View Full Document

tComputational Challenges in Parsing by Classification



View the full content.
View Full Document
View Full Document

16 views

Unformatted text preview:

Computational Challenges in Parsing by Classification Joseph Turian and I Dan Melamed lastname cs nyu edu Computer Science Department New York University New York New York 10003 Abstract This paper presents a discriminative parser that does not use a generative model in any way yet whose accuracy still surpasses a generative baseline The parser performs feature selection incrementally during training as opposed to a priori which enables it to work well with minimal linguistic cleverness The main challenge in building this parser was fitting the training data into memory We introduce gradient sampling which increased training speed 100 fold Our implementation is freely available at http nlp cs nyu edu parser 1 Introduction Discriminative machine learning methods have improved accuracy on many NLP tasks including POS tagging shallow parsing relation extraction and machine translation However only limited advances have been made on full syntactic constituent parsing Successful discriminative parsers have used generative models to reduce training time and raise accuracy above generative baselines Collins Roark 2004 Henderson 2004 Taskar et al 2004 However relying upon information from a generative model might limit the potential of these approaches to realize the accuracy gains achieved by discriminative methods on other NLP tasks Another difficulty is that discriminative parsing approaches can be very task specific and require quite a bit of trial and error with different hyper parameter values and types of features In the present work we make progress towards overcoming these obstacles We propose a flexible well integrated method for training discriminative parsers demonstrating techniques that might also be useful for other structured learning problems The learning algorithm projects the hand provided atomic features into a compound feature space and performs incremental feature selection from this large feature space We achieve higher accuracy than a generative



Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view tComputational Challenges in Parsing by Classification and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view tComputational Challenges in Parsing by Classification and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?