| |
Search videos for Parsing |
|
|
|
|
Dana Perino: We're Not Occupying Iraq, We Were Invited!
In this clip from C-SPAN, White House spokeswoman Dana Perino tells Helen Thomas that the US isn't occupying Iraq, and that we're there by invitation of the sovereign government of Iraq. Oh, and that we're there under a UN mandate. You know, the one that didn't authorize force?
Length: 72
Rating: 4.70 (78 ratings)
Tags: Dana Perino Iraq Occupation War White House Bush
|
Play |
|
|
Forest-based Search Algorithms in Parsing and Machine Translation
Google Tech Talks
March, 14 2008
ABSTRACT
Many problems in Natural Language Processing (NLP) involves an
efficient search for the best derivation over (exponentially) many
candidates, especially in parsing and machine translation. In these
cases, the
concept of "packed forest" provides a compact representation of the
huge search spaces, where efficient inference algorithms based on
Dynamic Programming (DP) are possible.
In this talk we address two important open problems within this
framework: exact k-best inference which is often used in NLP
pipelines such as parse reranking and MT rescoring, and approximate
inference when the search space is too big for exact search.
We first present a series of fast and exact k-best algorithms on
forests, which are orders of magnitudes faster than previously used
methods on state-of-the-art parsers such as Collins (1999). We then
extend these algorithms for approximate search when the forests are
too big for exact inference. We discuss two particular instances of
this new method, forest rescoring for MT decoding with integrated
language models, and forest reranking for discriminative parsing. In
the former, our methods perform orders of magnitudes faster than
conventional beam search on both state-of-the-art phrase-based and
syntax-based systems, with the same level of search error or
translation quality. In the latter, faster search also leads to
better learning, where our approximate decoding makes whole-Treebank
discriminative training practical and results in the best accuracy to
date for parsers trained on the Treebank.
This talk includes joint work with David Chiang (USC Information
Sciences Institute).
Liang Huang (2008). Forest Reranking: Discriminative Parsing with Non-
Local Features.
Proceedings of ACL 2008 (to appear).
http://www.cis.upenn.edu/~lhuang3/forest-rerank.pdf
Liang Huang and David Chiang (2007). Forest Rescoring: Faster
Decoding with Integrated Language Models.
Proceedings of ACL 2007.
http://www.cis.upenn.edu/~lhuang3/acl-cube.pdf
Liang Huang and David Chiang (2005). Better k-best Parsing.
Proceedings of IWPT 2005.
http://www.cis.upenn.edu/~lhuang3/huang-iwpt-correct.pdf
Speaker: Liang Huang
Liang Huang is a final-year PhD student at the University of
Pennsylvania, co-supervised by Aravind Joshi and Kevin Knight (USC/
ISI). He is mainly interested in the theoretical aspects of
computational linguistics, in particular, efficient algorithms in
parsing and machine translation, generic dynamic programming, and
formal properties of synchronous grammars. He also works on applying
computational linguistics to structural biology.
Length: 3679
Rating: 4.80 (12 ratings)
Tags: google techtalks techtalk engedu talk talks googletechtalks education
|
Play |
|
|
Movie/Script: Alignment and Parsing of Video and Text Transcription
Google Tech Talks
March, 26 2008
ABSTRACT
Timothee Cour - Research Scientist
Movies and TV are a rich source of highly diverse and complex video of people, objects, actions and locales "in the wild". Harvesting automatically labeled sequences of actions from video would enable creation of large-scale and highly-varied datasets. To enable such collection, we focus on the task of recovering scene structure in movies and TV series for object/person tracking and action retrieval. We present a weakly supervised algorithm that uses the screenplay and closed captions to parse a movie into a hierarchy of shots and scenes. Scene boundaries in the movie are aligned with screenplay scene labels and shots are reordered into a sequence of long continuous tracks or threads which allow for more accurate tracking of people and actions across shot boundaries. Scene segmentation, alignment, and shot threading are formulated as inference in a unified generative model and a novel hierarchical dynamic programming algorithm that can handle alignment and jump-limited reorderings in linear time is introduced. We present quantitative and qualitative results on movie alignment and parsing, and use the recovered structure for tracking and naming of characters as well as retrieval of common actions in several episodes of popular TV series.
If time permits we will also present our recent results on approximate inference with eigenvalue optimization.
Speaker: Timothee Cour - Research Scientist
Timothee Cour is a fifth year PhD student at the University of Pennsylvania, Philadelphia, in Computer Science. He completed his undergraduate education at the Ecole Polytechnique in France, majoring in Computer Science and Applied Mathematics. His research advisor is Prof. Ben Taskar and he also worked closely with Prof. Jianbo Shi.
Length: 2920
Rating: 0.00 (0 ratings)
Tags: google techtalks techtalk engedu talk talks googletechtalks education
|
Play |
|
|
Incremental Bayesian Networks for Natural Language Parsing
Google Tech Talks
August 13, 2007
ABSTRACT
Natural language parsing is a particularly challenging structure prediction problem, due to the large space of output structures and the complex nature of the statistical dependencies between features of the output structures. Typically these statistical dependencies are specified by hand, but recently there has been interest in using latent variables to induce them automatically. In this talk I will present a framework for structure prediction with latent variables based on a form of Dynamic Bayesian Network called Incremental Sigmoid Belief Networks (ISBNs), and illustrate how it can be applied to parsing. Approximations to ISBNs have achieved...
Length: 3658
Rating: 4.00 (4 ratings)
Tags: google howto incremental bayesian networks
|
Play |
|
|
CS 61B Lecture 37: Expression Parsing
CS 61B: Data Structures - Fall 2006
Instructor Jonathan Shewchuk
Fundamental dynamic data structures, including linear lists, queues, trees, and other linked structures; arrays strings, and hash tables. Storage management. Elementary principles of software engineering. Abstract data types. Algorithms for sorting and searching. Introduction to the Java programming language.
http://www.cs.berkeley.edu
Length: 2443
Rating: 5.00 (2 ratings)
Tags: CS 61b expression parsing shewchuk ucberkeley lecture
|
Play |
|
|
Parsing the Iran Challenge
Ruprecht Polenz, a senior CDU Member of the Bundestag, is one of the most powerful German voices on his country's foreign policy and national security policy issues. He has been focused on what is real, what is not, and what policy contours America and Europe should take towards Iran for some time. In addition, his Foreign Affairs Committee determines, with the government and the full Bundestag, whether or not German forces will be deployed, so he is keenly interested in NATO operations in Kosovo and Afghanistan and will speak to these topics in his remarks.
Length: 2369
Rating: 5.00 (3 ratings)
Tags: Iran Foreign Policy US NATO Kosovo Afghanistan Europe Germany
|
Play |
|
|
Google I/O 2008 - Parsing and Generating KML
Parsing and Generating KML with Google's KML Library
Michael Ashbridge (Google)
KML is a file format used to display geographic data in an earth browser, such as Google Earth, Google Maps and Google Maps for mobile. You can create KML files to pinpoint locations, add image overlays and expose rich data in new ways. This session will introduce Google's open source KML library for working with KML files. We'll explore its architecture and then show you how to parse and generate KML in your applications and scripts. Participants should have basic familiarity with KML.
Length: 2454
Rating: 0.00 (0 ratings)
Tags: Google I/O IO2008 KML
|
Play |
|
|
