Actions

Events: Difference between revisions

Computational Linguistics and Information Processing

No edit summary
Line 19: Line 19:
'''Venue:''' AVW 3258
'''Venue:''' AVW 3258


In the past few years, there has been an increased interest in the machine learning community in spectral
There has been an increased interest in the machine learning community in spectral
algorithms for estimating models with latent variables. Examples include algorithms for estimating mixture of
algorithms for estimating models with latent variables. Examples include algorithms for estimating mixture of
Gaussians or for estimating the parameters of a hidden Markov model.
Gaussians or for estimating the parameters of a hidden Markov model.

Revision as of 11:52, 22 October 2012

The CLIP Colloquium is a weekly speaker series organized and hosted by CLIP Lab. The talks are open to everyone. Most talks are held at 11AM in AV Williams 3258 unless otherwise noted. Typically, external speakers have slots for one-on-one meetings with Maryland researchers before and after the talks; contact the host if you'd like to have a meeting.

If you would like to get on the cl-colloquium@umiacs.umd.edu list or for other questions about the colloquium series, e-mail Jimmy Lin, the current organizer.


{{#widget:Google Calendar |id=lqah25nfftkqi2msv25trab8pk@group.calendar.google.com |color=B1440E |title=Upcoming Talks |view=AGENDA |height=300 }}


10/03/2012: Consistent and Efficient Algorithms for Latent-Variable PCFGs

Speaker: Shay Cohen, Columbia University
Time: Wednesday, October 3, 2012, 11:00 AM
Venue: AVW 3258

There has been an increased interest in the machine learning community in spectral algorithms for estimating models with latent variables. Examples include algorithms for estimating mixture of Gaussians or for estimating the parameters of a hidden Markov model.

The EM algorithm has been the mainstay for estimation with latent variables, but because it is not guaranteed to converge to a global maximum of the likelihood, it is not a consistent estimator. Spectral algorithms, on the other hand, are often shown to be consistent.

In this talk, I am interested in presenting a spectral algorithm for latent-variable PCFGs, a model widely used in the NLP community for parsing. This model, originally introduced by Matsuzaki et al. (2005), augments with a latent state the nonterminals in an underlying PCFG grammar. These latent states re-fine the nonterminal category in order to capture subtle syntactic nuances in the data. This model has been successfully implemented in state-of-the-art parsers such as the Berkeley parser (Petrov et al., 2006).

Our spectral algorithm for latent-variable PCFGs is based on a novel tensor formulation designed for inference with PCFGs. This tensor formulation yields an "observable operator model" for PCFGs which can be readily used for spectral estimation.

The algorithm we developed is considerably faster than EM, and makes only one pass over the data. Statistics are collected from the data in this pass, and singular value decomposition is performed on matrices containing these statistics. Our algorithm is also provably consistent in the sense that, given enough samples, it will estimate probabilities for test trees close to their true probabilities under the latent-variable PCFG model.

If time permits, I will also present a method to improve the efficiency of parsing with latent-variable PCFGs. This method relies on tensor decomposition of the latent-variable PCFG. The tensor decomposition is approximate, and therefore the new parser is an approximate parser as well. Still, the quality of approximation can be guaranteed theoretically by inspecting how errors from the approximation propagate in the parse trees.

10/10/2012: Beyond MaltParser - Advances in Transition-Based Dependency Parsing

Speaker: Joakim Nivre, Uppsala University / Google
Time: Wednesday, October 10, 2012, 11:00 AM
Venue: AVW 3258

The transition-based approach to dependency parsing has become popular thanks to its simplicity and efficiency. Systems like MaltParser achieve linear-time parsing with projective dependency trees using locally trained classifiers to predict the next parsing action and greedy best-first search to retrieve the optimal parse tree, assuming that the input sentence has been morphologically disambiguated using a part-of-speech tagger. In this talk, I survey recent developments in transition-based dependency parsing that address some of the limitations of the basic transition-based approach. First, I show how globally trained classifiers and beam search can be used to mitigate error propagation and enable richer feature representations. Secondly, I discuss different methods for extending the coverage to non-projective trees, which are required for linguistic adequacy in many languages.Finally, I present a model for joint tagging and parsing that leads to improvements in both tagging and parsing accuracy as compared to the standard pipeline approach.

