Presentation
0 likes212 views
This document discusses exploring higher order dependency parsers. It introduces dependency grammar and higher order parsing, which includes sibling and grandchild relations. The author experiments with augmenting parsers with semantic features like word senses and morphosyntactic features. For both English and Czech, third order grandchild parsers showed improved accuracy over first and second order parsers when augmented with these features. Semantic features worked best with sibling parsers, while morphosyntactic features worked best with grandchild parsers. Future work is proposed on higher order labeled parsing and joint extraction of senses and roles.
Presentation
- 1. Exploring Higher Order Dependency Parsers Pranava Swaroop Madhyastha Supervised by: Prof. Michael Rosner & RNDr. Daniel Zeman September 6, 2011
- 2. Introduction ◮ Dependency Grammar. ◮ Binary asymmetric relations - Head and Modifier - Highly lexical relationships. ◮ A quick example: ◮ Projective Constraint ◮ Graph Based Dependency Parsing ◮ Arc-Factored Parsing
- 3. Problem Description? ◮ Augmentation of Features ◮ Semantic features ◮ Morpho-syntactic features ◮ Higher order parsing ◮ Context availability ◮ horizontal and vertical context availability ◮ Motivation ◮ Semi-supervised dependency parsing and improvements. ◮ Using well defined linguistic components.
- 4. What is Higher Order Dependency Parsing ◮ First-order model - decomposition of the tree into head and modifier dependencies. ◮ Second-order models - inclusion of sibling relation of the modifier tokens along with head and modifier or inclusion of head and modifier and children of the modifier. ◮ Third-order models - one level up. ◮ An illustration
- 5. Still Why?
- 6. Features ◮ For a given φ - a feature vector and w - the list of related parameters, each part is scored as Part(x, p) = w .φ(x, p) (1) ◮ Each of these contributing feature vectors would be scored by calculating the individual features in this fashion: ◮ dir.pos(h).pos(m) ◮ dir.form(h).pos(m) ◮ and so on ... ◮ The most basic feature patterns consider the surface form, part-of-speech, lemma and other morphosyntactic attributes of the head or the modifier of a dependency.
- 7. Experimentation done with: ◮ English - Penn Treebank ◮ Section 2 to 10 as training set - a set of 15000 sentences. ◮ Random sets of sentences from sections 15, 17, 19, 25 of the Penn Treebank as development data - a set of 1000 sentences. ◮ Test set was chosen from Sections 0, 1, 21, 23 of the penn treebank - a set of 2000 sentences. ◮ Czech - Prague Dependency Treebank ◮ The sentences were chosen from pdt2-full-automorph dataset. ◮ The training set consisted of train1 - train5 splits - a set of 15,000 sentences.. ◮ The development set consisted of train6 and train7 splits - a set of 1000 sentences. ◮ The test set was made up of dtest and etest parts - a set of 2000 sentences.
- 8. Experimentation ◮ Fine and Coarse Grained Wordsenses ◮ Approximation ◮ For English: ◮ Both Fine and Coarse Grained Wordsense extraction make use of WordNet::SenseRelate package. ◮ Fine grained wordsense basically restricts a word to a particular sense - Word - noun and first sense (extracted from the wordnet) ◮ Coarse Grained wordsense is a more generic wordsense description Word - the semantic file to which the word belongs to. ◮ For Czech: ◮ Only Fine Grained Wordsense extraction (approximately). ◮ extracted by using the sempos which is already tagged in the prague dependency treebank.
- 9. Results for the Wordsense augmentation experiment ◮ Sibling based parsers show a statistically significant improvement. ◮ For English with Fine Grained wordsense addition - Third order grand-sibling based parser gives an improvement of +0.81 percent (Unlabeled Accuracy Score). A closer statistical examination showed that sibling based interactions which are close to each other have better precision. ◮ For English with Coarse Grained wordsense addition - the second order sibling based parser gives an improvement of approximately +1.09 percent. ◮ Again for Czech with fine grained wordsense augmentation, the 3rd order sibling based parser gives an improvement of approximately +1.20 percent.
- 10. Results for Morphosyntactic augmentation experiment ◮ Morphosyntactic augmentation was basically used directly by extracting tags from the corpus. ◮ For Czech, instead of the 15 Letter tagset, we tried out a subset (which includes - Person, Number, POSSGender, Tense, Voice and Case) ◮ For English we integrated the fine grained part-of-speech.
- 11. Results ◮ Both for English and Czech, there is a significant improvement in the parsing accuracy when it is parsed with the grandchild based algorithms. ◮ For Czech, the third order grand sibling based algorithm shows an improvement of +1.72 percent. ◮ For English, the third order grand sibling based algorithm shows an improvement of +1.21 percent.
- 12. Conclusion ◮ Semantic features work better with sibling based parsers (larger horizontal contexts). ◮ Morpho-syntactic features work better with grandchild based parsers (larger vertical contexts). ◮ Features can be instrumental in several tasks, which include accurate labeling of semantic roles and other related tasks. ◮ Linguistic information can be better handled by a higher order parsing algorithm.
- 13. Future Work ◮ Higher order parsers with labels (we have not yet tested labeled accuracy scores). ◮ Joint extraction of word-senses and semantic roles. ◮ Experimentation with lexical clusters. ◮ Thorough experimentation of several features. ◮ Maximum and Minimum order requirements.
- 14. Thanks