The Latest Progress of KB-QA. Ming Zhou Microsoft Research Asia NLPCC 2018 Workshop Hohhot, 2018
|
|
- Emil Briggs
- 5 years ago
- Views:
Transcription
1 The Latest Progress of KB-QA Ming Zhou Microsoft Research Asia NLPCC 2018 Workshop Hohhot, 2018
2 Query CommunityQA KBQA TableQA PassageQA VQA Edited Response Question Generation Knowledge Table Doc Image Automatic Response Automatic Response Automatic Response Automatic Response Human-in-the-Loop (HI)
3 Who is Michelle Obama married to in 1992? λx. Marriage_Spouse(x, Michelle Obama) Marriage_StartDate(x, 1992) Barack Obama
4 KBQA in Search Engine
5 Semantic Parsing-based Method KBQA Information Answer Ranking-based Retrieval-based KBQA Method CCG SCFG DCS NN x Place_of_Birth Barack Obama Feature NLG Sub-graph Embedding Barack Obama Place_of_Birth Honolulu Barack Obama Place_of_Birth Honolulu
6
7 expression expression constant variable function application
8 China, Bill Gates, Mount Everest, 2017,
9 x, y, z,
10 λx. Place_Of_Birth(Barack Obama, x) the argument of the function the definition of the function
11 Deduction of two expressions λxλy. Place_Of_Birth x, y λx. (x = Barack Obama) λy. Place_Of_Birth Barack Obama, y
12 Natural Language Semantic Parsing Grammar-based Semantic Parsing Neural Network-based Semantic Parsing Logical Form
13 Logical Form Ranking Semantic Rule-Driven CYK Parsing Natural Language Question
14 syntactic semantic A CCG Rule Example border (S\NP)/NP Match natural language input natural language syntax semantics Syntactic symbols: S, N, NP, ADJ and PP Syntactic combinator: / and \ Slashes specify combination orders and directions λ-calculus expression Sematic types are the logical forms of the natural language parts
15 State borders New Mexico NP (S\NP)/NP NP S\NP > S <
16 Texas borders New Mexico borders(texas, new_mexico) use rules to extract all possible <Q, LF> pairs Texas := NP : texas borders := (S \ NP) / NP : λx.λy.borders(y, x) New Mexico := NP : new_mexico 1. maximize the likelihood: 2. keep CCG rules that occur in the highest scoring derivations of training data
17 lexical semantic Category X α β a sequence of terminal and non-terminal symbols the logical form of α Non-terminal symbols in α and β should have 1-to-1 correspondence. [Person] TomHanks Tom Hanks [Film] the moive starred by Person 1 λx. Film_Actor_Film( Person 1, x) [Film] the moive starred by Tom Hanks λx. Film_Actor_Film(Tom Hanks, x)
18 λxλy. Film_Film_Director(y, x) Film_Actor_Film(Tom Hanks, y) director of [Film] SCFG rule matching λy. Film_Actor_Film(Tom Hanks, y) the movie starred by [Person] SCFG rule matching Lots of semantic derivations will be generated during this procedure. Tom Hanks entity linking director of the movie starred by Tom Hanks
19 Paired Entities of a given KB Predicate Film.Film.Director <Forrest Gump, Robert Zemeckis> <Titanic, James Cameron> <Rain Man, Barry Levinson> Passage Retrieval from Raw Text Robert Zemeckis is director of Forrest Gump Titanic was a movie directed by James Cameron Barry Levinson was famous as the director of Rain Man Relation Patterns Film.Film.Director [Director] is director of [Film] 0.84 [Film] was a movie directed by [Director] 0.81 [Director] was famous as the director of [Film] 0.77 Director is director of Film 1 λx. Film_Director_Film(x, Film 1 )
20 Encoder Decoder
21
22 Decoder column value SQL SELECT WHERE COUNT MIN MAX AND > < = column value SQL column value t = 0 t = 2 t = 6 SQL Wilfrid Laurier York York <S> SELECT COUNT CFL Team WHERE College = "York" SQL SQL column SQL column SQL value Output Encoder Attention Pick # CFL Team Player Position College 27 Hamilton Tiger-Cats Connor Healy DB Wilfrid Laurier 28 Calgary Stampeders Anthony Forgone OL York 29 Toronto Argonauts Frank Hoffman DL York SELECT, WHERE, COUNT, MIN, MAX, AND, >, <, =. Question Table SQL
23
24 Learning-to-Rank Model Question Features Answer Features Question Feature Extraction Answer Feature Extraction Natural Language Question KB Answer Entity Candidate
