Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent.

Slides:



Advertisements
Similar presentations
Support to the Policy Making Process Knowledge Maps, Ontologies and multi- criteria decision making Arantza Aldea.
Advertisements

A Human-Centered Computing Framework to Enable Personalized News Video Recommendation (Oh Jun-hyuk)
The 20th International Conference on Software Engineering and Knowledge Engineering (SEKE2008) Department of Electrical and Computer Engineering
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
Ciro Cattuto, Dominik Benz, Andreas Hotho, Gerd Stumme Presented by Smitashree Choudhury.
Chapter 6: Modeling and Representation Service-Oriented Computing: Semantics, Processes, Agents – Munindar P. Singh and Michael N. Huhns, Wiley, 2005.
Improved TF-IDF Ranker
A Linguistic Approach for Semantic Web Service Discovery International Symposium on Management Intelligent Systems 2012 (IS-MiS 2012) July 13, 2012 Jordy.
ConceptNet: A Wonderful Semantic World
Recognizing Implicit Discourse Relations in the Penn Discourse Treebank Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng Department of Computer Science National.
Research topics Semantic Web - Spring 2007 Computer Engineering Department Sharif University of Technology.
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Faculty Of Applied Science Simon Fraser University Cmpt 825 presentation Corpus Based PP Attachment Ambiguity Resolution with a Semantic Dictionary Jiri.
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
Visual Web Information Extraction With Lixto Robert Baumgartner Sergio Flesca Georg Gottlob.
Gimme’ The Context: Context- driven Automatic Semantic Annotation with CPANKOW Philipp Cimiano et al.
Information Extraction and Ontology Learning Guided by Web Directory Authors:Martin Kavalec Vojtěch Svátek Presenter: Mark Vickers.
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
Designing clustering methods for ontology building: The Mo’K workbench Authors: Gilles Bisson, Claire Nédellec and Dolores Cañamero Presenter: Ovidiu Fortu.
Article by: Feiyu Xu, Daniela Kurz, Jakub Piskorski, Sven Schmeier Article Summary by Mark Vickers.
Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Dijrre, Peter Gerstl, Roland Seiffert Presented by Huimin Ye.
Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Dijrre, Peter Gerstl, Roland Seiffert Presented by Drew DeHaas.
Ontology Learning and Population from Text: Algorithms, Evaluation and Applications Chapters Presented by Sole.
Adding Common Sense into Artificial Intelligence Common Sense Computing Initiative Software Agents Group MIT Media Lab.
Common Sense Computing MIT Media Lab Interaction Challenges for Agents with Common Sense Henry Lieberman MIT Media Lab Cambridge, Mass. USA
Ontology Learning from Text: A Survey of Methods Source: LDV Forum,Volume 20, Number 2, 2005 Authors: Chris Biemann Reporter:Yong-Xiang Chen.
ConceptNet 5 Jason Gaines 1. Overview What Is ConceptNet 5? History Structure Demonstration Questions Further Information 2.
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification on Reviews Peter D. Turney Institute for Information Technology National.
Logics for Data and Knowledge Representation Semantic Matching.
1 Statistical NLP: Lecture 10 Lexical Acquisition.
Learning Object Metadata Mining Masoud Makrehchi Supervisor: Prof. Mohamed Kamel.
APPLICATIONS OF CONTEXT FREE GRAMMARS BY, BRAMARA MANJEERA THOGARCHETI.
Division of IT Convergence Engineering Towards Unified Management A Common Approach for Telecommunication and Enterprise Usage Sung-Su Kim, Jae Yoon Chung,
