David L. Chen and Raymond J. Mooney Department of Computer Science The University of Texas at Austin Learning to Interpret Natural Language Navigation.

Slides:



Advertisements
Similar presentations
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
Advertisements

Online Max-Margin Weight Learning for Markov Logic Networks Tuyen N. Huynh and Raymond J. Mooney Machine Learning Group Department of Computer Science.
Proceedings of the Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2007) Learning for Semantic Parsing Advisor: Hsin-His.
Adapting Discriminative Reranking to Grounded Language Learning Joohyun Kim and Raymond J. Mooney Department of Computer Science The University of Texas.
Recognizing Implicit Discourse Relations in the Penn Discourse Treebank Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng Department of Computer Science National.
Predicting the Semantic Orientation of Adjective Vasileios Hatzivassiloglou and Kathleen R. McKeown Presented By Yash Satsangi.
Robot? What’s a Robot? Introducing Karel-the-Robot.
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
Learning Table Extraction from Examples Ashwin Tengli, Yiming Yang and Nian Li Ma School of Computer Science Carnegie Mellon University Coling 04.
1 Learning to Interpret Natural Language Navigation Instructions from Observation Ray Mooney Department of Computer Science University of Texas at Austin.
1 Learning Natural Language from its Perceptual Context Ray Mooney Department of Computer Science University of Texas at Austin Joint work with David Chen.
Richard Socher Cliff Chiung-Yu Lin Andrew Y. Ng Christopher D. Manning
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Some Thoughts on HPC in Natural Language Engineering Steven Bird University of Melbourne & University of Pennsylvania.
Author: James Allen, Nathanael Chambers, etc. By: Rex, Linger, Xiaoyi Nov. 23, 2009.
Student-teacher Training at Muban Chombueng Rajabhat University Storyboards EDU623 Designing Learning Environments Bradley Opatz.
David L. Chen Supervisor: Professor Raymond J. Mooney Ph.D. Dissertation Defense January 25, 2012 Learning Language from Ambiguous Perceptual Context.
David Chen Advisor: Raymond Mooney Research Preparation Exam August 21, 2008 Learning to Sportscast: A Test of Grounded Language Acquisition.
The CoNLL-2013 Shared Task on Grammatical Error Correction Hwee Tou Ng, Yuanbin Wu, and Christian Hadiwinoto 1 Siew.
Using Soar for an indoor robotic search mission Scott Hanford Penn State University Applied Research Lab 1.
Leveraging Reusability: Cost-effective Lexical Acquisition for Large-scale Ontology Translation G. Craig Murray et al. COLING 2006 Reporter Yong-Xiang.
Processing of large document collections Part 7 (Text summarization: multi- document summarization, knowledge- rich approaches, current topics) Helena.
David L. Chen Fast Online Lexicon Learning for Grounded Language Acquisition The 50th Annual Meeting of the Association for Computational Linguistics (ACL)
PETRA – the Personal Embedded Translation and Reading Assistant Werner Winiwarter University of Vienna InSTIL/ICALL Symposium 2004 June 17-19, 2004.
Abstract Question answering is an important task of natural language processing. Unification-based grammars have emerged as formalisms for reasoning about.
Topic Modelling: Beyond Bag of Words By Hanna M. Wallach ICML 2006 Presented by Eric Wang, April 25 th 2008.
Thanks to Dr. Kris Schindler for this (and all Karel the Robot slides)
ORIENTEERING. Orienteering, What Is It? Orienteering is a competition to find in in the woods. The person who finds all the in the fastest time, wins.
David Steer Department of Geosciences The University of Akron Learning objectives and assessments May 2013.
A Bootstrapping Method for Building Subjectivity Lexicons for Languages with Scarce Resources Author: Carmen Banea, Rada Mihalcea, Janyce Wiebe Source:
