tree-edit crfs for rte

Post on 31-Dec-2015

38 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

Tree-edit CRFs for RTE. Mengqiu Wang and Chris Manning. Tree-edit CRFs for RTE. Extension to McCallum et al. UAI2005 work on CRFs for finite-state String Edit Distance Key attractions: - PowerPoint PPT Presentation

TRANSCRIPT

1

Tree-edit CRFs for RTE

Mengqiu Wang and Chris Manning

2

Tree-edit CRFs for RTE

• Extension to McCallum et al. UAI2005 work on CRFs for finite-state String Edit Distance

• Key attractions:• Models the transformation of dependency parse trees

(thus directly models syntax), unlike McCallum et al. ’05, which only models word strings

• Discriminatively trained

3

TE-CRFs model in details

• First of all, let’s look at the correspondence between alignment (with constraints) and edit operations

BushNNP

person

metVBD

FrenchJJ

location

presidentNN

Jacques ChiracNNP

person

whoWP

qword

leaderNN

isVB

theDT

FranceNNP

location

Q: A:$

root$

root

root

subj obj

det of

root

subj with

nmod

nmod

substitute

substitute

substitute

substitute

delete

insert

Fancy

substitute

5

TE-CRFs model in details• Each valid tree edit operation sequence that

transforms one tree into the other corresponds to an alignment. A tree edit operation sequence is models as a transition sequence among a set of states in a FSM

S1 S2

S3D, S, I

D, S, I D, S, I

D, E, I

D, S, I

D, S, I

D, S, I

substitute delete substitute substitute insert substitute

S1 S2 S1 S1 S1 S3 S1

S2 S3 S2 S1 S2 S1 S3

S3 S2 S1 S3 S3 S2 S2

… … … …… ……

6

FSM

This is for one edit operation sequence

substitute delete substitute substitute insert substitute

S1 S2 S1 S1 S1 S3 S1

S2 S3 S2 S1 S2 S1 S3

S3 S2 S1 S3 S3 S2 S2

… … … …… ……

delete substitute substitute substitute insert substitute

S1 S2 S1 S1 S1 S3 S1… … … …… ……

substitute delete substitute substitute substitute insert

S1 S2 S1 S1 S1 S3 S1… … … …… ……

substitute substitute delete substitute insert substitute

S1 S2 S1 S1 S1 S3 S1… … … …… ……

There are many other valid edit sequences

7

FSM cont.

S1 S2

S3D, S, I

D, S, I D, S, I

D, S, I

D, S, I

D, S, I

D, S, I

Start Stop

ε ε

S1 S2

S3D, S, I

D, S, I D, S, I

D, S, I

D, S, I

D, S, I

D, S, I

Positive State Set

Negative State Set

εε

8

FSM transitions

S3S2

S1 S1S3

S2

S2

Start

S2 S3 S3S3 S1

S1S2 S2

S2S2 S1

S2S1

S3S3

S3

… …… …

S2… …

Stop

S3S2

S1 S1S3

S2

S2S2 S3 S3

S3 S1

S1S2 S2

S2S2 S1

S2S1

S3S3

S3

… …… …

S2

… …

Positive State Set

Negative State Set

9

What is the semantic interpretation of the FSM states?

• At this moment since all the states in the FSM are all fully-connected, it’s unclear what they mean. We fix the number of states to 3, and experiments shows that setting it to 1 or 6 hurts performance.

• We are running new experiments with more meaningfully designed FSM topologies, e.g., each states deterministically corresponds to a particular edit operation.

10

Parameterization

S1 S2substitute

positive or negative

positive and negative

11

Training using EM

E-stepM-step

Using L-BFGS

Jensen’s Inequality

12

Features for RTE

• Substitution• Same --Word/WordWithNE/Lemma/NETag/Verb/Noun/Adj/Adv/Other• Sub/MisSub -- Punct/Stopword/ModalWord• Antonym/Hypernym/Synonym/Nombank/Country• Different – NE/Pos• Unrelated words

• Delete• Stopword/Punct/NE/Other/Polarity/Quantifier/Likelihood/

Conditional/If• Insert

• Stopword/Punct/NE/Other/Polarity/Quantifier/Likelihood/Conditional/If

• Tree• RootAligned/RootAlignedSameWord• Parent,Child,DepRel triple match/mismatch

• Date/Time/Numerical• DateMismatch, hasNumDetMismatch, normalizedFormMismatch

13

Tree-edit CRFs for Textual Entailment

• Preliminary results• Trained on RTE2 dev, tested on RTE2 test.• model taken after 50 EM iterations• acc:0.6275, map:0.6407

• SUM, acc=0.675• QA, acc=0.64• IR, acc=0.615• IE, acc=0.58

14

Work in progress

• Implementing a unordered tree-edit algorithm, which would allow swapping of sub-trees

• Use Stanford Parser dependency structure. Need to getting rid of cycles in CollapsedDependencyGraph (almost there, only have a few self-loops now).

• Experiment with deterministic topologies• More features!! • Training a separate model for each sub-task (is

task information given at test time?)

top related