25 what is the name of Justin Bieber brother attr what is det nsubj name prep_of London place_of_birth Justin Bieber person.sibling_s sibling CVT type gender sibling Person Male the nn Justin brother nn Bieber gender Jazmyn Bieber type gender Jaxon Bieber type Male Person Male Person h i (QG, TG; A) Question Graph (QG) Each feature is a pairwise concatenation of a question graph feature and a topic graph feature of a specific answer node candidate. Topic Graph (TG)
26 String Similarity Model Original Question Generated Question Answer-aware Question Generation Natural Language Question KB Answer Entity Candidate
27 which city was Obama born? Ranking Model (question-generated question) Predicate POS Question Generation Pattern NP What TYPE is the NP of ENTITY? NP VP What NP is VP by ENTITY? date of birth Barack Obama city place of birth Barack Obama DataOfBirth.BarackObama Type.City PlaceOfBirth.BarackObama
28 Distance on Embedding Space Question Embedding Answer Embedding Question Encoder (word embedding, CNN, RNN, ) Answer Encoder (word embedding, CNN, RNN, ) Natural Language Question KB Answer Entity Candidate
29 score(q, a) embedding of q embedding of a embedding matrix W dot product embedding matrix W binary encoding of q binary encoding of a 1987 Who did Clooney marry in 1987? G. Clooney K. Preston answer candidate Honolulu Model J. Travolta
30 Ranking using a set of Question-Subgraph features Original Question Answer Subgraph Answer Subgraph Extraction Natural Language Question KB Answer Entity Candidate
31
32
33 SP SP AR AR AR SP AR SP SP AR AR SP AR: Answer Ranking-based KBQA 30 SP: Semantic Parsing-based KBQA AR-based methods perform better than SP-based methods 0 F1 Score Berant 2013 Bao 2014 Bordes 2014 Berant 2014 Dong 2015 Yang 2014 Yao 2015 Bao+Yang2015 Berant 2015 Yih 2015 Xu 2016 Cheng2017
34
35
36
37
38
39
What Will Search Engines be Changed by NLP Advancements. Dr. Ming Zhou Microsoft Research Asia ICTIR-2018, Tianjin
What Will Search Engines be Changed by NLP Advancements Dr. Ming Zhou Microsoft Research Asia ICTIR-2018, Tianjin HEADER & SEARCH BOX Online Offline (Crawler) Pre-Web Phase Context & Query Understanding
More informationQuestion Answering over Knowledge Bases: Entity, Text, and System Perspectives. Wanyun Cui Fudan University
Question Answering over Knowledge Bases: Entity, Text, and System Perspectives Wanyun Cui Fudan University Backgrounds Question Answering (QA) systems answer questions posed by humans in a natural language.
More informationNeural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision Anonymized for review Abstract Extending the success of deep neural networks to high level tasks like natural language
More informationLarge-Scale Syntactic Processing: Parsing the Web. JHU 2009 Summer Research Workshop
Large-Scale Syntactic Processing: JHU 2009 Summer Research Workshop Intro CCG parser Tasks 2 The Team Stephen Clark (Cambridge, UK) Ann Copestake (Cambridge, UK) James Curran (Sydney, Australia) Byung-Gyu
More informationQuestion Answering System for Yioop
Question Answering System for Yioop Advisor Dr. Chris Pollett Committee Members Dr. Thomas Austin Dr. Robert Chun By Niravkumar Patel Problem Statement Question Answering System Yioop Proposed System Triplet
More informationConstruction and Querying of Large-scale Knowledge Bases. Part II: Schema-agnostic Knowledge Base Querying
Construction and Querying of Large-scale Knowledge Bases Part II: Schema-agnostic Knowledge Base Querying Transformation in Information Search Desktop search Mobile search Which hotel has a roller coaster
More informationABC-CNN: Attention Based CNN for Visual Question Answering
ABC-CNN: Attention Based CNN for Visual Question Answering CIS 601 PRESENTED BY: MAYUR RUMALWALA GUIDED BY: DR. SUNNIE CHUNG AGENDA Ø Introduction Ø Understanding CNN Ø Framework of ABC-CNN Ø Datasets
More informationTransition-based Parsing with Neural Nets
CS11-747 Neural Networks for NLP Transition-based Parsing with Neural Nets Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Two Types of Linguistic Structure Dependency: focus on relations between
More informationAnswering Natural Language Questions via Phrasal Semantic Parsing
Answering Natural Language Questions via Phrasal Semantic Parsing Kun Xu Sheng Zhang Yansong Feng Dongyan Zhao Peking University December 9, 2014 Movie Movie 1 What else movies did the director of the
