Learning and Generating from Structured Data
Lei Sha
Institute of Computational Linguistics, Peking [email protected]
May 28, 2018
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 1 / 53
Table of Contents
1 Learning Structured Data from Raw Text
2 Generating Text from Structured Data
3 Other Works
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 2 / 53
Introduction
Structured data can be used in two symmetrical procedures:
Text −→ Structured data
Structured data −→ Text
On September 11th, five hijackers crashed American Airlines
Flight 11 into the World Trade Center’s North Tower.
On September 11th, five hijackers crashed American Airlines
Flight 11 into the World Trade Center’s North Tower.
Learning Structured Data from Raw Text
Generating Text from Structured Data
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 3 / 53
Table of Contents
1 Learning Structured Data from Raw Text
2 Generating Text from Structured Data
3 Other Works
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 4 / 53
Learning Structured Data from Raw Text
Structured data usually serve for applications like question answering,dialogues, and information retrieval
The tasks of learning structured data includes:
Relation extraction
Event extraction
We focused on event extraction in our research.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 5 / 53
Event Extraction
Motivation:
Event extraction is important for knowledge acquisition from largeamounts of news text.
The result of event extraction can be used to construct knowledgebase, which can be applied to question answering, dialogue system,etc.
Its paradigm is ubiquitous in our daily life:
Knowledge GraphStructured summary of search engineWikipedia infobox
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 6 / 53
Applications of Event Extraction
The Google search result of September 11 attacks:
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 7 / 53
Applications of Event Extraction
The Wikipedia infobox of September 11 attacks:
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 8 / 53
Applications of Event Extraction
The extracted events can be transferred into triples and store in theknowledge graphs.The knowledge graphs can be leveraged by upper applications.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 9 / 53
Event Extraction
What’s an event?
Event Type: Business
Trigger Release
ArgumentCompany MicrosoftProduct Surface Pro
Place USA
Figure: Microsoft releases surface Pro in USA.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 10 / 53
Event Extraction
What’s an event?
Event Type: Attack
Trigger Crash
Argument
Attacker Five hijackers
TargetWorld Trade Center’s
North TowerInstrument American Airlines Flight 11
Time September 11th
Figure: On September 11th, five hijackers crashed American Airlines Flight 11into the World Trade Center’s North Tower.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 11 / 53
Event Extraction from News Text
What should we do?
Extract trigger
Identify arguments
Classify roles
Event Type: Die
Trigger Die
ArgumentVictim cameramanPlace Baghdad
Instrument American tank
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 12 / 53
Event Extraction from News Text
Challenges of event extraction:
Patterns are accurate (precision > 96%), but cannot cover every case
Pattern example
(weapon) tore [through] (building) at (place) ⇒ Attack{Roles· · · }
Some arguments tend to occur together: Cameraman & Americantank (in Die event)
Some arguments tend not to occur together: Baghdad & PalestineHotel (in Die event) (Hint: dependency distance is too long)
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 13 / 53
Event Extraction from News Text
Conventional pattern-based and classifier-based event extraction method
... In Baghdad, a cameraman died when ...
n, v, adj: trigger candidate
trigger = died find best pattern①
get arguments & roles
yes
MaxEnt for argument② MaxEnt for role③
MaxEnt for reportable event④
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 14 / 53
Event Extraction from News Text
Sha et al.: RBPB: Regularization-Based Pattern Balancing Method forEvent Extraction. (ACL 2016)
... In Baghdad, a cameraman died when ...
n, v, adj: trigger candidate
trigger = died
Classifier for Event type①
Classifier for argument② Classifier for role③
Regularization
... In Baghdad, a cameraman died when ...
n, v, adj: trigger candidate
trigger = died find best pattern①
get arguments & roles
yes
Classifier for argument② Classifier for role③
Classifier for reportable event④ Classifier for reportable event④
pattern balancing
argument-argument relationship
We transfer pattern information into embedded features
We use regularization method to capture argument-argumentrelationships
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 15 / 53
Event Extraction from News Text
How to use pattern better?
