Академический Документы
Профессиональный Документы
Культура Документы
1 2
Universitat Politècnica de Catalunya Xerox Research Centre Europe
ACL-IJNLP 2015 1 / 28
Challenge
ACL-IJNLP 2015 2 / 28
Approaches
`1 or `2
unseen conjunctions?
ACL-IJNLP 2015 3 / 28
Contribution
Learning algorithm
Convex relaxation of the low-rank minimization function
Experiments
Improvement over `1 & `2
ACL-IJNLP 2015 4 / 28
Task
Given:
x = hl, e, r i
Goal:
Classify x into one entity class y in the set Y
ACL-IJNLP 2015 5 / 28
Classifier
Log-Linear Model
ACL-IJNLP 2015 6 / 28
Scoring Function
sθ (x, y) = φ(x) · wy
ACL-IJNLP 2015 7 / 28
Scoring Function
sθ (hl, e, r i, y) = φl (l)> Wy φr (r )
ACL-IJNLP 2015 8 / 28
Low Rank Parameter Matrices
SVD
···
u11 u1k
. . .
"σ1 ··· 0
# v11 ··· ···
v1d2
. . .
. . . . .. . . . . .
Wy = . . . .
. . .
.
.
.
.
.
.
.
.
.
. . .
. . . 0 ··· σk vk 1 ··· ··· vkd2
ud1 ··· ud1 k | {z }| {z }
| {z } Σy V>
y
Uy
ACL-IJNLP 2015 9 / 28
Score Function - Rewritten
Left-right context model
sθ (hl, e, r i, y) = φl (l)> Wy φr (r )
u11 ··· u1k
v ··· ··· r1
. . . v1d
" #
σ1 ··· 0
. 11 2
. .
. . . . . .
. . .
.
[l1 ··· ]
ld
1
. .
. ..
.
.. .
. .
. .
.
.
.
.
.
.
.
| {z } . . . r
. . . 0 ··· σk vk 1 ··· ··· vkd d2
φl (l)>
ud ··· ud k | {z }| {z
2
} | {z }
| 1 1
Σy
{z } V>
y
φr (r )
Uy
| {z }
SVD(Wy )
ACL-IJNLP 2015 10 / 28
Score Function - Rewritten
sθ (hl, e, r i, y) = φl (l)> Wy φr (r )
u ··· u1k
11
. . .
"σ
1 ··· 0
# "v11 ··· ··· v1d #" r1 #!
. . . 2
. . . .
. . . . . .
[l1 ··· ld ] . .
1
. . . . . . .
. . . . . . . . . . .
. . .
. . . 0 ··· σk vk 1 ··· ··· vkd rd
2 2
ud ··· ud k | {z }| {z }
| {z1 1
} Σy V>
y φr (r )
φl (l)> U y
Rank k → intrinsic dimensionality of the inner product behind the score function
ACL-IJNLP 2015 11 / 28
Adding Entity Features
One parameter matrix per feature tag and class label, i.e. θ = {Wt,y }t∈T ,y∈Y
X
sθ (hl, e, r i, y ) = φl (l)> Wt,y φr (r )
t∈φe (e)
↓
Parameters: tensor
↓
Rank defined by matricization
ACL-IJNLP 2015 12 / 28
Learning The Parameters
Objective Function
ACL-IJNLP 2015 13 / 28
Experimental Settings
ACL-IJNLP 2015 14 / 28
Class 10-30 Seed
PER clinton, dole, arafat, yeltsin, wasim akram, lebed, dutroux, waqar
younis, mushtaq ahmed, croft
LOC u.s., england, germany, britain, australia, france, spain, pakistan,
italy, china
ORG reuters, u.n., oakland, puk, osce, cincinnati, eu, nato, ajax, honda
MISC russian, german, british, french, dutch, english, israeli, european,
iraqi, australian
O year, percent, thursday, government, police, results, tuesday,
soccer, president, monday, friday, people, minister, sunday, divi-
sion, week, time, state, market, years, officials, group, company,
saturday, match, at, world, home, august, standings
For each entity class, the seed of entities for the 10-30 set.
Experimental Settings
ACL-IJNLP 2015 16 / 28
CoNLL 2003 English Corpus
ACL-IJNLP 2015 17 / 28
CoNLL 2003 English Corpus
train
13341
dev
5270
3303
ambiguous
177 out of 3303 (3.54%)
Almost all seen entities that appear in dev can be directly classified
as the same class.
ACL-IJNLP 2015 18 / 28
Results on dev set
61.13
60 57.7
45.16
41.14
AVG-F1 (%)
39.84
37.1 44.67
29.67 39.74
27.07
30.21
27.05 L1
20
L2
NN
0
10 40 640 All
Seed set
AVG-F1 on dev set using different seed set for training, comparing `1 , `2 and nuclear-norm (NN) regularizer.
Feature set: elementary features and all conjunctions of entity tags and left-right contexts (cluster & PoS), window
size = 1
Seed set: number of examples per entity class (and 3× of non-entity examples)
ACL-IJNLP 2015 19 / 28
Results on dev set
60.94 61.13
60 60 56.16 60 57.7
L1
L2 44.2 45.16
42.81 41 41.14
40.45 39.84
AVG-F1 (%)
AVG-F1 (%)
AVG-F1 (%)
40 NN 38.3 36.87 45.04 37.1 44.67
39.52 39.74
28.25 28.54 28.48 29.67
25.11 27.18 25.91 27.07
28.88 28.57 L1 30.21 L1
17.72 27.41 25.3 27.05
14.12 20
L2 L2
17.58
14.23 NN NN
0 0 0
10 40 640 All 10 40 640 All 10 40 640 All
Seed set Seed set Seed set
Only full conjunctions of left-right contexts Elementary features and all conjunctions of Elementary features and all conjunctions of
(cluster), window size = 1 entity tags and left-right contexts (cluster), entity tags and left-right contexts (cluster &
window size = 1 PoS), window size = 1
59.46 58.43
60 60 56.74 60 54.56
53.65
AVG-F1 (%)
AVG-F1 (%)
38.95 37.45 38.22 37.11
40 35.58 44.03 42.83
33.67 32.76 39.95
28.9 38.01 28.92 28.65 37.21
27.62
32.73 24.62
20.72 L1 28.33 L1 28.21 28.04 L1
17.4 24.41
20.05 L2 L2 L2
17.39
NN NN NN
0 0 0
10 40 640 All 10 40 640 All 10 40 640 All
Seed set Seed set Seed set
Only full conjunctions of entity tags and left- Elementary features and all conjunctions of Elementary features and all conjunctions of
right contexts (cluster), window size = 1 entity tags and left-right contexts (cluster), entity tags and left-right contexts (cluster &
window size = 2 PoS), window size = 2
ACL-IJNLP 2015 20 / 28
Results on test set
81
74 74
F1 (%)
55 56
51 54
46 47 48
40
34 36
29 31
`1 `2 nuclear-norm
F1 performance on test set using “all” seed set for training, with best setting (based on results on dev) for each
regularizers.
ACL-IJNLP 2015 21 / 28
Model Dimensions
61.73 61.13
60 54.24
50.19 58.14
AVG-F1 (%)
40 43.93
28.22
20
0
1 2 3 4 5 6 7 8 9 10 20 30 40 50 60 70
dimension
Avg. F1 on development for increasing dimensions, using the best low-rank model in development set trained with
all seeds.
ACL-IJNLP 2015 22 / 28
Cluster
PoS tags
conjunctions in dev
Cluster
PoS tags
PoS tags
PoS tags
ACL-IJNLP 2015 27 / 28
Thank you!
ACL-IJNLP 2015 28 / 28