Example sentences provide an intuitive means of grasping the meaning of a word, and are frequently used to complement conventional word definitions. When a word has multiple meanings, it is useful to have example sentences for specific senses (and hence definitions) of that word rather than indiscriminately lumping all of them together. In this paper, we investigate to what extent such sense-specific example sentences can be extracted from parallel corpora using lexical knowledge bases for multiple languages as a sense index. We use word sense disambiguation heuristics and a cross-lingual measure of semantic similarity to link example sentences to specific word senses. From the sentences found for a given sense, an algorithm then selects a smaller subset that can be presented to end users, taking into account both representativeness and diversity. Preliminary results show that a precision of around 80% can be obtained for a reasonable number of word senses, and that the subset selection yields convincing results.
4. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
a thin, sharp-pointed metal pin with a raised spiral
thread running around it and a slotted head, used to join
things together by being rotated in under pressure
(Concise OED)
Use a crosshead screwdriver to tighten the screws inserted
in the pre-fixed connectors.
(Web)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
5. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
a thin, sharp-pointed metal pin with a raised spiral
thread running around it and a slotted head, used to join
things together by being rotated in under pressure
(Concise OED)
Use a crosshead screwdriver to tighten the screws inserted
in the pre-fixed connectors.
(Web)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
7. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
any sentence that contains a word (being used in a speciļ¬c
sense)
allow the user to grasp a wordās meaning
see circumstances a word would typically be used in
traditional intensional word deļ¬nitions may be too confusing
humans used to deriving meaning from context
users can verify whether they have understood deļ¬nition correctly
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
8. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
any sentence that contains a word (being used in a speciļ¬c
sense)
allow the user to grasp a wordās meaning
see circumstances a word would typically be used in
possible contexts, e.g. child vs. youngster
typical collocations, e.g. to give birth or birth rate
but not *to give nascence or *nascence rate
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
9. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
=ā most modern dictionaries include example sentences
number, length often limited
digital dictionaries: tight space constraints of print media no
longer apply!
larger number of example sentences can be presented to the
user on demand
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
10. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
=ā most modern dictionaries include example sentences
number, length often limited
digital dictionaries: tight space constraints of print media no
longer apply!
larger number of example sentences can be presented to the
user on demand
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
11. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
=ā most modern dictionaries include example sentences
number, length often limited
digital dictionaries: tight space constraints of print media no
longer apply!
larger number of example sentences can be presented to the
user on demand
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
12. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Example Sentences
=ā most modern dictionaries include example sentences
number, length often limited
digital dictionaries: tight space constraints of print media no
longer apply!
larger number of example sentences can be presented to the
user on demand
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
13. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Goals
automatically obtain example sentences for a speciļ¬c sense of
a word
choose set of representative sentences to present to user
distinguish senses:
There were many bats flying out of the cave.
vs.
In professional baseball, only wooden bats
are permitted.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
14. Introduction
Example Extraction
Example Selection
Results
Conclusion
Introduction
Goals
automatically obtain example sentences for a speciļ¬c sense of
a word
choose set of representative sentences to present to user
not all examples are equally useful
screen space may be limited (can still show more only on demand)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
16. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Index (Dictionary)
English: Princeton WordNet 3.0
Spanish: Spanish WordNet
Ļ(t): get senses for term t
Ļ(t, s): is sense s a sense of term t?
behind the scenes: morphological analysis, multi-word
expression detection
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
17. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Index (Dictionary)
English: Princeton WordNet 3.0
Spanish: Spanish WordNet
Ļ(t): get senses for term t
Ļ(t, s): is sense s a sense of term t?
behind the scenes: morphological analysis, multi-word
expression detection
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
18. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Index (Dictionary)
English: Princeton WordNet 3.0
Spanish: Spanish WordNet
Ļ(t): get senses for term t
Ļ(t, s): is sense s a sense of term t?