More informationGhent University-IBCN Participation in TAC-KBP 2015 Cold Start Slot Filling task
Ghent University-IBCN Participation in TAC-KBP 2015 Cold Start Slot Filling task Lucas Sterckx, Thomas Demeester, Johannes Deleu, Chris Develder Ghent University - iminds Gaston Crommenlaan 8 Ghent, Belgium
More informationSeq2SQL: Generating Structured Queries from Natural Language Using Reinforcement Learning
Seq2SQL: Generating Structured Queries from Natural Language Using Reinforcement Learning V. Zhong, C. Xiong, R. Socher Salesforce Research arxiv: 1709.00103 Reviewed by : Bill Zhang University of Virginia
More informationConversational Knowledge Graphs. Larry Heck Microsoft Research
Conversational Knowledge Graphs Larry Heck Microsoft Research Multi-modal systems e.g., Microsoft MiPad, Pocket PC TV Voice Search e.g., Bing on Xbox Task-specific argument extraction (e.g., Nuance, SpeechWorks)
More informationComputational Linguistics: Syntax-Semantics
Computational Linguistics: Syntax-Semantics Raffaella Bernardi University of Trento Contents 1 The Three Tasks Revised................................... 3 2 Lambda terms and CFG...................................
More informationComputational Linguistics: Syntax-Semantics Interface
Computational Linguistics: Syntax-Semantics Interface Raffaella Bernardi KRDB, Free University of Bozen-Bolzano P.zza Domenicani, Room: 2.28, e-mail: bernardi@inf.unibz.it Contents 1 Lambda terms and DCG...................................
More informationQuery Intent Detection using Convolutional Neural Networks
Query Intent Detection using Convolutional Neural Networks Homa B. Hashemi, Amir Asiaee, Reiner Kraft QRUMS workshop - February 22, 2016 Query Intent Detection michelle obama age Query Intent Detection
More informationNatural Language Processing
Natural Language Processing Info 159/259 Lecture 18: Semantics (Oct 25, 2018) David Bamman, UC Berkeley Graph-based parsing For a given sentence S, we want to find the highest-scoring tree among all possible
More informationThe Verb. From Probabilities to Internal Categories. Cem Bozşahin. Cognitive Science Department, The Informatics Institute, ODTÜ
The Verb From Probabilities to Internal Categories Cem Bozşahin bozsahin@metu.edu.tr Cognitive Science Department, The Informatics Institute, ODTÜ November 18, 2016 Joint work with Mark Steedman (with
More informationA General-Purpose Rule Extractor for SCFG-Based Machine Translation
A General-Purpose Rule Extractor for SCFG-Based Machine Translation Greg Hanneman, Michelle Burroughs, and Alon Lavie Language Technologies Institute Carnegie Mellon University Fifth Workshop on Syntax
More informationSemantics as a Foreign Language. Gabriel Stanovsky and Ido Dagan EMNLP 2018
Semantics as a Foreign Language Gabriel Stanovsky and Ido Dagan EMNLP 2018 Semantic Dependency Parsing (SDP) A collection of three semantic formalisms (Oepen et al., 2014;2015) Semantic Dependency Parsing
More informationarxiv: v1 [cs.cl] 31 Oct 2016
Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, Ni Lao arxiv:1611.00020v1 [cs.cl] 31 Oct 2016 Northwestern
More informationOutline. Morning program Preliminaries Semantic matching Learning to rank Entities
112 Outline Morning program Preliminaries Semantic matching Learning to rank Afternoon program Modeling user behavior Generating responses Recommender systems Industry insights Q&A 113 are polysemic Finding
More informationLeveraging Knowledge Graphs for Web-Scale Unsupervised Semantic Parsing. Interspeech 2013
Leveraging Knowledge Graphs for Web-Scale Unsupervised Semantic Parsing LARRY HECK, DILEK HAKKANI-TÜR, GOKHAN TUR Focus of This Paper SLU and Entity Extraction (Slot Filling) Spoken Language Understanding
More informationS-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking Yi Yang * and Ming-Wei Chang # * Georgia Institute of Technology, Atlanta # Microsoft Research, Redmond Traditional
More informationText Mining for Software Engineering
