Ameeta Agrawal Nikolay Yakovets 01 Dec 2011. …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning.

Slides:



Advertisements
Similar presentations
Symbol Table.
Advertisements

Tracking L2 Lexical and Syntactic Development Xiaofei Lu CALPER 2010 Summer Workshop July 14, 2010.
Evaluation of Text Generation: Automatic Evaluation vs. Variation Amanda Stent, Mohit Singhai, Matthew Marge.
Recognizing Textual Entailment Challenge PASCAL Suleiman BaniHani.
Extracting Simplified Statements for Factual Question Generation Michael Heilman and Noah A. Smith 1.
 A subtask of text simplification  Replacing words or short phrases by simpler variants in a context aware fashion  Motivation  To reach out to wider.
Linear Obfuscation to Combat Symbolic Execution Zhi Wang 1, Jiang Ming 2, Chunfu Jia 1 and Debin Gao 3 1 Nankai University 2 Pennsylvania State University.
PSY 369: Psycholinguistics Some basic linguistic theory part2.
Predicting Text Quality for Scientific Articles Annie Louis University of Pennsylvania Advisor: Ani Nenkova.
1 Improving a Statistical MT System with Automatically Learned Rewrite Patterns Fei Xia and Michael McCord (Coling 2004) UW Machine Translation Reading.
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
Course Summary LING 575 Fei Xia 03/06/07. Outline Introduction to MT: 1 Major approaches –SMT: 3 –Transfer-based MT: 2 –Hybrid systems: 2 Other topics.
Semi-Automatic Learning of Transfer Rules for Machine Translation of Low-Density Languages Katharina Probst April 5, 2002.
Does Syntactic Knowledge help English- Hindi SMT ? Avinesh. PVS. K. Taraka Rama, Karthik Gali.
1 Statistical NLP: Lecture 13 Statistical Alignment and Machine Translation.
1.3 Executing Programs. How is Computer Code Transformed into an Executable? Interpreters Compilers Hybrid systems.
Learning Table Extraction from Examples Ashwin Tengli, Yiming Yang and Nian Li Ma School of Computer Science Carnegie Mellon University Coling 04.
Toshiba Update 04/09/2006 Data-Driven Prosody and Voice Quality Generation for Emotional Speech Zeynep Inanoglu & Steve Young Machine Intelligence Lab.
Natural Language Processing Lab Northeastern University, China Feiliang Ren EBMT Based on Finite Automata State Transfer Generation Feiliang Ren.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Tree Kernels for Parsing: (Collins & Duffy, 2001) Advanced Statistical Methods in NLP Ling 572 February 28, 2012.
GLOSSARY COMPILATION Alex Kotov (akotov2) Hanna Zhong (hzhong) Hoa Nguyen (hnguyen4) Zhenyu Yang (zyang2)
PowerConc: An R-gram Based Corpus Analysis Tool Jiajin Xu & Yunlong Jia Beijing Foreign Studies University.
The Impact of Grammar Enhancement on Semantic Resources Induction Luca Dini Giampaolo Mazzini
METEOR-Ranking & M-BLEU: Flexible Matching & Parameter Tuning for MT Evaluation Alon Lavie and Abhaya Agarwal Language Technologies Institute Carnegie.
Advanced Signal Processing 05/06 Reinisch Bernhard Statistical Machine Translation Phrase Based Model.
Based on “Semi-Supervised Semantic Role Labeling via Structural Alignment” by Furstenau and Lapata, 2011 Advisors: Prof. Michael Elhadad and Mr. Avi Hayoun.
Illinois-Coref: The UI System in the CoNLL-2012 Shared Task Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Mark Sammons, and Dan Roth Supported by ARL,
Processing of large document collections Part 7 (Text summarization: multi- document summarization, knowledge- rich approaches, current topics) Helena.
Testing Grammars For Top Down Parsers By Asma M Paracha, Frantisek F. Franek Dept. of Computing & Software McMaster University Hamilton, Ont.
| Computer Science Department | UKP Lab - Prof. Dr. Iryna Gurevych | Zhemin Zhu | Zhemin Zhu, UKP, TU Darmstadt, Germany Delphine Bernhard,