behind the scenes: morphological analysis, multi-word
expression detection
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
19. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Disambiguation
disambiguate word occurrences, then use sentence as example
for those word senses
ļ¬ne-grained WSD not reliable enough (cf. SemEval results)
idea: use parallel corpora, jointly look at both versions of text
=ā greater accuracy can be achieved
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
20. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Disambiguation
disambiguate word occurrences, then use sentence as example
for those word senses
ļ¬ne-grained WSD not reliable enough (cf. SemEval results)
idea: use parallel corpora, jointly look at both versions of text
=ā greater accuracy can be achieved
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
21. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Disambiguation
disambiguate word occurrences, then use sentence as example
for those word senses
ļ¬ne-grained WSD not reliable enough (cf. SemEval results)
idea: use parallel corpora, jointly look at both versions of text
=ā greater accuracy can be achieved
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
22. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Sense Disambiguation
disambiguate word occurrences, then use sentence as example
for those word senses
ļ¬ne-grained WSD not reliable enough (cf. SemEval results)
idea: use parallel corpora, jointly look at both versions of text
=ā greater accuracy can be achieved
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
25. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Parallel Disambiguation
req.: text available in two languages a, b
good news: more and more parallel corpora available
word alignment
compute score
wsd(sa|ta, tb) = wsd(sa|ta) Ļ(ta,sa)csim(tb,sa)
s āĻ(ta)
Ļ(ta,s )csim(tb,s )
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
26. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Parallel Disambiguation
req.: text available in two languages a, b
good news: more and more parallel corpora available
word alignment
compute score
wsd(sa|ta, tb) = wsd(sa|ta) Ļ(ta,sa)csim(tb,sa)
s āĻ(ta)
Ļ(ta,s )csim(tb,s )
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
27. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Parallel Disambiguation
req.: text available in two languages a, b
good news: more and more parallel corpora available
word alignment
compute score
wsd(sa|ta, tb) = wsd(sa|ta) Ļ(ta,sa)csim(tb,sa)
s āĻ(ta)
Ļ(ta,s )csim(tb,s )
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
28. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Components
csim(tb, sa): cross-lingual similarity
monolingual WSD: compare bag-of-words vector for term
context with sense context (constructed from deļ¬nitions, etc.)
Semantic Similarity sim(s1, s2)
identify only near-identical senses (e.g. of house and home),
not arbitrary associations (e.g. house and door)
csim(tb, sa) =
sbāĻ(tb)
sim(sa, sb) wsd(sb|tb)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
29. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Components
csim(tb, sa): cross-lingual similarity
monolingual WSD: compare bag-of-words vector for term
context with sense context (constructed from deļ¬nitions, etc.)
Semantic Similarity sim(s1, s2)
identify only near-identical senses (e.g. of house and home),
not arbitrary associations (e.g. house and door)
wsd(s|t) = Ļ(t, s) Ī± + v(s)T
v(t)
||v(s)|| ||v(t)||
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
30. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Components
csim(tb, sa): cross-lingual similarity
monolingual WSD: compare bag-of-words vector for term
context with sense context (constructed from deļ¬nitions, etc.)
Semantic Similarity sim(s1, s2)
identify only near-identical senses (e.g. of house and home),
not arbitrary associations (e.g. house and door)
sim(s1, s2) =
ļ£±
ļ£“ļ£“ļ£“ļ£²
ļ£“ļ£“ļ£“ļ£³
1 s1 = s2
1 s1, s2 in near-synonymy relationship
1 s1, s2 in hypernymy/hyponymy relationship
0 otherwise
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
31. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Extraction
Extraction
Use as example sentence iļ¬ score suļ¬ciently high
wsd(sa|ta, tb) = wsd(ta, sa) Ļ(ta,sa)csim(tb,sa)
s āĻ(ta)
Ļ(ta,s )csim(tb,s )
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
33. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Task Motivation
for computational applications: more data =ā better data
for human users: a good limited selection should be provided
at ļ¬rst
assumption: space constraint k - number of sentences
goal: choose a good set of k example sentences
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
34. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Task Motivation
for computational applications: more data =ā better data
for human users: a good limited selection should be provided
at ļ¬rst
assumption: space constraint k - number of sentences
goal: choose a good set of k example sentences
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
35. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Task Motivation
for computational applications: more data =ā better data
for human users: a good limited selection should be provided
at ļ¬rst
assumption: space constraint k - number of sentences
goal: choose a good set of k example sentences
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
36. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good example sentence?