Text Mining for Software Engineering Faculty of Informatics Institute for Program Structures and Data Organization (IPD) Universität Karlsruhe (TH), Germany Department of Computer Science and Software
More informationCombining Neural Networks and Log-linear Models to Improve Relation Extraction
Combining Neural Networks and Log-linear Models to Improve Relation Extraction Thien Huu Nguyen and Ralph Grishman Computer Science Department, New York University {thien,grishman}@cs.nyu.edu Outline Relation
More informationA Hybrid Neural Model for Type Classification of Entity Mentions
A Hybrid Neural Model for Type Classification of Entity Mentions Motivation Types group entities to categories Entity types are important for various NLP tasks Our task: predict an entity mention s type
More informationTopics in Parsing: Context and Markovization; Dependency Parsing. COMP-599 Oct 17, 2016
Topics in Parsing: Context and Markovization; Dependency Parsing COMP-599 Oct 17, 2016 Outline Review Incorporating context Markovization Learning the context Dependency parsing Eisner s algorithm 2 Review
More informationSyntax-semantics interface and the non-trivial computation of meaning
1 Syntax-semantics interface and the non-trivial computation of meaning APA/ASL Group Meeting GVI-2: Lambda Calculi, Type Systems, and Applications to Natural Language APA Eastern Division 108th Annual
More informationDecoders Wilfrid Laurier University
Decoders Wilfrid Laurier University Wilfrid Laurier University January 27, 2012 A decoder usually converts one type of input pattern into a corresponding output pattern. A decoder usually converts one
More informationSolving Natural Language Math Problems
Solving Natural Language Math Problems Takuya Matsuzaki (Nagoya University) Noriko H. Arai (National Institute of Informatics) Solving NL Math why? It is the first and the last goal of symbolic approach
More informationType raising, continuations, and classical logic
Type raising, continuations, and classical logic Philippe de Groote Inria-Lorraine Abstract. There is a striking analogy between type raising, as introduced by Montague (973), and the notion of continuation
More informationQuerying unnormalized and Inc mpl te Knowledge Bases
Querying unnormalized and Inc mpl te Knowledge Bases Percy Liang Stanford University Automated Knowledge Base Construction (AKBC) 2016 June 17, 2016 Computing the answer What is the second most populous
More informationHarvard School of Engineering and Applied Sciences CS 152: Programming Languages. Lambda calculus
Harvard School of Engineering and Applied Sciences CS 152: Programming Languages Tuesday, February 19, 2013 The lambda calculus (or λ-calculus) was introduced by Alonzo Church and Stephen Cole Kleene in
More informationarxiv: v2 [cs.ai] 18 Sep 2013
Lambda Dependency-Based Compositional Semantics Percy Liang September 19, 2013 arxiv:1309.4408v2 [cs.ai] 18 Sep 2013 Abstract This short note presents a new formal language, lambda dependency-based compositional
More informationProseminar on Semantic Theory Fall 2013 Ling 720 An Algebraic Perspective on the Syntax of First Order Logic (Without Quantification) 1
An Algebraic Perspective on the Syntax of First Order Logic (Without Quantification) 1 1. Statement of the Problem, Outline of the Solution to Come (1) The Key Problem There is much to recommend an algebraic
More informationParsing Chart Extensions 1
Parsing Chart Extensions 1 Chart extensions Dynamic programming methods CKY Earley NLP parsing dynamic programming systems 1 Parsing Chart Extensions 2 Constraint propagation CSP (Quesada) Bidirectional
More informationAnswer Extraction. NLP Systems and Applications Ling573 May 13, 2014
Answer Extraction NLP Systems and Applications Ling573 May 13, 2014 Answer Extraction Goal: Given a passage, find the specific answer in passage Go from ~1000 chars -> short answer span Example: Q: What
More informationDowty Friday, July 22, 11
Dowty 1994 The Role of Negative Polarity and Concord Marking in Natural Language Reasoning SALT IV, Cornell, Ithaca, NY. starts by explaining Sánchez work more lucidly than Sánchez himself presents a simpler
More informationPure (Untyped) λ-calculus. Andrey Kruglyak, 2010