Unit-1 Introduction Prepared by: Prof. Harish I Rathod
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
Using NLP to Support Scalable Assessment of Short Free Text Responses Alistair Willis Department of Computing and Communications, The Open University,
Learning High Level Planning From Text Nate Kushman S.R.K. Branavan, Tao Lei, Regina Barzilay 1.
Efficient Instant-Fuzzy Search with Proximity Ranking Authors: Inci Centidil, Jamshid Esmaelnezhad, Taewoo Kim, and Chen Li IDCE Conference 2014 Presented.
1 David Chen & Raymond Mooney Department of Computer Sciences University of Texas at Austin Learning to Sportscast: A Test of Grounded Language Acquisition.
Artificial Intelligence 2005/06 Partially Ordered Plans - or: "How Do You Put Your Shoes On?"
A Model for Learning the Semantics of Pictures V. Lavrenko, R. Manmatha, J. Jeon Center for Intelligent Information Retrieval Computer Science Department,
Programming Languages and Design Lecture 3 Semantic Specifications of Programming Languages Instructor: Li Ma Department of Computer Science Texas Southern.
Robotics Club: 5:30 this evening
Paul AAAI Symposium Mar 2009 : Agents that Learn from Human Teachers SCAFFOLDING INSTRUCTIONS TO LEARN PROCEDURES FROM USERS Paul Groth and Yolanda.
University of Texas at Austin Machine Learning Group Department of Computer Sciences University of Texas at Austin Learning a Compositional Semantic Parser.
Natural Language Interfaces to Ontologies Danica Damljanović
Mining Dependency Relations for Query Expansion in Passage Retrieval Renxu Sun, Chai-Huat Ong, Tat-Seng Chua National University of Singapore SIGIR2006.
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
Wearable Virtual Guide for Indoor Navigation. Introduction Assistance for indoor navigation using a wearable vision system Novel cognitive model for representing.
Finding document topics for improving topic segmentation Source: ACL2007 Authors: Olivier Ferret (18 route du Panorama, BP6) Reporter:Yong-Xiang Chen.
Toward Semantic Search: RDFa based facet browser Jin Guang Zheng Tetherless World Constellation.
David Chen Supervising Professor: Raymond J. Mooney Doctoral Dissertation Proposal December 15, 2009 Learning Language from Perceptual Context 1.
Department of Computer Science The University of Texas at Austin USA Joint Entity and Relation Extraction using Card-Pyramid Parsing Rohit J. Kate Raymond.
Learning Event Durations from Event Descriptions Feng Pan, Rutu Mulkar, Jerry R. Hobbs University of Southern California ACL ’ 06.
NATURAL LANGUAGE PROCESSING
Dependency Parsing Niranjan Balasubramanian March 24 th 2016 Credits: Many slides from: Michael Collins, Mausam, Chris Manning, COLNG 2014 Dependency Parsing.
Parsing Natural Scenes and Natural Language with Recursive Neural Networks INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML 2011) RICHARD SOCHER CLIFF.
1 Sections 3.1 – 3.2a Basic Syntax and Semantics Fundamentals of Java: AP Computer Science Essentials, 4th Edition Lambert / Osborne.
Grounded Language Learning
The Dance of the Foci David Seppala-Holtzman St. Joseph’s College
Linguistic Graph Similarity for News Sentence Searching
Web News Sentence Searching Using Linguistic Graph Similarity
Semantic Parsing for Question Answering
Copyright © 2008 by Helene G. Kershner
Copyright © 2008 by Helene G. Kershner
Improving a Pipeline Architecture for Shallow Discourse Parsing
Joohyun Kim Supervising Professor: Raymond J. Mooney
Dude, where’s that IP? Circumventing measurement-based geolocation
Integrating Learning of Dialog Strategies and Semantic Parsing
Unified Pragmatic Models for Generating and Following Instructions
Learning to Sportscast: A Test of Grounded Language Acquisition
Sadov M. A. , NRU HSE, Moscow, Russia Kutuzov A. B
CH 4 - Language semantics
Presentation transcript:

David L. Chen and Raymond J. Mooney Department of Computer Science The University of Texas at Austin Learning to Interpret Natural Language Navigation Instructions from Observations Twenty-Fifth Conference on Artificial Intelligence (AAAI-11) August 9, 2011

Navigation Task Learn to interpret and follow free-form navigation instructions – e.g. Go down this hall and make a right when you see an elevator to your left Assume no prior linguistic knowledge Learn by observing how humans follow instructions Use virtual worlds and instructor/follower data from MacMahon et al. (2006)

H C L S S B C H E L E Environment H – Hat Rack L – Lamp E – Easel S – Sofa B – Barstool C - Chair 3

Environment 4

Example Task Task: Navigate from location 3 to location H H 4 4 5

Example Task “Take your first left. Go all the way down until you hit a dead end.” “Go towards the coat hanger and turn left at it. Go straight down the hallway and the dead end is position 4.” “Walk to the hat rack. Turn left. The carpet should have green octagons. Go to the end of this alley. This is p-4.” “Walk forward once. Turn left. Walk forward twice.” 6

Example Task 3 3 H H 4 4 Observed primitive actions: Forward, Left, Forward, Forward 7 Task: Navigate from location 3 to location 4

Related Work Simpler worlds, no prior linguistic knowledge – Shimizu and Haas 2009 – Matuszek et al More complex environments with prior linguistic knowledge – MacMahon et al – Vogel and Jurafsky 2010 – Kollar et al. 2010

Observation Instruction World State Training Action Trace

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Training Action Trace Navigation Plan Constructor

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Training Action Trace Navigation Plan Constructor Semantic Parser Learner

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Training Action Trace Navigation Plan Constructor Semantic Parser Learner Plan Refinement

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Instruction World State Training Testing Action Trace Navigation Plan Constructor Semantic Parser Learner Plan Refinement

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Instruction World State Training Testing Action Trace Navigation Plan Constructor Semantic Parser Learner Plan Refinement Semantic Parser

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Execution Module (MARCO) Instruction World State Training Testing Action Trace Navigation Plan Constructor Semantic Parser Learner Plan Refinement Semantic Parser Action Trace

Learning system for parsing navigation instructions Learning system for parsing navigation instructions Observation Instruction World State Execution Module (MARCO) Instruction World State Training Testing Action Trace Navigation Plan Constructor Semantic Parser Learner Plan Refinement Semantic Parser Action Trace

Constructing Navigation Plans Basic plan: Directly model the observed actions Travel Turn steps: 1 LEFT Instruction: Walk to the couch and turn left Action Trace: Forward, Left

Constructing Navigation Plans Landmarks plan: Add interleaving verification steps Basic plan: Directly model the observed actions Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Travel Turn steps: 1 LEFT Instruction: Walk to the couch and turn left Action Trace: Forward, Left

Plan Refinement Remove extraneous details in the plans First learn the meaning of words and short phrases Use the learned lexicon to remove parts of the plans unrelated to the instructions

Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Turn and walk to the couch Walk to the couch and turn left Walk to the couch and head down the brick hallway 1. Collect all plans g that co-occur with a word or short phrase w

Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Possible meanings of walk to the couch: 1. Collect all plans g that co-occur with a word or short phrase w

Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Possible meanings of walk to the couch: 2. Take intersections of all possible pairs of meanings Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT

Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Possible meanings of walk to the couch: 2. Take intersections of all possible pairs of meanings Turn LEFT Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT

Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Possible meanings of walk to the couch: 2. Take intersections of all possible pairs of meanings Turn LEFT Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Verify Travel at: SOFA

Lexicon Learning Verify Travel Turn Verify front: BRICK HALL steps: 5 at: SOFA RIGHT front: CHAIR Possible meanings of walk to the couch: 2. Take intersections of all possible pairs of meanings Turn LEFT Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Verify Travel at: SOFA …