one that showcases how a word is used in context
(typical prepositions, collocations, etc.)
one that helps in grasping the meaning
related work by Rychly et al. (2008):
one that is intelligible to learners
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
37. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good example sentence?
one that showcases how a word is used in context
(typical prepositions, collocations, etc.)
one that helps in grasping the meaning
related work by Rychly et al. (2008):
one that is intelligible to learners
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
38. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good example sentence?
one that showcases how a word is used in context
(typical prepositions, collocations, etc.)
one that helps in grasping the meaning
related work by Rychly et al. (2008):
one that is intelligible to learners
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
39. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Assets
example sentences can be thought of as having certain assets
6 diļ¬erent classes of n-gram assets
1 class of assets for entire original sentence
e.g. for account:
containing frequent bigram bank account can be an asset
containing frequent trigram to account for can be an asset
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
40. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Assets
example sentences can be thought of as having certain assets
6 diļ¬erent classes of n-gram assets
1 class of assets for entire original sentence
1: original unigram
2-5: bigram with preceding/following, trigram, etc.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
41. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Assets
example sentences can be thought of as having certain assets
6 diļ¬erent classes of n-gram assets
1 class of assets for entire original sentence
weights w(a) = f (x,a)
n
i=1 f (xi ,a)
, etc.
=ā higher weight for open an account than for Peterās chequing
account
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
42. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Assets
example sentences can be thought of as having certain assets
6 diļ¬erent classes of n-gram assets
1 class of assets for entire original sentence
weight: cosine similarity with sense deļ¬nition
=ā bias towards explanatory sentences
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
43. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good set of example sentences?
Select sentences with greatest total asset weights?
Instead: maximize
aā
xāC
A(x)
w(a)
Problem is NP-hard (proof via Vertex Cover reduction)
āā use greedy heuristic
No: Most frequent expressions would dominate the result set.
Need diversity!
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
44. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good set of example sentences?
Select sentences with greatest total asset weights?
Instead: maximize
aā
xāC
A(x)
w(a)
Problem is NP-hard (proof via Vertex Cover reduction)
āā use greedy heuristic
each asset in result set only counted once
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
45. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good set of example sentences?
Select sentences with greatest total asset weights?
Instead: maximize
aā
xāC
A(x)
w(a)
Problem is NP-hard (proof via Vertex Cover reduction)
āā use greedy heuristic
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
46. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
What is a good set of example sentences?
Select sentences with greatest total asset weights?
Instead: maximize
aā
xāC
A(x)
w(a)
Problem is NP-hard (proof via Vertex Cover reduction)
āā use greedy heuristic
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
47. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Greedy Heuristic to select set C
Greedily select highest-weighted sentence x:
x ā argmax
xāXC aāA(x)
w(a)
Then set the weights w(a) of all assets a ā A(x) to zero
=ā ranked list obtained (useful!)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
48. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Greedy Heuristic to select set C
Greedily select highest-weighted sentence x:
x ā argmax
xāXC aāA(x)
w(a)
Then set the weights w(a) of all assets a ā A(x) to zero
=ā ranked list obtained (useful!)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
49. Introduction
Example Extraction
Example Selection
Results
Conclusion
Example Selection
Greedy Heuristic to select set C
Greedily select highest-weighted sentence x:
x ā argmax
xāXC aāA(x)
w(a)
Then set the weights w(a) of all assets a ā A(x) to zero
=ā ranked list obtained (useful!)