Turn pattern into event type probability distribution
pattern + other features → trigger identification & classification
Event type Trigger Pattern
Attack shoot pattern 1Injure shoot pattern 2
Die shoot pattern 3Injure shoot pattern 4Injure shoot pattern 5
Die shoot pattern 6Die shoot pattern 7
Attack shoot pattern 8Attack shoot pattern 9Attack shoot pattern 10
⇒
AttackInjure Die
Table: Candidate pattern result for trigger “shoot”
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 16 / 53
Event Extraction from News Text
Argument-argument relationship regularization
Arguments tend to occur together: Positive relationship
Arguments tend not to occur together: Negative relationship
We need to capture these two relationships:
Use a bunch of position features and dependency features to decidethe probability to be “Pos”: P(rel = “Pos”|argi , argj)The training set of arg-arg relationship classifier is generated from theoriginal dataset
We obtain the arg-arg relationship matrix M
Mi ,j = P(rel = “Pos”|argi , argj)
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 17 / 53
Event Extraction from News Text
We use a score function to evaluate the current configuration of argument:x
x(i) represents the role taken by i-th candidate argument
xbin = Bin(x)
xbin(i) represents whether i-th candidate argument is an argument forthe current trigger
Score(x) = x>binMxbin + farg(xbin) + frole(x)
farg: function for argument identificationfrole: function for role classification
We use Beam Search to find the best configuration (largest score)
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 18 / 53
Event Extraction from News Text
Example of the quadratic item:
Assume that “Baghdad” and “Palestine hotel” have negativerelationship
In this example, the closer the value is to 1, the more likely it ispositive; the closer the value is to 0, the more likely it is negative
In Baghdad, a cameraman died when an American tank fired on the Palestine hotel.
1.0 0.5 0.9 0.20.5 1.0 0.5 0.50.9 0.5 1.0 0.60.2 0.5 0.6 1.0
1 0 0 110 0 1
= 0.2 + …
Figure: Example calculation process of negative relation.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 19 / 53
Event Extraction from News Text
Another example of the quadratic item:
Assume that “Baghdad” and “American tank” have positiverelationship
Again, the closer the value is to 1, the more likely it is positive; thecloser the value is to 0, the more likely it is negative
In Baghdad, a cameraman died when an American tank fired on the Palestine hotel.
1.0 0.5 0.9 0.20.5 1.0 0.5 0.50.9 0.5 1.0 0.60.2 0.5 0.6 1.0
1 0 1 010 10
= 0.9 + …
Figure: Example calculation process of positive relation.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 20 / 53
Event Extraction from News Text
Argument-argument relationship regularization
Pos relation vs. Neg relationBilinear in score: Score(x) = x>binMxbin + farg(xbin) + frole(x)
We found that... Oops! That doesn’t work.
Strengthen the two relationships
Map float numbers of Mij to discrete integers: [0, 1] −→ −1, 0, 1
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
�
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
Figure: Visualization of M before and after strengthen.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 21 / 53
Event Extraction from News Text
Argument-argument relationship regularization
Pos relation vs. Neg relationBilinear in score: Score(x) = x>binMxbin + farg(xbin) + frole(x)
We found that...
Oops! That doesn’t work.
Strengthen the two relationships
Map float numbers of Mij to discrete integers: [0, 1] −→ −1, 0, 1
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
�
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
Figure: Visualization of M before and after strengthen.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 21 / 53
Event Extraction from News Text
Argument-argument relationship regularization
Pos relation vs. Neg relationBilinear in score: Score(x) = x>binMxbin + farg(xbin) + frole(x)
We found that... Oops! That doesn’t work.
Strengthen the two relationships
Map float numbers of Mij to discrete integers: [0, 1] −→ −1, 0, 1
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
�
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
Figure: Visualization of M before and after strengthen.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 21 / 53
Event Extraction from News Text
Argument-argument relationship regularization
Pos relation vs. Neg relationBilinear in score: Score(x) = x>binMxbin + farg(xbin) + frole(x)
We found that... Oops! That doesn’t work.
Strengthen the two relationships
Map float numbers of Mij to discrete integers: [0, 1] −→ −1, 0, 1
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
�
Powerful bombA waiting shed
Davao airportBus
Powerful bomb
A waiting shed
Davao airport
Bus
Figure: Visualization of M before and after strengthen.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 21 / 53
Event Extraction from News Text
Example of the quadratic item (strengthened):
Assume that “Baghdad” and “Palestine hotel” have negativerelationship
In this example, 1 represents positive relationship, −1 representsnegative relationship, 0 means unclear relationship.