Pure (Untyped) λ-calculus Andrey Kruglyak, 2010 1 Pure (untyped) λ-calculus An example of a simple formal language Invented by Alonzo Church (1936) Used as a core language (a calculus capturing the essential
More informationDependency grammar and dependency parsing
Dependency grammar and dependency parsing Syntactic analysis (5LN455) 2015-12-09 Sara Stymne Department of Linguistics and Philology Based on slides from Marco Kuhlmann Activities - dependency parsing
More informationDependency grammar and dependency parsing
Dependency grammar and dependency parsing Syntactic analysis (5LN455) 2016-12-05 Sara Stymne Department of Linguistics and Philology Based on slides from Marco Kuhlmann Activities - dependency parsing
More informationAutoencoder. Representation learning (related to dictionary learning) Both the input and the output are x
Deep Learning 4 Autoencoder, Attention (spatial transformer), Multi-modal learning, Neural Turing Machine, Memory Networks, Generative Adversarial Net Jian Li IIIS, Tsinghua Autoencoder Autoencoder Unsupervised
More informationDependency grammar and dependency parsing
Dependency grammar and dependency parsing Syntactic analysis (5LN455) 2014-12-10 Sara Stymne Department of Linguistics and Philology Based on slides from Marco Kuhlmann Mid-course evaluation Mostly positive
More informationCKY algorithm / PCFGs
CKY algorithm / PCFGs CS 585, Fall 2018 Introduction to Natural Language Processing http://people.cs.umass.edu/~miyyer/cs585/ Mohit Iyyer College of Information and Computer Sciences University of Massachusetts
More informationHow GPUs Power Comcast's X1 Voice Remote and Smart Video Analytics. Jan Neumann Comcast Labs DC May 10th, 2017
How GPUs Power Comcast's X1 Voice Remote and Smart Video Analytics Jan Neumann Comcast Labs DC May 10th, 2017 Comcast Applied Artificial Intelligence Lab Media & Video Analytics Smart TV Deep Learning
More information27: Hybrid Graphical Models and Neural Networks
10-708: Probabilistic Graphical Models 10-708 Spring 2016 27: Hybrid Graphical Models and Neural Networks Lecturer: Matt Gormley Scribes: Jakob Bauer Otilia Stretcu Rohan Varma 1 Motivation We first look
More informationRobust Discovery of Positive and Negative Rules in Knowledge-Bases
Robust Discovery of Positive and Negative Rules in Knowledge-Bases Paolo Papotti joint work with S. Ortona (Meltwater) and V. Meduri (ASU) http://www.eurecom.fr/en/publication/5321/detail/robust-discovery-of-positive-and-negative-rules-in-knowledge-bases
More informationOpen-domain Factoid Question Answering via Knowledge Graph Search
Open-domain Factoid Question Answering via Knowledge Graph Search Ahmad Aghaebrahimian, Filip Jurčíček Charles University in Prague, Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics
More informationIntroduction to Lambda Calculus. Lecture 7 CS /08/09
Introduction to Lambda Calculus Lecture 7 CS 565 02/08/09 Lambda Calculus So far, we ve explored some simple but non-interesting languages language of arithmetic expressions IMP (arithmetic + while loops)
More informationFast Contextual Preference Scoring of Database Tuples
Fast Contextual Preference Scoring of Database Tuples Kostas Stefanidis Department of Computer Science, University of Ioannina, Greece Joint work with Evaggelia Pitoura http://dmod.cs.uoi.gr 2 Motivation
More informationSemantics and First-Order Predicate Calculus
Semantics and First-Order Predicate Calculus 11-711 Algorithms for NLP 17 November 2016 (With thanks to Noah Smith) Key Challenge of Meaning We actually say very little - much more is left unsaid, because
More informationContext-Free Grammars
Department of Linguistics Ohio State University Syntax 2 (Linguistics 602.02) January 3, 2012 (CFGs) A CFG is an ordered quadruple T, N, D, P where a. T is a finite set called the terminals; b. N is a
More informationLearning Compositional Semantics for Open Domain Semantic Parsing
for Open Domain Semantic Parsing Institute for Logic, Language and Computation University of Amsterdam Groningen October 31, 2012 Outline Groningen Groningen Does Google understand what I mean? Groningen
More informationLearning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li