Automatic Readability Evaluation Using a Neural Network Vivaek Shivakumar October 29, 2009.
A Language Independent Method for Question Classification COLING 2004.
Reordering Model Using Syntactic Information of a Source Tree for Statistical Machine Translation Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro.
Good Question! Statistical Ranking for Question Generation
Review 1.Lexical Analysis 2.Syntax Analysis 3.Semantic Analysis 4.Code Generation 5.Code Optimization.
Approaches to Machine Translation CSC 5930 Machine Translation Fall 2012 Dr. Tom Way.
Sentence Compression Based on ILP Decoding Method Hongling Wang, Yonglei Zhang, Guodong Zhou NLP Lab, Soochow University.
Joey Paquet, 2000, Lecture 5 Error Recovery Techniques in Top-Down Predictive Syntactic Analysis.
What’s in a translation rule? Paper by Galley, Hopkins, Knight & Marcu Presentation By: Behrang Mohit.
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Methods for Automatic Evaluation of Sentence Extract Summaries * G.Ravindra +, N.Balakrishnan +, K.R.Ramakrishnan * Supercomputer Education & Research.
The Functions and Purposes of Translators Syntax (& Semantic) Analysis.
LREC 2008 Marrakech 29 May Caroline Lavecchia, Kamel Smaïli and David Langlois LORIA / Groupe Parole, Vandoeuvre-Lès-Nancy, France Phrase-Based Machine.
A non-contiguous Tree Sequence Alignment-based Model for Statistical Machine Translation Jun Sun ┼, Min Zhang ╪, Chew Lim Tan ┼ ┼╪
Compiler Construction By: Muhammad Nadeem Edited By: M. Bilal Qureshi.
1 Minimum Error Rate Training in Statistical Machine Translation Franz Josef Och Information Sciences Institute University of Southern California ACL 2003.
Finding document topics for improving topic segmentation Source: ACL2007 Authors: Olivier Ferret (18 route du Panorama, BP6) Reporter:Yong-Xiang Chen.
8 December 1997Industry Day Applications of SuperTagging Raman Chandrasekar.
Improving a Statistical MT System with Automatically Learned Rewrite Rules Fei Xia and Michael McCord IBM T. J. Watson Research Center Yorktown Heights,
October 10, 2003BLTS Kickoff Meeting1 Transfer with Strong Decoding Learning Module Transfer Rules {PP,4894} ;;Score: PP::PP [NP POSTP] -> [PREP.
1 ICASSP Paper Survey Presenter: Chen Yi-Ting. 2 Improved Spoken Document Retrieval With Dynamic Key Term Lexicon and Probabilistic Latent Semantic Analysis.
Phone-Level Pronunciation Scoring and Assessment for Interactive Language Learning Speech Communication, 2000 Authors: S. M. Witt, S. J. Young Presenter:
Joey Paquet, 2000, 2002, 2008, 2012, Lecture 5 Error Recovery Techniques in Top-Down Predictive Syntactic Analysis.
. Sequence Alignment Author:- Aya Osama Supervision:- Dr.Noha khalifa.
Text Summarization using Lexical Chains. Summarization using Lexical Chains Summarization? What is Summarization? Advantages… Challenges…
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
Incremental Text Structuring with Hierarchical Ranking Erdong Chen Benjamin Snyder Regina Barzilay.
LingWear Language Technology for the Information Warrior Alex Waibel, Lori Levin Alon Lavie, Robert Frederking Carnegie Mellon University.
WikiSimple – Automatic Simplification of Wikipedia Articles By Kristian Woodsend and Mirella Lapata Presented by Kira Belkin 05/
The University of Illinois System in the CoNLL-2013 Shared Task Alla RozovskayaKai-Wei ChangMark SammonsDan Roth Cognitive Computation Group University.
Approaches to Machine Translation
Piecewise linear gap alignment.
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
Semi-Structured Reasoning for Answering Science Questions
Statistical NLP: Lecture 13
Lecture 12: Data Wrangling
Approaches to Machine Translation
Statistical Machine Translation Papers from COLING 2004
Function Notation.
Presentation transcript:

