A generative parser with a discriminative recognition algorithm

Jianpeng Cheng, Adam Lopez, Maria Lapata

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a framework for parsing and language modeling which marries a generative model with a discriminative recognition model in an encoder-decoder setting. We provide interpretations of the framework based on expectation maximization and variational inference, and show that it enables parsing and language modeling within a single implementation. On the English Penn Treenbank, our framework obtains competitive performance on constituency parsing while matching the state-of-the-art singlemodel language modeling score.
Original languageEnglish
Title of host publication55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)
PublisherAssociation for Computational Linguistics
Number of pages7
ISBN (Print)978-1-945626-76-0
Publication statusPublished - 4 Aug 2017
Event55th annual meeting of the Association for Computational Linguistics (ACL) - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017


Conference55th annual meeting of the Association for Computational Linguistics (ACL)
Abbreviated titleACL 2017
Internet address

Cite this