Learning to Match Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li 1. Introduction The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation,
More informationOpen-Domain Question Answering Using a Knowledge Graph and Web Corpus
Open-Domain Question Answering Using a Knowledge Graph and Web Corpus Uma Sawant, Soumen Chakrabarti and Ganesh Ramakrishnan IIT Bombay In Web search, entity-seeking queries often trigger a special Question
More informationPromoting Ranking Diversity for Biomedical Information Retrieval based on LDA
Promoting Ranking Diversity for Biomedical Information Retrieval based on LDA Yan Chen, Xiaoshi Yin, Zhoujun Li, Xiaohua Hu and Jimmy Huang State Key Laboratory of Software Development Environment, Beihang
More informationCMSC 330: Organization of Programming Languages. Lambda Calculus
CMSC 330: Organization of Programming Languages Lambda Calculus 1 Turing Completeness Turing machines are the most powerful description of computation possible They define the Turing-computable functions
More informationThat Doesn't Make Sense! A Case Study in Actively Annotating Model Explanations
That Doesn't Make Sense! A Case Study in Actively Annotating Model Explanations Sameer Singh University of California, Irvine NIPS 2017 Workshop on Learning with Limited Labeled Data Relation Extraction
More information564 Lecture 21 Nov. 4, 1999
564 Lecture 21 Nov. 4, 1999 1 Homework notes: 1. What we're doing when we calculate value of a tree like one "Dino is brown dinosaur that licked Fred", is we're calculating its truth-conditions, i.e. we're
More informationLearning Semantic Entity Representations with Knowledge Graph and Deep Neural Networks and its Application to Named Entity Disambiguation
Learning Semantic Entity Representations with Knowledge Graph and Deep Neural Networks and its Application to Named Entity Disambiguation Hongzhao Huang 1 and Larry Heck 2 Computer Science Department,
More informationINF4820, Algorithms for AI and NLP: Hierarchical Clustering
INF4820, Algorithms for AI and NLP: Hierarchical Clustering Erik Velldal University of Oslo Sept. 25, 2012 Agenda Topics we covered last week Evaluating classifiers Accuracy, precision, recall and F-score
More informationA Deep Relevance Matching Model for Ad-hoc Retrieval
A Deep Relevance Matching Model for Ad-hoc Retrieval Jiafeng Guo 1, Yixing Fan 1, Qingyao Ai 2, W. Bruce Croft 2 1 CAS Key Lab of Web Data Science and Technology, Institute of Computing Technology, Chinese
More informationArchitectural Design. Architectural Design. Software Architecture. Architectural Models
Architectural Design Architectural Design Chapter 6 Architectural Design: -the design the desig process for identifying: - the subsystems making up a system and - the relationships between the subsystems
More informationInformationslogistik Unit 5: Data Integrity & Functional Dependency
Informationslogistik Unit 5: Data Integrity & Functional Dependency 27. III. 2012 Outline 1 Reminder: The Relational Algebra 2 The Relational Calculus 3 Data Integrity Keeping data consistent 4 Functional
More informationLING 130: Quantified Noun Phrases
LING 130: Quantified Noun Phrases James Pustejovsky March 15, 2010 1 Syntax for Typed λ-calculus We will now present a language which uses specific types of entities, where the entities are combined with
More informationFigure : Example Precedence Graph
CS787: Advanced Algorithms Topic: Scheduling with Precedence Constraints Presenter(s): James Jolly, Pratima Kolan 17.5.1 Motivation 17.5.1.1 Objective Consider the problem of scheduling a collection of
More informationPure Lambda Calculus. Lecture 17
Pure Lambda Calculus Lecture 17 Lambda Calculus Lambda Calculus (λ-calculus) is a functional notation introduced by Alonzo Church in the early 1930s to formalize the notion of computability. Pure λ-calculus
More informationTowards Translating Natural Language Sentences into ASP
Towards Translating Natural Language Sentences into ASP Stefania Costantini and Alessio Paolucci Dip. di Informatica, Università di L Aquila, Coppito 67100, L Aquila, Italy stefania.costantini@univaq.it,