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
51. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Resources
OPUS corpora (OpenSubtitles, OpenOļ¬ce.org collections)
and Reuters RCV1 for non-disambiguated sentence selection
GIZA++/UPlug for lexical alignment
Princeton WordNet 3.0 and Spanish WordNet
(+ sense mappings for compatibility)
TreeTagger for morphological analysis
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
52. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Resources
OPUS corpora (OpenSubtitles, OpenOļ¬ce.org collections)
and Reuters RCV1 for non-disambiguated sentence selection
GIZA++/UPlug for lexical alignment
Princeton WordNet 3.0 and Spanish WordNet
(+ sense mappings for compatibility)
TreeTagger for morphological analysis
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
53. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Resources
OPUS corpora (OpenSubtitles, OpenOļ¬ce.org collections)
and Reuters RCV1 for non-disambiguated sentence selection
GIZA++/UPlug for lexical alignment
Princeton WordNet 3.0 and Spanish WordNet
(+ sense mappings for compatibility)
TreeTagger for morphological analysis
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
54. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Resources
OPUS corpora (OpenSubtitles, OpenOļ¬ce.org collections)
and Reuters RCV1 for non-disambiguated sentence selection
GIZA++/UPlug for lexical alignment
Princeton WordNet 3.0 and Spanish WordNet
(+ sense mappings for compatibility)
TreeTagger for morphological analysis
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
55. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Examples from OpenSubtitles Corpus
line (something, as a
cord or rope, that is long
and thin and ļ¬exible)
I got some ļ¬shing line if you want
me to stitch that.
Von Sefelt, get the stern line.
line (the descendants of
one individual)
What line of kings do you descend
from?
My line has ended.
catch (catch up with
and possibly overtake)
Heās got 100 laps to catch Beau
Brandenburg if he wants to become
world champion.
They wonāt catch up.
catch (grasp with the I didnāt catch your name.
mind or develop an
understanding of)
Sorry, I didnāt catch it.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
56. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Examples from OpenSubtitles Corpus
talk (exchange thoughts,
talk with)
Why donāt we have a seat and talk it
over.
Okay, Iāll talk to you but one
condition...
talk (use language) But weāll be listening from the kitchen
so talk loud.
You spit when you talk.
opening (a ceremony
accompanying the start
of some enterprise)
We donāt have much time until the
opening day of Exhibition.
What a disaster tomorrow is the
opening ceremony!
opening (the ļ¬rst
performance, as of a
theatrical production)
It will be rehearsed in the morning
ready for the opening tomorrow night.
You ready for our big opening night?
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
57. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Sense-disambiguated Example Sentences
Corpus Covered
Senses
Example
Sentences
Accuracy
(Wilson
interval)
OpenSubtitles en-es 13,559 117,078 0.815 Ā± 0.081
OpenSubtitles es-en 8,833 113,018 0.798 Ā± 0.090
OpenOļ¬ce.org en-es 1,341 13,295 0.803 Ā± 0.081
OpenOļ¬ce.org es-en 932 11,181 0.793 Ā± 0.087
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
58. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
error analysis:
(1) incorrect lexical alignments unlikely to lead to incorrect
disambiguation
(2) incomplete sense inventories can lead to mistakes
(3) also, on a few occasions, the morphological analyser led to
wrong results
implications for future work:
(1) better monolingual WSD
(2) additional languages, especially phylogenetically unrelated
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
59. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
error analysis:
(1) incorrect lexical alignments unlikely to lead to incorrect
disambiguation
(2) incomplete sense inventories can lead to mistakes
(3) also, on a few occasions, the morphological analyser led to
wrong results
implications for future work:
(1) better monolingual WSD
(2) additional languages, especially phylogenetically unrelated
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
60. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Rankings for OpenSubtitles Corpus
being or located on or
directed toward the
1. In America we drive on the right
side of the road.
side of the body to the
east when facing north
2. Iāll tie down your right arm so
you can learn to throw a left.
