140 likes | 255 Views
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:
E N D
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: • Models the transformation of dependency parse trees (thus directly models syntax), unlike McCallum et al. ’05, which only models word strings • Discriminatively trained
TE-CRFs model in details • First of all, let’s look at the correspondence between alignment (with constraints) and edit operations
$ root $ root Q: A: substitute root root met VBD is VB substitute subj obj subj with who WP qword leader NN Bush NNP person Jacques Chirac NNP person insert det of Fancy substitute nmod the DT France NNP location president NN substitute delete nmod French JJ location substitute
S2 S2 S3 S2 S1 S3 S2 S3 S1 S2 S3 S1 S3 S1 S1 S1 S2 S3 S1 S2 S1 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 D, S, I D, S, I D, S, I S1 S2 D, E, I D, S, I S3 D, S, I D, S, I substitute insert substitute delete substitute substitute … … … … … … …
… … … … … … … … … … … … … … … … … … … … … S2 S3 S2 S2 S2 S2 S3 S3 S3 S1 S3 S2 S1 S1 S3 S2 S1 S1 S1 S1 S1 S2 S1 S3 S1 S3 S1 S1 S1 S1 S2 S1 S1 S3 S1 S1 S1 S1 S1 S1 S1 S2 FSM substitute insert substitute delete substitute substitute … … … … … … … This is for one edit operation sequence substitute insert delete substitute substitute substitute insert substitute substitute delete substitute substitute substitute insert substitute substitute delete substitute There are many other valid edit sequences
D, S, I D, S, I D, S, I D, S, I D, S, I D, S, I S1 S1 S2 S2 D, S, I D, S, I D, S, I D, S, I S3 S3 D, S, I D, S, I D, S, I D, S, I FSM cont. ε ε Positive State Set Start Stop ε ε Negative State Set
FSM transitions Positive State Set … S1 S1 S2 S3 S2 S3 … S3 S3 S2 S3 S1 S2 … … … … … … … S1 S1 S2 S2 S2 … S2 S2 S3 S3 S2 … S1 S3 Stop Start Negative State Set … S1 S1 S2 S3 S2 S3 … S3 S3 S2 S3 S1 S2 … … … … … … … S1 S1 S2 S2 S2 … S2 S2 S3 S3 S2 … S1 S3
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.
Parameterization substitute S2 S1 positive or negative positive and negative
Training using EM Jensen’s Inequality E-step M-step Using L-BFGS
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
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
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?)