Author: William Tunstall-Pedoe Presenter: Bahareh Sarrafzadeh CS 886 Spring 2015.
Using Common Sense Reasoning to Create Intelligent Mobile Applications Software Agents Group MIT Media Lab.
Spoken dialog for e-learning supported by domain ontologies Dario Bianchi, Monica Mordonini and Agostino Poggi Dipartimento di Ingegneria dell’Informazione.
Jennie Ning Zheng Linda Melchor Ferhat Omur. Contents Introduction WordNet Application – WordNet Data Structure - WordNet FrameNet Application – FrameNet.
Semantic Learning Instructor: Professor Cercone Razieh Niazi.
Annotating Words using WordNet Semantic Glosses Julian Szymański Department of Computer Systems Architecture, Faculty of Electronics, Telecommunications.
RCDL Conference, Petrozavodsk, Russia Context-Based Retrieval in Digital Libraries: Approach and Technological Framework Kurt Sandkuhl, Alexander Smirnov,
Web Usage Mining for Semantic Web Personalization جینی شیره شعاعی زهرا.
An Intelligent Analyzer and Understander of English Yorick Wilks 1975, ACM.
Dimitrios Skoutas Alkis Simitsis
Approaches to Machine Translation CSC 5930 Machine Translation Fall 2012 Dr. Tom Way.
You Are What You Tag Yi-Ching Huang and Chia-Chuan Hung and Jane Yung-jen Hsu Department of Computer Science and Information Engineering Graduate Institute.
Presented by: Ashgan Fararooy Referenced Papers and Related Work on:
1/21 Automatic Discovery of Intentions in Text and its Application to Question Answering (ACL 2005 Student Research Workshop )
Understanding RDF. 2/30 What is RDF? Resource Description Framework is an XML-based language to describe resources. A common understanding of a resource.
KNOWLEDGE BASED SYSTEMS
Finding frequent and interesting triples in text Janez Brank, Dunja Mladenić, Marko Grobelnik Jožef Stefan Institute, Ljubljana, Slovenia.
Supertagging CMSC Natural Language Processing January 31, 2006.
UWMS Data Mining Workshop Content Analysis: Automated Summarizing Prof. Marti Hearst SIMS 202, Lecture 16.
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.
Finite State Machines (FSM) OR Finite State Automation (FSA) - are models of the behaviors of a system or a complex object, with a limited number of defined.
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 1 Mining knowledge from natural language texts using fuzzy associated concept mapping Presenter : Wu,
Learning Taxonomic Relations from Heterogeneous Evidence Philipp Cimiano Aleksander Pivk Lars Schmidt-Thieme Steffen Staab (ECAI 2004)
Emotion Recognition from Text Using Situational Information and a Personalized Emotion Model Yong-soo Seol 1, Han-woo Kim 1, and Dong-joo Kim 2 1 Department.
Knowledge Structure Vijay Meena ( ) Gaurav Meena ( )
Event-Based Extractive Summarization E. Filatova and V. Hatzivassiloglou Department of Computer Science Columbia University (ACL 2004)
A Portrait of the Semantic Web in Action Jeff Heflin and James Hendler IEEE Intelligent Systems December 6, 2010 Hyewon Lim.
Semantic Interoperability in GIS N. L. Sarda Suman Somavarapu.
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
Sentiment Analysis Using Common- Sense and Context Information Basant Agarwal 1,2, Namita Mittal 2, Pooja Bansal 2, and Sonal Garg 2 1 Department of Computer.
Parsing Natural Scenes and Natural Language with Recursive Neural Networks INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML 2011) RICHARD SOCHER CLIFF.
1 Commonsense Reasoning in and over Natural Language Hugo Liu Push Singh Media Laboratory Massachusetts Institute of Technology Cambridge, MA 02139, USA.
Approaches to Machine Translation
Approaches to Machine Translation
Topic: Semantic Text Mining
Presentation transcript:

Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent Information & Engineering Systems (KES ’ 04)

2 Abstract ConceptNet is a very large semantic network of commonsense knowledge suitable for making various kinds of practical inferences over text. ConceptNet is a very large semantic network of commonsense knowledge suitable for making various kinds of practical inferences over text. To meet the dual challenge of having to encode complex higher- order concepts, and maintaining ease-of-use, we introduce a novel use of semi-structured natural language fragments as the knowledge representation of commonsense concepts. To meet the dual challenge of having to encode complex higher- order concepts, and maintaining ease-of-use, we introduce a novel use of semi-structured natural language fragments as the knowledge representation of commonsense concepts.

3 Introduction What is ConceptNet? What is ConceptNet? The largest freely available, machine-useable commonsense resource. The largest freely available, machine-useable commonsense resource. Structured as a network of semi-structured natural language fragments. Structured as a network of semi-structured natural language fragments. Consists of over 250,000 elements of commonsense knowledge. Consists of over 250,000 elements of commonsense knowledge. Inspired dually by the range of commonsense concepts and relations in Cyc, and by the ease-of-use of WordNet. Inspired dually by the range of commonsense concepts and relations in Cyc, and by the ease-of-use of WordNet.

4 Introduction The work of the author for ConceptNet The work of the author for ConceptNet 1. Extending WordNet ’ s lexical notion of nodes to a conceptual notion of nodes  Semi-structured natural language fragments according to an ontology of allowable syntactic patterns. 2. Extending WordNet ’ s small ontology of semantic relations to include a richer set of relations appropriate to concept-level nodes. 3. We supplement the ConceptNet semantic network with some methodology for reasoning. 4. We supplement the ConceptNet semantic network with a toolkit and API which supports making practical commonsense inferences about text.

5 Fig 1. An excerpt from ConceptNet ’ s semantic network of commonsense knowledge

6 Origin of ConceptNet ConceptNet is mined out of the Open Mind Commonsense (OMCS) corpus. ConceptNet is mined out of the Open Mind Commonsense (OMCS) corpus.Open Mind CommonsenseOpen Mind Commonsense A collection of nearly 700,000 semi-structured English sentences of commonsense facts. A collection of nearly 700,000 semi-structured English sentences of commonsense facts. An automatic process which applies a set of ‘ commonsense extraction rules ’. An automatic process which applies a set of ‘ commonsense extraction rules ’. A pattern matching parser uses roughly 40 mapping rules. A pattern matching parser uses roughly 40 mapping rules.

7 Structure of Concept ConceptNet nodes are fragments semi-structured to conform to preferred syntactic patterns. ConceptNet nodes are fragments semi-structured to conform to preferred syntactic patterns. 3 general classes: 3 general classes: Noun Phrases: things, places, people Noun Phrases: things, places, people Attributes: modifiers Attributes: modifiers Activity Phrases: actions and actions compounded with a NP or PP Activity Phrases: actions and actions compounded with a NP or PP ConceptNet edges are described by an ontology of 19 binary relations. ConceptNet edges are described by an ontology of 19 binary relations. The syntactic and/or semantic type of the arguments are not formally constrained. The syntactic and/or semantic type of the arguments are not formally constrained.

8 Table 2. Semantic relation types currently in ConceptNet

9 Methodology for Reasoning over Natural Language Concepts Computing Conceptual Similarity Computing Conceptual Similarity Flexible Inference Flexible Inference Context finding Context finding Inference chaining Inference chaining Conceptual analogy Conceptual analogy

10 Computing Conceptual Similarity (1/3) 1. The concept is decomposed into first order atomic concepts to compute its meaning. Ex: “ buy good cheese ” → ” buy ”, “ good ”, “ cheese ” 2. Each atom is situated within the conceptual frameworks of several resources. WordNet WordNet Longman ’ s Dictionary of Contempory English (LDOCE) Longman ’ s Dictionary of Contempory English (LDOCE) Beth Levin ’ s English Verb Classes Beth Levin ’ s English Verb Classes FrameNet FrameNet

11 Computing Conceptual Similarity (2/3) 3. Within each resource, a similarity score is produced for each pair of corresponding atoms. (verb matching verb, etc) The similarity score is inversely proportional to inference distance in WordNet, LDOCE, or FrameNet ’ s inheritance structure. The similarity score is inversely proportional to inference distance in WordNet, LDOCE, or FrameNet ’ s inheritance structure. In Levin ’ s Verb Classes, the similarity score is proportional to the percentage of alternation classes shared. In Levin ’ s Verb Classes, the similarity score is proportional to the percentage of alternation classes shared. 4. The weighted sum of the similarity scores is produced for each atom using each of the resources. Weight on each resource is proportional to the predictive accuracy of that resource. Weight on each resource is proportional to the predictive accuracy of that resource. 5. Weight on a atom is proportional to the relative importance of the different atom type.