3. If we wait from the right side, we
have an advantage there.
put up with something 1. You canāt stand it, can you?
or somebody
unpleasant
2. You really think I can tolerate
such an act?
3. No one can stand that harmonica
all day long.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
61. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Rankings for OpenSubtitles Corpus
using or providing or 1. Not the electric chair.
producing or
transmitting or
2. Some electrical current
circulating through my body.
operated by electricity 3. Near as I can tell itās an
electrical impulse.
take something or
somebody with
1. And they were kind enough to
take me in here.
oneself somewhere 2. It conveys such a great feeling.
3. We interrupt this program to
bring you a special news bulletin.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
62. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Rankings for long in RCV1 Corpus
1. In the long term interest rate market, the yield of the key
182nd 10 year Japanese government bond (JGB) fell to
2.060 percent early on Tuesday, a record low for any
benchmark 10-year JGB.
2. āThe government and opposition have gambled away the last
chance for a long time to prove they recognise the countryās
problems, and that they put the national good above their
own power interestsā, news weekly Der Spiegel said.
3. As long as the index keeps hovering between 957 and 995,
we will maintain our short term neutral recommendation.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
63. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Rankings for purchase in RCV1 Corpus
1. Romaniaās State Ownership Fund (FPS), the countryās main
privatisation body, said on Wednesday it had accepted ļ¬ve
bids for the purchase of a 50.98 percent stake in the largest
local cement maker Romcim.
2. Grand Hotel Group said on Wednesday it has agreed to
procure an option to purchase the remaining 50 percent of
the Grand Hyatt complex in Melbourne from hotel developer
and investor Lustig & Moar.
3. The purchase price for the business, which had 1996
calendar year sales of about $25 million, was not disclosed.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
64. Introduction
Example Extraction
Example Selection
Results
Conclusion
Results
Rankings for colonial in RCV1 Corpus
1. Hong Kong came to the end of 156 years of British colonial
rule on June 30 and is now an autonomous capitalist region
of China, running all its own aļ¬airs except defence and
diplomacy.
2. The letter was sent in error to the embassy of Portugal ā the
former colonial power in East Timor ā and was neither
returned nor forwarded to the Indonesian embassy.
3. Sino-British relations hit a snag when former Governor Chris
Patten launched electoral reforms in the twilight years of
colonial rule despite ļ¬erce opposition by Beijing.
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
66. Introduction
Example Extraction
Example Selection
Results
Conclusion
Conclusion
Framework for:
extracting sense-disambiguated example sentences from
parallel corpora
selecting limited numbers of sentences given space constraints
Future Work:
better disambiguation, e.g. additional languages, better
techniques
additional input for selection: sentence length, deļ¬nition
extraction techniques
integrated user interface for UWN (Universal Wordnet)
Contact: demelo@mpi-inf.mpg.de
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
67. Introduction
Example Extraction
Example Selection
Results
Conclusion
Conclusion
Framework for:
extracting sense-disambiguated example sentences from
parallel corpora
selecting limited numbers of sentences given space constraints
Future Work:
better disambiguation, e.g. additional languages, better
techniques
additional input for selection: sentence length, deļ¬nition
extraction techniques
integrated user interface for UWN (Universal Wordnet)
Contact: demelo@mpi-inf.mpg.de
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences
68. Introduction
Example Extraction
Example Selection
Results
Conclusion
Conclusion
Framework for:
extracting sense-disambiguated example sentences from
parallel corpora
selecting limited numbers of sentences given space constraints
Future Work:
better disambiguation, e.g. additional languages, better
techniques
additional input for selection: sentence length, deļ¬nition
extraction techniques
integrated user interface for UWN (Universal Wordnet)
Contact: demelo@mpi-inf.mpg.de
G. de Melo / G. Weikum, Max-Planck-Institut Informatik Sense-Disambiguated Example Sentences