In Baghdad, a cameraman died when an American tank fired on the Palestine hotel.
1 0 1 -1 0 1 0 0 1 0 1 0-1 0 0 1
1 0 0 110 0 1
= -1 + …
Figure: Example calculation process of negative relation.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 22 / 53
Event Extraction from News Text
Another example of the quadratic item (strengthened):
Assume that “Baghdad” and “American tank” have positiverelationship
Again, 1 represents positive relationship, −1 represents negativerelationship, 0 means unclear relationship.
In Baghdad, a cameraman died when an American tank fired on the Palestine hotel.
1 0 1 -1 0 1 0 0 1 0 1 0-1 0 0 1
1 0 1 010 10
= 1 + …
Figure: Example calculation process of positive relation.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 23 / 53
Event Extraction from News Text
Can we do better?Challenges of event extraction by the previous solutions√
Using syntax information as feature
× Using syntax information as architecture√
Capture two kinds of argument-argument relationship (Pos & Neg)
× Capture large amount of argument-argument relationship
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 24 / 53
Event Extraction from News Text
Sha et al.(AAAI 2018) Jointly Extracting Event Triggers and Argumentsby Dependency-Bridge RNN and Tensor-Based Argument Interaction
Motivation 1:
Dependency relation −→ Dependency bridge
According to definition of dependency relation, dependency edgesusually contain some information about temporal, consequence,conditional or purpose.
Figure: Example of dependency parse tree.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 25 / 53
Event Extraction from News Text
We add dependency bridges to conventional LSTM-RNN architecture.Bidirectionality:
Forward: Set all dependency bridges as forward.Backward: Set all dependency bridges as backward.
A cameraman died when tank fired on the hotel
LSTM layer
Figure: Dependency bridge on LSTM. Apart from the last LSTM cell, each cellalso receives information from former syntactically related cells.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 26 / 53
Event Extraction from News Text
Details of dependency bridge
We add a new gate dt and change the calculation of hidden state.
ht = ot � tanh(ct) + dt �(
1|Sin|
∑(i ,p)∈Sin aphi
)
𝑋#
𝜎 𝜎 𝑡𝑎𝑛ℎ 𝜎
× +
×𝑡𝑎𝑛ℎ
×
ℎ#
𝑓# 𝑖# 𝐶#~ 𝑜#
𝐶#01
ℎ#01
𝐶#
ℎ#
𝑋#
𝜎 𝜎 𝑡𝑎𝑛ℎ 𝜎
× +
×𝑡𝑎𝑛ℎ
×
ℎ#
𝑓# 𝑖# 𝐶#~ 𝑜#
𝐶#01
ℎ#01
𝐶#
ℎ#
𝜎
×
𝑊34567
𝑊345894
𝑊:;<=>
ℎ?ℎ>ℎ@
𝑑#
+
Figure: The calculation detail of dependency bridge.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 27 / 53
Event Extraction from News Text
Motivation 2:
We represent each arg-arg relationship by a vector
We use a tensor to represent all kinds of arg-arg relationships in asentence
Tensor layerD
NN
Representation of Candidate Arguments
Figure: The calculation detail of tensor layer.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 28 / 53
Event Extraction from News Text
The whole architecture ...
Tensor layer is applied to the hidden layer of the dependency bridgeRNN
Then we apply max-pooling over arguments to find the mostimportant “interactive features” for the arguments
Tensor layer
...
