but
mandatory
task
bids
are
all-or-nothing
:
mandatory
tasks
must
be
all
accepted
or
all
rejected
for
each
bid
.
The
objective
is
to
find
the
cheapest
assignment
of
tasks
to
bidders
.
Back to list