About the Speaker: Joakim Nivre is Professor of Computational Linguistics at Uppsala University and currently visiting scientist at Google, New York. He holds a Ph.D. in General Linguistics from the University of Gothenburg and a Ph.D. in Computer Science from Växjö University. Joakim's research focuses on data-driven methods for natural language processing, in particular for syntactic and semantic analysis. He is one of the main developers of the transition-based approach to syntactic dependency parsing, described in his 2006 book Inductive Dependency Parsing and implemented in the MaltParser system. Joakim's current research interests include the analysis of mildly non-projective dependency structures, the integration of morphological and syntactic processing for richly inflected languages, and methods for cross-framework parser evaluation. He has produced over 150 scientific publications, including 3 books, and has given nearly 70 invited talks at conferences and institutions around the world. He is the current secretary of the European Chapter of the Association for Computational Linguistics.

Host: Hal Daume III, hal@umd.edu

10/17/2012: Using Syntactic Head Information in Hierarchical Phrase-Based Translation

Speaker: Junhui Li
Time: Wednesday, October 17, 2012, 11:00 AM
Venue: AVW 3258

The traditional hierarchical phrase-based (HPB) model is prone to overgeneration due to lack of linguistic knowledge: the grammar may suggest more derivations than appropriate, many of which may lead to ungrammatical translations. On the other hand, limitations of glue grammar rules in HPB model may actually prevent systems from considering some reasonable derivations. This talk presents a simple but effective translation model, called the Head-Driven HPB (HD-HPB) model, which incorporates head information in translation rules to better capture syntax-driven information in a derivation. In addition, unlike the original glue rules, the HD-HPB model allows improved reordering between any two neighboring non-terminals to explore a larger reordering search space. In experiments, we examined different head label sets to refine non-terminal X, including part-of-speech (POS) tags, coarsed POS tags, dependency labels.

About the Speaker: Junhui Li joined CLIP lab as a post-doc researcher from Aug 2012. He was previously a post-doc researcher in the Centre for Next Generation Localisation (CNGL), at Dublin City University from Feb 2011 to Jul 2012. Before that, he was a student at NLP Lab of Soochow University, China.

10/23/2012: Bootstrapping via Graph Propagation

Speaker: Anoop Sarkar, Simon Fraser University
Time: Tuesday, October 23, 2012, 2:00 PM
Venue: AVW 4172

Note special time and place!!!

In natural language processing, the bootstrapping algorithm introduced by David Yarowsky (15 years ago) is a discriminative unsupervised learning algorithm that uses some seed rules to bootstrap a classifier (this is the ordinary sense of bootstrapping which is distinct from the Bootstrap in statistics). The Yarowsky algorithm works remarkably well on a wide variety of NLP classification tasks such as distinguishing between word senses and deciding if a noun phrase is an organization, location, or person.

Extending previous attempts at providing an objective function optimization view of Yarowsky, we show that bootstrapping a classifier from a small set of seed rules can be viewed as the propagation of labels between examples via features shared between them. This paper introduces a novel variant of the Yarowsky algorithm based on this view. It is a bootstrapping learning method which uses a graph propagation algorithm with a well defined per-iteration objective function that incorporates the cautious behaviour of the original Yarowsky algorithm.

The experimental results show that our proposed bootstrapping algorithm achieves state of the art performance or better on several different natural language data sets, outperforming other unsupervised methods such as the EM algorithm. We show that cautious learning is an important principle in unsupervised learning, however we do not understand it well, and we show that the Yarowsky algorithm can outperform or match co-training without any reliance on multiple views.

About the Speaker: Anoop Sarkar is an Associate Professor at Simon Fraser University in British Columbia, Canada where he co-directs the Natural Language Laboratory. He received his Ph.D. from the Department of Computer and Information Sciences at the University of Pennsylvania under Prof. Aravind Joshi for his work on semi-supervised statistical parsing using tree-adjoining grammars.

His research is focused on statistical parsing and machine translation (exploiting syntax or morphology, semi-supervised learning, and domain adaptation). His interests also include formal language theory and stochastic grammars, in particular tree automata and tree-adjoining grammars.

10/31/2012: Kilian Weinberger

Previous Talks