12 Computing Conceptual Similarity (3/3) Computing conceptual similarity using lexical inferential distance is very difficult, so we can only make heuristic approximations. Computing conceptual similarity using lexical inferential distance is very difficult, so we can only make heuristic approximations. Table 3. Some pairwise similarities in ConceptNet

13 Flexible Inference One of the strengths of representing concepts in natural language is the ability to add flexibility and fuzziness to improve inference. One of the strengths of representing concepts in natural language is the ability to add flexibility and fuzziness to improve inference. Inferences in semantic networks are based on graph reasoning methods like spreading activation, structure mapping, and network traversal. Inferences in semantic networks are based on graph reasoning methods like spreading activation, structure mapping, and network traversal. Basic spreading activation Basic spreading activation activation_score(B) = activation_score(A)*weight(edge(A,B))

14 Flexible Inference – Context Finding Determining the context around a concept, or around the intersection of several concepts is useful. Determining the context around a concept, or around the intersection of several concepts is useful. The contextual neighborhood around a node is found by performing spreading activation from that source node. The contextual neighborhood around a node is found by performing spreading activation from that source node. Pairwise similarity of nodes leading to a more accurate estimation of contextual neighborhood. Pairwise similarity of nodes leading to a more accurate estimation of contextual neighborhood.

15 Flexible Inference – Inference Chaining Inference chain is a basic type of inference on a graph: traversing the graph from one node to another via some path. Inference chain is a basic type of inference on a graph: traversing the graph from one node to another via some path. A temporal chain between “ buy food ” and “ fall asleep ” : A temporal chain between “ buy food ” and “ fall asleep ” : “ buy food ”  “ have food ”  “ eat food ”  “ feel full ”  “ feel sleepy ”  “ fall asleep ” The pairwise conceptual similarity is particularly crucial to the robustness of inference chaining. The pairwise conceptual similarity is particularly crucial to the robustness of inference chaining. ex: “ buy steak ” instead of “ buy food ” (Liu, 2003) used inference chaining for affective text classification. (Liu, 2003) used inference chaining for affective text classification.

16 Flexible Inference – Conceptual Analogy Structural analogy is not just a measure of semantic distance. Structural analogy is not just a measure of semantic distance. Ex: “ wedding ” is much more like “ funeral ” than “ bride ” Structure-mapping methods are employed to generate simple conceptual analogies. Structure-mapping methods are employed to generate simple conceptual analogies. We can emphasize functional similarity versus temporal similarity by biasing the weights of particular semantic relations. We can emphasize functional similarity versus temporal similarity by biasing the weights of particular semantic relations.

17 Some Applications of ConceptNet MAKEBELIEVE MAKEBELIEVE A story-generator that allows a person to interactively invent a story with the system. A story-generator that allows a person to interactively invent a story with the system. GloBuddy GloBuddy A dynamic foreign language phrasebook. A dynamic foreign language phrasebook. AAA AAA A profiling and recommendation system that recommends products from Amazon.com by using ConceptNet to reason about a person ’ s goals and desires. A profiling and recommendation system that recommends products from Amazon.com by using ConceptNet to reason about a person ’ s goals and desires.

18 Conclusion ConceptNet is presently the largest freely available commonsense resource, with a set of tools to support several kinds of practical inferences over text. ConceptNet is presently the largest freely available commonsense resource, with a set of tools to support several kinds of practical inferences over text. ConceptNet maintains an easy-to-use knowledge representation and incorporates more complex higher-order commonsense concepts and relations. ConceptNet maintains an easy-to-use knowledge representation and incorporates more complex higher-order commonsense concepts and relations. A novel methodology for computing the pairwise similarity of concepts is presented. A novel methodology for computing the pairwise similarity of concepts is presented. ConceptNet has been widely used in a number of research projects. ConceptNet has been widely used in a number of research projects.