Acameraman
diedwhentankfired
onthe
hotel
Candidate trigger
Candidate Arguments
DBLSTM
-RNN
DBRNN layer Pooling layer Output layer
DNN
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 29 / 53
Weights of each dependency relation
nm
od:a
ssm
od cc
nm
od:t
mod
ccom
pnsu
bjp
ass
advm
od:c
om
pco
nj
am
od
mark
:clf
com
pound:v
caux:a
sp etc
aux:p
rtm
od
neg
dis
cours
eadvcl
:loc
auxpass
aux:m
odal
nsu
bj:xsu
bj
para
:prn
mod
nm
od:t
opic
xco
mp
nsu
bj
num
mod
advm
od
punct
nm
od:r
ange
nm
od:p
rep
case
cop
am
od:o
dm
od
nam
edep
appos
det
nm
od
dobj
mark
advm
od:loc
com
pound:n
nadvm
od:d
vp
root
aux:b
aacl
0.0
0.5
1.0
1.5
2.0The w
eig
hts
of
each
dependency
rela
tions
Figure: The visualization of trained weights of each dependency relations.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 30 / 53
Event Extraction from News Text
Figure: Performances of various approaches on ACE 2005 dataset.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 31 / 53
Table of Contents
1 Learning Structured Data from Raw Text
2 Generating Text from Structured Data
3 Other Works
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 32 / 53
Table-to-Text Brief Summary Generation
A table can be a list of RBF tuples:
John E Blaha birthDate 1942,08,26
John E Blaha birthPlace San Antonio
John E Blaha occupation Fighter pilot
San Antonio located in USA
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 33 / 53
Table-to-Text Brief Summary Generation
A table can be also a list of attributes (like Wiki infobox):
Figure: An example of Wikipedia infobox.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 34 / 53
Table-to-Text Brief Summary Generation
Generate brief summary from structured data is useful
In the last step of QA system, Table-to-text is used to generateanswer.
User
Question Analysis
Search from KB
Answer Generation
Answer
Question
Table
Text
Figure: Table-to-text in question answering system.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 35 / 53
Table-to-Text Brief Summary Generation
Table-to-text can also be used to generate response in dialogue system
Slot extraction Intenttracking
Statetracking
SearchKB
Slot extraction Intenttracking
Statetracking
SearchKB
Table to TextGenerator
Table to TextGenerator
Figure: Table-to-text in dialogue system.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 36 / 53
Table-to-Text Brief Summary Generation
We generate brief summary for wikipedia infobox
Sir Arthur Ignatius Conan Doyle(22 May 1859 – 7 July 1930) wasa British writer best known forhis detective fiction featuring thecharacter Sherlock Holmes.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 37 / 53
Table-to-Text Brief Summary Generation
Motivation:
Traditional: language model based generator
Use probability of word-by-word: P(wt |wt−1)Different from human’s generation process
Human: first plan for order, then write
Use probability of field-by-field: P(ft |ft−1)
We propose to add human nature into machine learning models
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 38 / 53
Table-to-Text Brief Summary Generation
Sha et al. (AAAI 2018) Order-Planning Neural Text Generation FromStructured Data (arxiv)
Content-based attention
Use the last output word yt−1 to predict the importance of each tablecontent for the next output.
Link-based attention
See which field we are going to generate this time.
Hybrid attention
Combine content-based and link-based attention together.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 39 / 53
Table-to-Text Brief Summary Generation
How to build field-by-field probability (P(ft |ft−1))?
The element in the i-th row and j-th column is the probability of fieldj occurs after field i
Figure: Field-by-field probability matrix (Link matrix).
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 40 / 53
Table-to-Text Brief Summary Generation
How to build link sub-matrix?
NameBorn Occupation
Nationality
Name
Born
Occupation
Nationality Link matrix
Link sub-matrix
Figure: The process of select link sub-matrix.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 41 / 53
Table-to-Text Brief Summary Generation
We calculate the hybrid attention as follows:
(a) Encoder: Table Representation(b) Dispatcher: Planning What to Generate Next
Name Arthur
Name Ignatius
Name Conan
Name Doyle
Born 22
Born May
Born 1859
Occupation writer
Occupation physician
Nationality British
LST
M=
Last step'sattention
Link (sub)matrix
Content-basedattention
Link-basedattention
Hybrid attention
Weightedsum
Attentionvector
Field Content
Figure: Illustration of content-based attention and link-based attention.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 42 / 53
Table-to-Text Brief Summary Generation
Then we generate text according to the hybrid attention:
Table content
LSTM LSTM LSTM
<start>
. . . LSTM
. . .
<eos>
LSTM
LastLSTMstate
Attentionvector
Embedding of thegenerated wordin last step
Figure: The decoder in our model, which is incorporated with a copyingmechanism.Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 43 / 53
Table-to-Text Brief Summary Generation
Overall performance of our model:
Figure: Comparison of the overall performance between our model and previousmethods. lBest results in Lebret, Grangier, and Auli (2016).
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 44 / 53
Table-to-Text Brief Summary Generation
Simple case study:
Figure: Case study. Left: Wikipedia infobox. Right: A reference and twogenerated sentences by different attention (both with the copy mechanism).
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 45 / 53
Table-to-Text Brief Summary Generation
Visualization of attention probabilities in our model.
x-axis: generated words “...) was an american economist ...”;y-axis: 〈field : content word〉 pairs in the table.
)w
as anam
eric
anec
onom
ist
death place:uniteddeath place:states
nationality:americanoccupation:governor
occupation:ofoccupation:the
occupation:federaloccupation:reserveoccupation:system
occupation:,occupation:economics
occupation:professorknown for:expert
(a) αcontent
)w
as anam
eric
anec
onom
ist
(b) αlink
)w
as anam
eric
anec
onom
ist
(c) αhybrid
Figure: Subplot (b) exhibits strips because, by definition, link-based attention willyield the same score for all content words with the same field.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 46 / 53
Table of Contents
1 Learning Structured Data from Raw Text
2 Generating Text from Structured Data
3 Other Works
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 47 / 53
Other works
Research papers:
Event schema induction (Sha et al, NAACL 2016)
Chinese SRL (Sha et al, EMNLP 2016)
Textual Entailment Recognition (Sha et al, EMNLP 2015, Coling2016)
Repeated Reading (Sha et al, NLPCC 2017)
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 48 / 53
Other works
Automatically Design Neural Network Architecture (in SinovationVentures)
Implement a simple version of paper “Neural Architecture SearchWith Reinforcement Learning”Use policy gradient method to increase the probability of samplingchild networks with high reward
Figure: The process of a parent controller recurrent neural network sampling achild network.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 49 / 53
Other works
Multi-intent switch dialogue system (in MSRA system group)
Figure: The architecture of ISwitch.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 50 / 53
Publications (lead author)
Sha et al: Order-Planning Neural Text Generation From Structured Data. InAAAI 2018.
Sha et al: Joint Extracting Event Trigger and Arguments Using dependency bridgeRecurrent Tensor Network. In AAAI 2018.
Sha et al: Multi-View Fusion Neural Network for Answer Selection. In AAAI 2018.
Sha et al: Will Repeated Reading Benefit Natural Language Understanding? InNLPCC 2017.
Sha et al: Reading and Thinking: Re-read LSTM Unit for Textual EntailmentRecognition. In Coling 2016.
Sha et al: Capturing Argument Connection for Chinese Semantic Role Labeling. InEMNLP 2016.
Sha et al: RBPB: Regularization-Based Pattern Balancing Method for EventExtraction. In ACL 2016.
Sha et al: Joint Learning Templates and Slots for Event Schema Induction. InNAACL 2016.
Sha et al: Recognizing Textual Entailment Using Probabilistic Inference. InEMNLP 2015.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 51 / 53
Publications (co-author)
Feng Qian, Lei Sha, Baobao Chang, Lu-chen Liu, Ming Zhang: Syntax AwareLSTM Model for Chinese Semantic Role Labeling. In EMNLP 2017
Qiaolin Xia, Lei Sha, Baobao Chang, Zhifang Sui: A Progressive LearningApproach to Chinese SRL Using Heterogeneous Data. In ACL 2017
Xiaodong Zhang, Lei Sha, Sujian Li, Houfeng Wang: Attentive Interactive NeuralNetworks for Answer Selection in Community Question Answering. In AAAI 2017
Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Sujian Li, Baobao Chang andZhifang Sui: Encoding Temporal Information for Time-Aware Link Prediction. InEMNLP 2016.
Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Sujian Li, Baobao Chang andZhifang Sui: Towards Time-Aware Knowledge Graph Completion. In Coling 2016.
Li Li, Houfeng Wang, Lei Sha, Xu Sun, Baobao Chang, Shi Zhao: Multi-labelText Categorization with Joint Learning Predictions-as-Features Method. InEMNLP 2015.
Tingsong Jiang, Lei Sha and Zhifang Sui: Event Schema Induction Based onRelational Co-occurrence over Multiple Documents. In NLPCC 2014.
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 52 / 53
Thank you. Any questions?
Lei Sha (ICL, Peking University) Learning and Generating from Structured Data May 28, 2018 53 / 53