More informationPropositional Calculus: Boolean Functions and Expressions. CS 270: Mathematical Foundations of Computer Science Jeremy Johnson
Propositional Calculus: Boolean Functions and Expressions CS 270: Mathematical Foundations of Computer Science Jeremy Johnson Propositional Calculus Objective: To provide students with the concepts and
More informationDiscriminative classifiers for image recognition
Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study
More informationCentralities (4) By: Ralucca Gera, NPS. Excellence Through Knowledge
Centralities (4) By: Ralucca Gera, NPS Excellence Through Knowledge Some slide from last week that we didn t talk about in class: 2 PageRank algorithm Eigenvector centrality: i s Rank score is the sum
More informationMaximum Entropy based Natural Language Interface for Relational Database
International Journal of Engineering Research and Technology. ISSN 0974-3154 Volume 7, Number 1 (2014), pp. 69-77 International Research Publication House http://www.irphouse.com Maximum Entropy based
More informationOutline. Part I. Introduction Part II. ML for DI. Part III. DI for ML Part IV. Conclusions and research direction
Outline Part I. Introduction Part II. ML for DI ML for entity linkage ML for data extraction ML for data fusion ML for schema alignment Part III. DI for ML Part IV. Conclusions and research direction Data
More information6.1 Basics of functional type theory, semantics of serial verbs via function composition.
PART 6. SEMANTIC PARSING OF THE VERB CLUSTER IN DUTCH AND GERMAN 6.1 Basics of functional type theory, semantics of serial verbs via function composition. Basics of functional type theory (ignoring intensionality)
More informationRecursive Definitions, Fixed Points and the Combinator
Recursive Definitions, Fixed Points and the Combinator Dr. Greg Lavender Department of Computer Sciences University of Texas at Austin Recursive Self-Reference Recursive self-reference occurs regularly
More informationCS224n: Natural Language Processing with Deep Learning 1 Lecture Notes: Part IV Dependency Parsing 2 Winter 2019
CS224n: Natural Language Processing with Deep Learning 1 Lecture Notes: Part IV Dependency Parsing 2 Winter 2019 1 Course Instructors: Christopher Manning, Richard Socher 2 Authors: Lisa Wang, Juhi Naik,
More informationan incremental algorithm for transition-based ccg parsing
an incremental algorithm for transition-based ccg parsing B. R. Ambati, T. Deoskar, M. Johnson and M. Steedman Miyazawa Akira January 22, 2016 The Graduate University For Advanced Studies / National Institute
More information(Multinomial) Logistic Regression + Feature Engineering
-6 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University (Multinomial) Logistic Regression + Feature Engineering Matt Gormley Lecture 9 Feb.
More informationCS 4110 Programming Languages & Logics. Lecture 17 Programming in the λ-calculus
CS 4110 Programming Languages & Logics Lecture 17 Programming in the λ-calculus 10 October 2014 Announcements 2 Foster Office Hours 11-12 Enjoy fall break! Review: Church Booleans 3 We can encode TRUE,
More informationMonday 15 June 2015 Afternoon
Oxford Cambridge and RSA Monday 15 June 2015 Afternoon GCSE MEDIA STUDIES B322/01 Textual Analysis and Media Studies Topic (Moving Image) *4845802352* Candidates answer on the Question Paper. OCR supplied
More informationNatural Language Processing (CSE 517): Compositional Semantics
Natural Language Processing (CSE 517): Compositional Semantics Noah Smith c 2018 University of Washington nasmith@cs.washington.edu May 18, 2018 1 / 54 Bridging the Gap between Language and the World In
More informationIntroduction to Semantics. Expanding Our Formalism, Part 2 1
Expanding Our Formalism, Part 2 1 1. Lambda Notation for Defining Functions As you may have guessed by this point, most expressions of natural language will have some kind of function as their extension
More informationThe Neo4j Developer Manual v3.0
The Neo4j Developer Manual v3.0 Table of Contents Introduction.............................................................................. 1 1. Neo4j highlights......................................................................
