Timezone: »
Spotlight
Discriminative Log-Linear Grammars with Latent Variables
Slav Petrov · Dan Klein
We demonstrate that log-linear grammars with latent variables can be practically trained using discriminative methods. Central to efficient discriminative training is a hierarchical pruning procedure which allows feature expectations to be efficiently approximated. We investigate an EM alternating procedure as well as a direct, gradient-based procedure and show that direct optimization is superior. On full-scale treebank parsing experiments, the discriminative latent models outperform both the comparable generative latent models as well as the discriminative non-latent baselines.
Author Information
Slav Petrov (Google)
Dan Klein (UC Berkeley)
Related Events (a corresponding poster, oral, or spotlight)
-
2007 Poster: Discriminative Log-Linear Grammars with Latent Variables »
Mon. Dec 3rd 06:30 -- 06:40 PM Room
More from the Same Authors
-
2023 Poster: Goal Driven Discovery of Distributional Differences via Language Descriptions »
Ruiqi Zhong · Peter Zhang · Steve Li · Jinwoo Ahn · Dan Klein · Jacob Steinhardt -
2021 : Language, Context, and Action: A Semantic Machines View of Conversational AI »
Dan Klein -
2021 Poster: Learning Space Partitions for Path Planning »
Kevin Yang · Tianjun Zhang · Chris Cummins · Brandon Cui · Benoit Steiner · Linnan Wang · Joseph Gonzalez · Dan Klein · Yuandong Tian -
2018 Poster: Speaker-Follower Models for Vision-and-Language Navigation »
Daniel Fried · Ronghang Hu · Volkan Cirik · Anna Rohrbach · Jacob Andreas · Louis-Philippe Morency · Taylor Berg-Kirkpatrick · Kate Saenko · Dan Klein · Trevor Darrell -
2015 Poster: On the Accuracy of Self-Normalized Log-Linear Models »
Jacob Andreas · Maxim Rabinovich · Michael Jordan · Dan Klein -
2015 Poster: Grammar as a Foreign Language »
Oriol Vinyals · Łukasz Kaiser · Terry Koo · Slav Petrov · Ilya Sutskever · Geoffrey Hinton -
2014 Poster: Unsupervised Transcription of Piano Music »
Taylor Berg-Kirkpatrick · Jacob Andreas · Dan Klein -
2014 Demonstration: Unsupervised Transcription of Piano Music »
Taylor Berg-Kirkpatrick · Jacob Andreas · Dan Klein -
2014 Spotlight: Unsupervised Transcription of Piano Music »
Taylor Berg-Kirkpatrick · Jacob Andreas · Dan Klein -
2010 Workshop: Coarse-to-Fine Learning and Inference »
Ben Taskar · David J Weiss · Benjamin J Sapp · Slav Petrov -
2009 Poster: Randomized Pruning: Efficiently Calculating Expectations in Large Dynamic Programs »
Alexandre Bouchard-Côté · Slav Petrov · Dan Klein -
2009 Spotlight: Randomized Pruning: Efficiently Calculating Expectations in Large Dynamic Programs »
Alexandre Bouchard-Côté · Slav Petrov · Dan Klein -
2008 Workshop: Speech and Language: Unsupervised Latent-Variable Models »
Slav Petrov · Aria Haghighi · Percy Liang · Dan Klein -
2008 Poster: Efficient Inference in Phylogenetic InDel Trees »
Alexandre Bouchard-Côté · Michael Jordan · Dan Klein -
2008 Spotlight: Efficient Inference in Phylogenetic InDel Trees »
Alexandre Bouchard-Côté · Michael Jordan · Dan Klein -
2007 Poster: Agreement-Based Learning »
Percy Liang · Dan Klein · Michael Jordan -
2007 Spotlight: Agreement-Based Learning »
Percy Liang · Dan Klein · Michael Jordan -
2007 Session: Spotlights »
Dan Klein -
2007 Session: Spotlights »
Dan Klein -
2007 Poster: A Probabilistic Approach to Language Change »
Alexandre Bouchard-Côté · Percy Liang · Tom Griffiths · Dan Klein