Ameeta Agrawal Nikolay Yakovets 01 Dec 2011

…Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature…. In complex sentences, facts can be presented with varied and complex linguistic constructions. 2

…Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature…. 3 main clause

In complex sentences, facts can be presented with varied and complex linguistic constructions. …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature…. 4 main clause appositive

In complex sentences, facts can be presented with varied and complex linguistic constructions. …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature…. 5 main clause appositive participial phrase

In complex sentences, facts can be presented with varied and complex linguistic constructions. …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature…. 6 main clause appositive participial phraseconjunction of clauses

In complex sentences, facts can be presented with varied and complex linguistic constructions. Prime Minister Vladimir V. Putin cut short a trip to Siberia. He is the country's top leader. He returned to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism. 7 Output:

 Source:  Complex sentence  Target:  Set of simple declarative sentences  Easier to read  Simpler vocabulary and syntactic structure

 Development of reading aids for:  People with aphasia (Carroll et al., 1999)  Non-native speakers (Siddharthan, 2003)  Individuals with low literacy (Watanabe et al., 2009)  Improve performance of:  Parsers (Chandrasekar et al., 1996)  Summarizers (Klebanov et al., 2004)  Semantic role labelers (Vickrey and Koller, 2008)

 Baseline: substitution of difficult words with more common words  Input: Prime Minister Putin, the country’s paramount leader…  Output: Prime Minister Putin, the country’s top leader…  Sentence structural rules  e.g. Rewrite operations: deletion, substitution, insertion, reordering, etc.  Input: Prime Minister Putin, the country’s paramount leader, cut short a trip to Siberia.  Output: Prime Minister Putin is the country’s top leader. He cut short a trip to Siberia.  Challenge: learning the rules  How do you do this automatically?

 Woodsend, Lapata, 2011  Wikipedia to induce quasi-synch grammar  align phrases and learn syntactic & lexical simplification rules  Integer Linear Programming to put the phrases together  Coster, Kauchak, 2011  generate a parallel corpus using Wikipedia and Simple Wikipedia  align phrases and dynamic programming to find the best global sentence alignment  Biran, Brody, Elhadad, 2011  use Wikipedia revision histories to learn lexical simplification rules

 Woodsend, Lapata, 2011  Wikipedia and Simple Wikipedia to induce quasi- synch grammar  align phrases and learn syntactic & lexical simplification rules  Integer Linear Programming to put the phrases together  Coster, Kauchak, 2011  generate a parallel corpus using Wikipedia and Simple Wikipedia  align phrases to find the best global sentence alignment  Biran, Brody, Elhadad, 2011  use Wikipedia and Simple Wikipedia revision histories to learn lexical simplification rules

 Alignment  Most alignment previously done at global level  Useful when input and output sequences are similar and of roughly equal size  But consider the example sentences: …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism, so the attacks could be considered a challenge to his stature… Prime Minister Vladimir V. Putin cut short a trip to Siberia. He is the country's top leader. He returned to Moscow to oversee the federal response. Mr. Putin built his reputation in part on his success at suppressing terrorism.  Sequences not similar, not equal size!

 Alignment  Propose to test local alignment  More useful for dissimilar sequences that are suspected to contain regions of similarity  Other sequence alignment algorithms used in Bioinformatics  Perhaps conceptual graphs as they provide an intuitive and easily understandable means to represent knowledge (??)

 Two ways:  Human judges  Automatic evaluation (readability measures) For Wikipedia, Simple Wikipedia and our output: Flesch-Kincaid Grade Level index BLEU: scores the target output by counting n-gram matches with the reference TERp: similar to word error rate, allows shifts Closest to Simple Wikipedia = good!