More informationStructural and Syntactic Pattern Recognition
Structural and Syntactic Pattern Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Fall 2017 CS 551, Fall 2017 c 2017, Selim Aksoy (Bilkent
More informationGuiding Semi-Supervision with Constraint-Driven Learning
Guiding Semi-Supervision with Constraint-Driven Learning Ming-Wei Chang 1 Lev Ratinov 2 Dan Roth 3 1 Department of Computer Science University of Illinois at Urbana-Champaign Paper presentation by: Drew
More informationDomain-Specific. Languages. Martin Fowler. AAddison-Wesley. Sydney Tokyo. With Rebecca Parsons
Domain-Specific Languages Martin Fowler With Rebecca Parsons AAddison-Wesley Upper Saddle River, NJ Boston Indianapolis San Francisco New York Toronto Montreal London Munich Paris Madrid Sydney Tokyo Singapore
More informationCMSC 330: Organization of Programming Languages
CMSC 330: Organization of Programming Languages Lambda Calculus CMSC 330 Summer 2017 1 100 years ago Albert Einstein proposed special theory of relativity in 1905 In the paper On the Electrodynamics of
More informationExam I Computer Science 420 Dr. St. John Lehman College City University of New York 12 March 2002
Exam I Computer Science 420 Dr. St. John Lehman College City University of New York 12 March 2002 NAME (Printed) NAME (Signed) E-mail Exam Rules Show all your work. Your grade will be based on the work
More informationAn Inverse Lambda Calculus Algorithm. For Natural Language Processing. Marcos Alvarez Gonzalez
An Inverse Lambda Calculus Algorithm For Natural Language Processing by Marcos Alvarez Gonzalez A Thesis Presented In Partial Fulfillment of the Requirements for the Degree Master of Science Approved November
More information16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning. Spring 2018 Lecture 14. Image to Text
16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning Spring 2018 Lecture 14. Image to Text Input Output Classification tasks 4/1/18 CMU 16-785: Integrated Intelligence in Robotics
More informationCSCI 585 Database Systems Prof. Dennis McLeod. Sample Midterm Exam
CSCI 585 Database Systems Prof. Dennis McLeod Sample Midterm Exam The purpose of this sample exam is to show the style of questions the exams will contain. It is not an indication of scope of topic coverage
More informationCMSC 330: Organization of Programming Languages. Lambda Calculus
CMSC 330: Organization of Programming Languages Lambda Calculus 1 100 years ago Albert Einstein proposed special theory of relativity in 1905 In the paper On the Electrodynamics of Moving Bodies 2 Prioritätsstreit,
More informationNon-deterministic Finite Automata (NFA)
Non-deterministic Finite Automata (NFA) CAN have transitions on the same input to different states Can include a ε or λ transition (i.e. move to new state without reading input) Often easier to design
More informationNatural Language Processing
Natural Language Processing Machine Learning Potsdam, 26 April 2012 Saeedeh Momtazi Information Systems Group Introduction 2 Machine Learning Field of study that gives computers the ability to learn without
More informationClass Intro & Compositional Semantics & Others
LING 147. Semantics of Questions Week 1 Yimei Xiang September 1, 2016 1 Class intro Class Intro & Compositional Semantics & Others What does a declarative denote? A declarative denotes a proposition. Its
More informationIntroduction to Lambda Calculus. Lecture 5 CS 565 1/24/08
Introduction to Lambda Calculus Lecture 5 CS 565 1/24/08 Lambda Calculus So far, we ve explored some simple but non-interesting languages language of arithmetic expressions IMP (arithmetic + while loops)
More informationXML RETRIEVAL. Introduction to Information Retrieval CS 150 Donald J. Patterson
Introduction to Information Retrieval CS 150 Donald J. Patterson Content adapted from Manning, Raghavan, and Schütze http://www.informationretrieval.org OVERVIEW Introduction Basic XML Concepts Challenges
More informationThe answer (circa 2001)
Question ing Question Answering Overview and task definition History Open-domain question ing Basic system architecture Predictive indexing methods Pattern-matching methods Advanced techniques? What was
More informationAll groups final presentation/poster and write-up
Logistics Non-NIST groups project proposals Guidelines posted Write-up and slides due this Friday Coming Monday, each Non-NIST group will give project pitch (5 min) based on the slides Everyone in class
More informationParsing with Dynamic Programming
CS11-747 Neural Networks for NLP Parsing with Dynamic Programming Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Two Types of Linguistic Structure Dependency: focus on relations between words
More information