Lexicon Learning Possible meanings of walk to the couch: 3. Rank the entries by the scoring function Turn LEFT Verify Travel Turn Verify LEFT steps: 2 at: SOFA front: SOFA front: BLUE HALL front: BLUE HALL Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Verify Travel at: SOFA …

Refining Plans Using A Lexicon Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT Walk to the couch and turn left

Refining Plans Using A Lexicon Walk to the couch and turn left Lexicon entry: turn left Turn LEFT Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT

Refining Plans Using A Lexicon Walk to the couch and Lexicon entry: walk to the couch Verify Travel at: SOFA Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT

Refining Plans Using A Lexicon and Lexicon exhausted Verify Travel Turn Verify front: BLUE HALL front: BLUE HALL steps: 1 at: SOFA LEFT

Refining Plans Using A Lexicon and Remove all unmarked nodes Verify Travel Turn at: SOFA LEFT

Refining Plans Using A Lexicon Walk to the couch and turn left Verify Travel Turn at: SOFA LEFT

Experiments Single SentencesParagraphs # Instructions Vocabulary Size Avg. # sentences Avg. # words Avg. # actions Three different virtual worlds Hand-segmented original data to single sentences

Plan Construction Test how well the system infers the correct navigation plans Gold-standard plans annotated manually Use partial parse accuracy as metric – Credit for the correct action type (e.g. Turn) – Additional credit for correct arguments (e.g. LEFT) Lexicon learned and tested on the same data from two maps out of three

Plan Construction PrecisionRecallF1 Basic Plans Landmarks Plans Refined Landmarks Plans

End-to-end Execution Test how well the system can perform the overall navigation task Leave-one-map-out approach Strict metric: Only successful if the final position matches exactly

End-to-end Execution Lower baseline – A simple generative model based on the frequency of actions alone Upper baselines – Training with human annotated gold plans – Complete MARCO system (MacMahon, 2006) – Humans

End-to-end Execution Single SentencesParagraphs Simple Generative Model 11.08%2.15% Basic Plans 56.99%13.99% Landmarks Plans 21.95%2.66% Refined Landmarks Plans 54.40%16.18% Human Annotated Plans 58.29%26.15% MARCO 77.87%55.69% Human Followers N/A69.64%

End-to-end Execution Single SentencesParagraphs Simple Generative Model 11.08%2.15% Basic Plans 56.99%13.99% Landmarks Plans 21.95%2.66% Refined Landmarks Plans 54.40%16.18% Human Annotated Plans 58.29%26.15% MARCO 77.87%55.69% Human Followers N/A69.64%

End-to-end Execution Single SentencesParagraphs Simple Generative Model 11.08%2.15% Basic Plans 56.99%13.99% Landmarks Plans 21.95%2.66% Refined Landmarks Plans 54.40%16.18% Human Annotated Plans 58.29%26.15% MARCO 77.87%55.69% Human Followers N/A69.64%

End-to-end Execution Single SentencesParagraphs Simple Generative Model 11.08%2.15% Basic Plans 56.99%13.99% Landmarks Plans 21.95%2.66% Refined Landmarks Plans 54.40%16.18% Human Annotated Plans 58.29%26.15% MARCO 77.87%55.69% Human Followers N/A69.64%

Example Parse Instruction: “Place your back against the wall of the ‘T’ intersection. Turn left. Go forward along the pink-flowered carpet hall two segments to the intersection with the brick hall. This intersection contains a hatrack. Turn left. Go forward three segments to an intersection with a bare concrete hall, passing a lamp. This is Position 5.” Parse:Turn ( ), Verify ( back: WALL ), Turn ( LEFT ), Travel ( ), Verify ( side: BRICK HALLWAY ), Turn ( LEFT ), Travel ( steps: 3 ), Verify ( side: CONCRETE HALLWAY )

Conclusion Presented an end-to-end system that learns to interpret free-form navigation instructions Learn by observing how humans follow instructions No prior linguistic knowledge More details and data/code at: