Scalable Semantic Parsing with Partial Ontologies ACL 2015
|
|
- Georgiana Small
- 5 years ago
- Views:
Transcription
1 Scalable Semantic Parsing with Partial Ontologies Eunsol Choi Tom Kwiatkowski Luke Zettlemoyer ACL
2 Semantic Parsing: Long-term Goal Build meaning representations for open-domain texts How many people live in Seattle? Semantic Parser SELECT Population FROM CityData where City=="Seattle ; Executor 620,778 (Kwiatkowski et.al, 13, Liang et.al. 11, Cai & Yates 2013, Berant et.al. 13,14, Reddy et. a. 14) 2
3 Semantic Parsing: Large Domain is a large, community authored knowledge base with: 40 Million Entities 2 Billion Facts 20,000 Relations 10,000 Types 100 Domains 3
4 Current semantic parsers can parse How many people live in Seattle? Which college did Obama go to? What party did Clay establish? 4
5 Current semantic parsers can parse cannot parse How many people live in Seattle? Which college did Obama go to? How many people live in Anyang? Which college did Eunsol go to? What party did Clay establish? Who are Russian short story writers in 19th century? What is a popular seaside resort city in Italy? 5
6 Remaining Challenges Fact Incompleteness How many people live in Anyang? Which college did Eunsol go to? Schema Incompleteness Who are Russian short story writers in 19th century? What is a popular seaside resort city in Italy? 6
7 Remaining Challenges Fact Incompleteness How many people live in Anyang? Which college did Eunsol go to? Schema Incompleteness Who are Russian short story writers in 19th century? What is a popular seaside resort city in Italy? 7
8 Remaining Challenges: Fact Incompleteness 620,778 Seattle Population State How many people live in Anyang? Which college did Eunsol go to? Washington Anyang Unable to handle sentences Population with facts not in Freebase? 8
9 Remaining Challenges: Fact Incompleteness 620,778 Seattle Population State How many people live in Anyang? Which college did Eunsol go to? Washington Anyang 70% of people in FB have no birth place (West 14) Population 66% of facts missing in pilot study for our dataset? 9
10 Remaining Challenges Fact Incompleteness How many people live in Anyang Which college did Eunsol Schema Incompleteness Who are Russian short story writers in 19th century? What is a popular seaside resort city in Italy? 10
11 Remaining Challenges: Schema Incompleteness Who are Russian short story writers in 19th century? What is popular seaside resort city in Italy? Unable to handle concepts outside existing schema 11
12 Remaining Challenges: Schema Incompleteness Who are Russian short story writers in 19th century? What is popular seaside resort city in Italy? In a pilot study on our dataset: Unable to handle concepts 27.2% of sentences describe outside existing schema concepts not in Freebase 12
13 Previous Approach? Existing data is filtered to ensure completeness: FB917 dataset is created from Freebase (Cai and Yates 13) 93% of originally gathered questions cannot be answered with FB (WebQuestions, Berant 13) 13
14 Remaining Challenges Fact Incompleteness How New many learning people approach live in Anyang? with broad coverage lexical statistics Which college did Eunsol go to? Schema Incompleteness Who are Russian short story writers in 19th century? Semantic parser with partial groundings What is a popular seaside resort city in Italy? 14
15 This Work Build meaning representations with both Freebase concepts and open concepts British playwright, novelist and short story writer Semantic Parser 15
16 Parsing with Incompleteness 1. Open Information Extraction (Banko et al., 07; Fader et al., 11) 2. Matrix Factorization (Riedel, 13;Krishnamurthy, 15) 3. Web Search Queries (Joshi, 14)
17 Outline 1. Task and Applications 2. Data 3. Semantic Parser with Partial Ontology 4. Learning 5. Evaluation
18 Task Build a meaning representation with Freebase concepts and concepts outside Freebase British playwright, novelist and short story writer Semantic Parser
19 Focus: Noun Phrases Interesting noun-noun modifier, implicit relations. Itself is a referring expression, resembling queries. 19
20 Focus: Noun Phrases Interesting noun-noun modifier, implicit relations. Useful for information extraction, when paired with an entity. 20
21 Applications Input: Referring Expression Resolution (QA) Noun Phrase Entity Attribute Extraction (IE) (Entity, Noun Phrase) British playwright, novelist and short story writer Somerset Maugham, British playwright, novelist and short story writer Output: Sommerset Maugham (S. Maugham, Nationality, U.K) (S. Maugham, Profession, Novelist) (S. Maugham, Profession, Playwright)
22 Overview: Approach British playwright, novelist and short story writer Semantic Parser 22
23 Referring Expression Resolution (QA) British playwright, novelist and short story writer Semantic Parser Sommerset Maugham 23
24 Referring Expression Resolution (QA) Entity Attribute Extraction (IE) British playwright, novelist and short story writer Semantic Parser Sommerset Maugham (x, Nationality, U.K) (x, Profession, Novelist) (x, Profession, Playwright) 24
25 Referring Expression Resolution (QA) Entity Attribute Extraction (IE) Somerset Maugham, British playwright, novelist and short story writer Semantic Parser Sommerset Maugham (S.Maugham, Nationality, U.K) (S.Maugham, Profession, Novelist) (S.Maugham, Profession, Playwright) 25
26 Outline 1. Task and Applications 2. Data 3. Semantic Parser with Partial Ontology 4. Learning 5. Evaluation
27 Wikipedia Category 27
28 Wikipedia Category 28
29 Wikipedia Category Film directors from New York 29
30 Wikipedia Category Film directors from New York 30
31 Wikipedia Category On average, 15% entity overlap with Freebase Exciting opportunity for information extraction Challenge for existing learning techniques Film directors from New York 31
32 Wikipedia Category: Data statistics Entire Set Number of Category 365 K Number of words per category 4.1 Number of entity-category pair 7 million 32
33 Appositives Relation between a named entity and a nominal. Laurie Hays, a executive editor at Bloomberg News, is leaving the company. Laurie Hays, a executive editor at Bloomberg News 33
34 Appositives Extracted from open texts such as news articles Malta, an EU outpost in the Mediterranean, decided today Richard Nixon, a former president of the United States Maputo, the relaxed seaside capital of Mozambique, 34
35 Appositives Extracted from open texts such as news articles Malta, an EU outpost in the Mediterranean, decided today Richard Nixon, a former president of the United States Maputo, the relaxed seaside capital of Mozambique, 35
36 Appositives: Data statistics Entire Set Number of apposition 67 K vocab 25 K Number of words per apposition
37 Outline 1. Task and Applications 2. Data 3. Semantic Parser with Partial Ontology 4. Learning 5. Evaluation
38 Two Stage Semantic Parsing (EMNLP 13) British playwright, novelist and short story writer Domain Independent Parse Ontology Match 38
39 Two Stage Semantic Parsing (EMNLP 13) British playwright, novelist and short story writer Domain Independent Parse Ontology Match 39
40 Two Stage Semantic Parsing (EMNLP 13) British playwright, novelist and short story writer Domain Independent Parse Ontology Match 40
41 Two Stage Semantic Parsing with Partial Grounding British playwright, novelist and short story writer Domain Independent Parse Ontology Match 41
42 Partial Grounding: Open Schema Explicitly model concepts not in Knowledge base as OpenRel and OpenType Plants described in 1891 Lower_classification(plant, x) OpenRel_described_in(x, 1891) Former municipalities in Brandenburg OpenType_Former(x) OpenRel(x, Municipality) Located_In(x, Brandenburg) 42
43 Partial Grounding: Open Schema Explicitly model concepts not in Knowledge base Benefits of as open OpenRel schema: and OpenType Plants described in 1891 Help learn String-Freebase concepts (plant, lower_classification, x) Allow partial execution (x, OpenRel(described_in), 1891) Capture useful information, although not Former municipalities in Brandenburg grounded (x, Type, OpenType_Former) (x, OpenRel, Municipality) (x, Located_In, Brandenburg) 43
44 Two Stage Semantic Parsing Domain Independent Parse with Partial Grounding Ontology Match Structure Match Constant Matches for. OPEN Constant Matches OpenType OpenRel Municipality Location.ContainedBy Brandenburg 44
45 Outline 1. Task and Applications 2. Data 3. Semantic Parser with Partial Ontology 4. Learning 5. Evaluation
46 Previous Work: Direct Supervision How many people live in Seattle? How many people live in Seattle? Semantic Parser SELECT Population FROM CityData where City=="Seattle ; Latent Executor 620, ,778 46
47 Supervision from Unfiltered Data 47
48 Supervision from Unfiltered Data Social democratic parties in Greece Semantic Parser Executor {Agreement for the New Greece, Agricultural and Labour Party, Free Citizens, Democratic Social Movement } 4 entities 48
49 Supervision from Unfiltered Data Social democratic parties in Greece Semantic Parser Missing X Political_Party.Ideology facts make direct Social supervision Democratic difficult. X Political_Party.Country Greece Executor {Agreement for the New Greece, Agricultural and Labour Party, Free Citizens, Democratic Social Movement } 4 entities 49
50 Supervision from Unfiltered Data Social democratic parties in Greece Semantic Parser 50
51 Supervision from Unfiltered Data Social democratic parties in Greece Semantic Parser Executor Gold mapping is expensive to gather large scale. {Agreement for the New Greece, Agricultural and Labour Party, Free Citizens, Democratic Social Movement } 4 entities 51
52 Learning with Fact Incompleteness 1. Two-Stage Learning 2. Two kinds of data i. Small Annotated Dataset ii. Broad Coverage Lexical Statistics 52
53 Two-Stage Learning Social democratic parties in Greece CCG Domain Independent Parse Ontology Matcher ONT 53
54 Two-Stage Learning Social democratic parties in Greece CCG Domain Independent Parse Small training set with logical form British playwright, novelist and short story writer, ( ) x
55 Two-Stage Learning Social democratic parties in Greece CCG Domain Independent Parse Derivations are scored using a linear model Highest scoring logical form( second stage ) is passed to the 55
56 Two-Stage Learning ONT Ontology Matcher is a large, community authored knowledge base with: 20,000 Relations 10,000 Types 100 Domains 56
57 Broad Coverage Lexical Statistics : Wikipedia Category dataset 85 K vocabulary 365 K category 2.5 M entity 7 M category-entity pair 57
58 Mapping words to Freebase Attribute Pixar Feature Films Animation Films from Pixar Pixar songs 58
59 Mapping words to Freebase Attribute Pixar Feature Films Animation Films from Pixar Pixar songs Ratatouille Wall-E Finding Nemo Toy Story Monster Inc. Just keep swimming 59
60 Mapping words to Freebase Attribute Pixar Feature Films Animation Films from Pixar Pixar songs Ratatouille Wall-E Finding Nemo Toy Story Monster Inc. Just keep swimming (film.production_companies, Pixar) (film.film.produced_by, John Lasseter) (film.film.directed_by, John Lasseter) (film.film.film_festivals, 2011 Anima Mundi ) (film.film.starring.actor, Bob Peterson) 60
61 Mapping words to Freebase Attribute Pixar Feature Films Animation Films from Pixar Pixar songs Ratatouille Wall-E Finding Nemo Toy Story Monster Inc. Just keep swimming Large amount of information (film.production_companies, Pixar) for String - Entity - Freebase attribute alignment (film.film.produced_by, John Lasseter) (film.film.directed_by, John Lasseter) (film.film.film_festivals, 2011 Anima Mundi ) (film.film.starring.actor, Bob Peterson) 61
62 Mapping words to Freebase Attribute Pixar Feature Films Animation Films from Pixar Pixar songs Pointwise Mutual Information(PMI)= Ratatouille Wall-E Finding Nemo Toy Story Monster Inc. Just keep swimming P(String, Freebase Attribute) log( ) (film.production_companies, /m/0kk9v) (film.film.produced_by, John Lasseter) (film.film.directed_by, P(Freebase John Attribute) Lasseter) (film.film.film_festivals, m.0h15pp1 ) P(String) as a feature 62
63 Features Domain Independent Parse Parse Features: CCG Lexicon, Capitalization String -> Freebase features Wikipedia Lexical Statistics Ontology Match Surface Lexical Features String Match, Stem Match KnowledgeBase Features 63
64 Outline 1. Task and Applications 2. Data 3. Semantic Parser with Partial Ontology 4. Learning 5. Evaluation
65 Experimental Setup Training Set: 500 annotated Wikipedia Category Test Set (Manual Evaluation): 500 unseen Wikipedia Category 300 appositives Baseline: SVM Classifier trained with annotated logical forms 65
66 Applications Input: Referring Expression Resolution (QA) Noun Phrase Entity Attribute Extraction (IE) (Entity, Noun Phrase) British playwright, novelist and short story writer Somerset Maugham, British playwright, novelist and short story writer Output: Entity attributes for Freebase S. Maugham Nationality U.K S. Maugham Profession Novelist Sommerset Maugham S. Maugham Profession Playwright
67 Evaluation Metric: Referring Expression Resolution Alternative Rock Groups from Nevada Gold music group(x) music.artist.origin(x, NEVADA) music.genre.artist(alternative rock, x) X X Output music.artist.origin(x, NEVADA) music.genre.artist(hard rock, x) X Precision: 0.5 Recall: 0.3 F1:0.375 Exact Match: False 67
68 Referring Expression Resolution: (5 fold cross validation on Training Set) 40% 32% % % % 6.8 0% Exact Match F1 68
69 Referring Expression Resolution: (5 fold cross validation on Training Set) 40% 32% 24% % 8% % Exact Match F1 69
70 Referring Expression Resolution: (5 fold cross validation on Training Set) 40% 32% 24% % 8% % Exact Match F1 70
71 Referring Expression Resolution: (5 fold cross validation on Training Set) 40% Baseline Our System Without OpenSchema Without Lexical Statistics KCAZ13 32% 24% % 8% 0% Exact Match 1.4 F
72 Applications Input: Referring Expression Resolution (QA) Noun Phrase Entity Attribute Extraction (IE) (Entity, Noun Phrase) British playwright, novelist and short story writer Somerset Maugham, British playwright, novelist and short story writer Output: Entity attributes for Freebase (S. Maugham, Nationality, U.K) (S. Maugham, Profession, Novelist) (S. Maugham, Profession, Playwright) Sommerset Maugham
73 Entity Attribute Extraction: (5 fold cross validation on Training Set) Baseline Our System Precision Recall F1 73
74 Entity Attribute Extraction: Test Result Baseline Our System Wikipedia Appositive 74
75 Error analysis 10% : named entity retrieving failure 10% : spurious lexical match 10% : looking at different domain e.g: stage actor to film.actor 15% : wrong underspecified logical form 30% : mapping to superset or subset e.g: novel to book 75
76 Entity Attribute Extraction: Test Result % % 61.9% % 0 Baseline Our System Baseline Our System Wikipedia Appositive 76
77 Entity Attribute Extraction: Test Result % % 61.9% 7 million category-entity pairs, Given 66% missing facts, 12 million new facts! % 0 Baseline Our System Baseline Our System Wikipedia Appositive 77
78 Contributions Introduce large-scale semantic parsing datasets Partial grounding to large knowledge base Learn from two kinds of supervision: large-scale co-occurence statistics and small labeled tuning set 78
79 Future work Barack Hussein Obama is the 44th and current President of the United States, the first African American to hold the office. More compositional and complicated structures: orders, comparison, min, max, range Extending to declarative sentences 79
80 Questions? 80
81 The Number of Extracted Facts Baseline Our System Wikipedia (Dev) Wikipedia (Test) Appositive 81
82 Referring Expression Resolution: Test Set IE Baseline Our System 50 Exact Match (%) Wikipedia 0 Appositive
Projektseminar: Sentimentanalyse Dozenten: Michael Wiegand und Marc Schulder
Projektseminar: Sentimentanalyse Dozenten: Michael Wiegand und Marc Schulder Präsentation des Papers ICWSM A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews
More informationSentiment Aggregation using ConceptNet Ontology
Sentiment Aggregation using ConceptNet Ontology Subhabrata Mukherjee Sachindra Joshi IBM Research - India 7th International Joint Conference on Natural Language Processing (IJCNLP 2013), Nagoya, Japan
More informationMUSI-6201 Computational Music Analysis
MUSI-6201 Computational Music Analysis Part 9.1: Genre Classification alexander lerch November 4, 2015 temporal analysis overview text book Chapter 8: Musical Genre, Similarity, and Mood (pp. 151 155)
More informationMusic Genre Classification
Music Genre Classification chunya25 Fall 2017 1 Introduction A genre is defined as a category of artistic composition, characterized by similarities in form, style, or subject matter. [1] Some researchers
More informationSarcasm Detection in Text: Design Document
CSC 59866 Senior Design Project Specification Professor Jie Wei Wednesday, November 23, 2016 Sarcasm Detection in Text: Design Document Jesse Feinman, James Kasakyan, Jeff Stolzenberg 1 Table of contents
More informationIdentifying functions of citations with CiTalO
Identifying functions of citations with CiTalO Angelo Di Iorio 1, Andrea Giovanni Nuzzolese 1,2, and Silvio Peroni 1,2 1 Department of Computer Science and Engineering, University of Bologna (Italy) 2
More informationNatural Language Processing
atural Language Processg Info 159/259 Lecture 19: Semantic parsg (Oct. 31, 2017) David Bamman, UC Berkeley Announcements 259 fal project presentations: 3:30-5pm Tuesday, Dec. 5 (RRR week), 202 South Hall
More informationLarge scale Visual Sentiment Ontology and Detectors Using Adjective Noun Pairs
Large scale Visual Sentiment Ontology and Detectors Using Adjective Noun Pairs Damian Borth 1,2, Rongrong Ji 1, Tao Chen 1, Thomas Breuel 2, Shih-Fu Chang 1 1 Columbia University, New York, USA 2 University
More informationImproving MeSH Classification of Biomedical Articles using Citation Contexts
Improving MeSH Classification of Biomedical Articles using Citation Contexts Bader Aljaber a, David Martinez a,b,, Nicola Stokes c, James Bailey a,b a Department of Computer Science and Software Engineering,
More informationEnabling editors through machine learning
Meta Follow Meta is an AI company that provides academics & innovation-driven companies with powerful views of t Dec 9, 2016 9 min read Enabling editors through machine learning Examining the data science
More informationSemantic Role Labeling of Emotions in Tweets. Saif Mohammad, Xiaodan Zhu, and Joel Martin! National Research Council Canada!
Semantic Role Labeling of Emotions in Tweets Saif Mohammad, Xiaodan Zhu, and Joel Martin! National Research Council Canada! 1 Early Project Specifications Emotion analysis of tweets! Who is feeling?! What
More informationWHAT MAKES FOR A HIT POP SONG? WHAT MAKES FOR A POP SONG?
WHAT MAKES FOR A HIT POP SONG? WHAT MAKES FOR A POP SONG? NICHOLAS BORG AND GEORGE HOKKANEN Abstract. The possibility of a hit song prediction algorithm is both academically interesting and industry motivated.
More informationImproving Frame Based Automatic Laughter Detection
Improving Frame Based Automatic Laughter Detection Mary Knox EE225D Class Project knoxm@eecs.berkeley.edu December 13, 2007 Abstract Laughter recognition is an underexplored area of research. My goal for
More informationUWaterloo at SemEval-2017 Task 7: Locating the Pun Using Syntactic Characteristics and Corpus-based Metrics
UWaterloo at SemEval-2017 Task 7: Locating the Pun Using Syntactic Characteristics and Corpus-based Metrics Olga Vechtomova University of Waterloo Waterloo, ON, Canada ovechtom@uwaterloo.ca Abstract The
More informationSegment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing Hamid Izadinia, Fereshteh Sadeghi, Santosh K. Divvala, Hannaneh Hajishirzi, Yejin Choi, Ali Farhadi Presentated by Edward
More informationMidiFind: Fast and Effec/ve Similarity Searching in Large MIDI Databases
1 MidiFind: Fast and Effec/ve Similarity Searching in Large MIDI Databases Gus Xia Tongbo Huang Yifei Ma Roger B. Dannenberg Christos Faloutsos Schools of Computer Science Carnegie Mellon University 2
More informationMusic Radar: A Web-based Query by Humming System
Music Radar: A Web-based Query by Humming System Lianjie Cao, Peng Hao, Chunmeng Zhou Computer Science Department, Purdue University, 305 N. University Street West Lafayette, IN 47907-2107 {cao62, pengh,
More informationWhat s New in the 17th Edition
What s in the 17th Edition The following is a partial list of the more significant changes, clarifications, updates, and additions to The Chicago Manual of Style for the 17th edition. Part I: The Publishing
More informationChapter 1 Midterm Review
Name: Class: Date: Chapter 1 Midterm Review Multiple Choice Identify the choice that best completes the statement or answers the question. 1. A survey typically records many variables of interest to the
More informationDetecting Musical Key with Supervised Learning
Detecting Musical Key with Supervised Learning Robert Mahieu Department of Electrical Engineering Stanford University rmahieu@stanford.edu Abstract This paper proposes and tests performance of two different
More informationSinger Traits Identification using Deep Neural Network
Singer Traits Identification using Deep Neural Network Zhengshan Shi Center for Computer Research in Music and Acoustics Stanford University kittyshi@stanford.edu Abstract The author investigates automatic
More informationThe Visual Denotations of Sentences. Julia Hockenmaier with Peter Young and Micah Hodosh University of Illinois
The Visual Denotations of Sentences Julia Hockenmaier with Peter Young and Micah Hodosh juliahmr@illinois.edu University of Illinois Sentence-Based Image Description and Search Hodosh, Young, Hockenmaier,
More informationThe ACL Anthology Network Corpus. University of Michigan
The ACL Anthology Corpus Dragomir R. Radev 1,2, Pradeep Muthukrishnan 1, Vahed Qazvinian 1 1 Department of Electrical Engineering and Computer Science 2 School of Information University of Michigan {radev,mpradeep,vahed}@umich.edu
More informationDigital Text, Meaning and the World
Digital Text, Meaning and the World Preliminary considerations for a Knowledgebase of Oriental Studies Christian Wittern Kyoto University Institute for Research in Humanities Objectives Develop a model
More informationAbsolute Relevance? Ranking in the Scholarly Domain. Tamar Sadeh, PhD CNI, Baltimore, MD April 2012
Absolute Relevance? Ranking in the Scholarly Domain Tamar Sadeh, PhD CNI, Baltimore, MD April 2012 Copyright Statement All of the information and material inclusive of text, images, logos, product names
More informationA repetition-based framework for lyric alignment in popular songs
A repetition-based framework for lyric alignment in popular songs ABSTRACT LUONG Minh Thang and KAN Min Yen Department of Computer Science, School of Computing, National University of Singapore We examine
More informationLyric-Based Music Mood Recognition
Lyric-Based Music Mood Recognition Emil Ian V. Ascalon, Rafael Cabredo De La Salle University Manila, Philippines emil.ascalon@yahoo.com, rafael.cabredo@dlsu.edu.ph Abstract: In psychology, emotion is
More informationModelling Intellectual Processes: The FRBR - CRM Harmonization. Authors: Martin Doerr and Patrick LeBoeuf
The FRBR - CRM Harmonization Authors: Martin Doerr and Patrick LeBoeuf 1. Introduction Semantic interoperability of Digital Libraries, Library- and Collection Management Systems requires compatibility
More informationThe Mediterranean TV Channel. Project presentation
The Mediterranean TV Channel Project presentation Key figures for the Euro-Mediterranean area 43 countries Member States of the European Union Mediterranean coastal States A population of about 700 million
More informationNeural Network Predicating Movie Box Office Performance
Neural Network Predicating Movie Box Office Performance Alex Larson ECE 539 Fall 2013 Abstract The movie industry is a large part of modern day culture. With the rise of websites like Netflix, where people
More informationCombination of Audio & Lyrics Features for Genre Classication in Digital Audio Collections
1/23 Combination of Audio & Lyrics Features for Genre Classication in Digital Audio Collections Rudolf Mayer, Andreas Rauber Vienna University of Technology {mayer,rauber}@ifs.tuwien.ac.at Robert Neumayer
More informationIntroduction to Natural Language Processing Phase 2: Question Answering
Introduction to Natural Language Processing Phase 2: Question Answering Center for Games and Playable Media http://games.soe.ucsc.edu The plan for the next two weeks Week9: Simple use of VN WN APIs. Homework
More informationABSTRACT CITATION HANDLING: PROCESSING CITATION TEXTS IN SCIENTIFIC DOCUMENTS. Michael Alan Whidby Master of Science, 2012
ABSTRACT Title of thesis: CITATION HANDLING: PROCESSING CITATION TEXTS IN SCIENTIFIC DOCUMENTS Michael Alan Whidby Master of Science, 2012 Thesis directed by: Professor Bonnie Dorr Dr. David Zajic Department
More informationa start time signature, an end time signature, a start divisions value, an end divisions value, a start beat, an end beat.
The KIAM System in the C@merata Task at MediaEval 2016 Marina Mytrova Keldysh Institute of Applied Mathematics Russian Academy of Sciences Moscow, Russia mytrova@keldysh.ru ABSTRACT The KIAM system is
More informationTHE STRATHMORE LAW REVIEW EDITORIAL POLICY AND STYLE GUIDE
THE STRATHMORE LAW REVIEW EDITORIAL POLICY AND STYLE GUIDE Submissions to the Strathmore Law Review The Strathmore Law Review is an annual peer-reviewed, student-edited academic law journal published by
More informationThe MAMI Query-By-Voice Experiment Collecting and annotating vocal queries for music information retrieval
The MAMI Query-By-Voice Experiment Collecting and annotating vocal queries for music information retrieval IPEM, Dept. of musicology, Ghent University, Belgium Outline About the MAMI project Aim of the
More informationGovernment Unit 3 Performance Task Analysis and Argumentative Writing: Foreign Affairs Paragraph
Government Unit 3 Performance Task Analysis and Argumentative Writing: Foreign Affairs Paragraph Step # 1: Choose a foreign affairs topic from the list below, or suggest an alternative with Mr. H. Step
More informationNielsen Examines TV Viewers to the Political Conventions. September 2008
Nielsen Examines TV Viewers to the Political Conventions September 8 Nielsen Examines TV Viewers to the Political Conventions, September 8 The 8 presidential race has already proven itself an historic
More informationA Comparison of Methods to Construct an Optimal Membership Function in a Fuzzy Database System
Virginia Commonwealth University VCU Scholars Compass Theses and Dissertations Graduate School 2006 A Comparison of Methods to Construct an Optimal Membership Function in a Fuzzy Database System Joanne
More informationSentence and Expression Level Annotation of Opinions in User-Generated Discourse
Sentence and Expression Level Annotation of Opinions in User-Generated Discourse Yayang Tian University of Pennsylvania yaytian@cis.upenn.edu February 20, 2013 Yayang Tian (UPenn) Sentence and Expression
More information1) I feel good today.?! 2) Hey! Can you hear me.?! 3) I like oranges.?! 4) What time did you go to the movie last night.?! 5) Where are we going.?!
Skill: End Marks; Types of Sentences Declarative sentences (those that make a statement) end with a period. Exclamatory sentences (those that show strong emotions) end with an exclamation point. Interrogative
More informationAuthor-Specific Sentiment Aggregation for Polarity Prediction of Reviews
Author-Specific Sentiment Aggregation for Polarity Prediction of Reviews Subhabrata Mukherjee and Sachindra Joshi Max-Planck-Institut für Informatik, Saarbrücken, Germany IBM Research, India smukherjee@mpi-inf.mpg.de,
More informationVideo-based Vibrato Detection and Analysis for Polyphonic String Music
Video-based Vibrato Detection and Analysis for Polyphonic String Music Bochen Li, Karthik Dinesh, Gaurav Sharma, Zhiyao Duan Audio Information Research Lab University of Rochester The 18 th International
More informationCSE 517 Natural Language Processing Winter 2013
CSE 517 Natural Language Processing Winter 2013 Phrase Based Translation Luke Zettlemoyer Slides from Philipp Koehn and Dan Klein Phrase-Based Systems Sentence-aligned corpus Word alignments cat chat 0.9
More informationMusic Genre Classification and Variance Comparison on Number of Genres
Music Genre Classification and Variance Comparison on Number of Genres Miguel Francisco, miguelf@stanford.edu Dong Myung Kim, dmk8265@stanford.edu 1 Abstract In this project we apply machine learning techniques
More informationDetect Missing Attributes for Entities in Knowledge Bases via Hierarchical Clustering
Detect Missing Attributes for Entities in Knowledge Bases via Hierarchical Clustering Bingfeng Luo, Huanquan Lu, Yigang Diao, Yansong Feng and Dongyan Zhao ICST, Peking University Motivations Entities
More informationAgilent Technologies. N5106A PXB MIMO Receiver Tester. Error Messages. Agilent Technologies
Agilent Technologies N5106A PXB MIMO Receiver Tester Messages Agilent Technologies Notices Agilent Technologies, Inc. 2008 2009 No part of this manual may be reproduced in any form or by any means (including
More informationWHITEPAPER. Customer Insights: A European Pay-TV Operator s Transition to Test Automation
WHITEPAPER Customer Insights: A European Pay-TV Operator s Transition to Test Automation Contents 1. Customer Overview...3 2. Case Study Details...4 3. Impact of Automations...7 2 1. Customer Overview
More informationLarge Scale Concepts and Classifiers for Describing Visual Sentiment in Social Multimedia
Large Scale Concepts and Classifiers for Describing Visual Sentiment in Social Multimedia Shih Fu Chang Columbia University http://www.ee.columbia.edu/dvmm June 2013 Damian Borth Tao Chen Rongrong Ji Yan
More informationRecommending Citations: Translating Papers into References
Recommending Citations: Translating Papers into References Wenyi Huang harrywy@gmail.com Prasenjit Mitra pmitra@ist.psu.edu Saurabh Kataria Cornelia Caragea saurabh.kataria@xerox.com ccaragea@ist.psu.edu
More informationNational University of Singapore, Singapore,
Editorial for the 2nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL) at SIGIR 2017 Philipp Mayr 1, Muthu Kumar Chandrasekaran
More informationBi-Modal Music Emotion Recognition: Novel Lyrical Features and Dataset
Bi-Modal Music Emotion Recognition: Novel Lyrical Features and Dataset Ricardo Malheiro, Renato Panda, Paulo Gomes, Rui Paiva CISUC Centre for Informatics and Systems of the University of Coimbra {rsmal,
More informationWeb of Science Unlock the full potential of research discovery
Web of Science Unlock the full potential of research discovery Hungarian Academy of Sciences, 28 th April 2016 Dr. Klementyna Karlińska-Batres Customer Education Specialist Dr. Klementyna Karlińska- Batres
More informationSemi-supervised Musical Instrument Recognition
Semi-supervised Musical Instrument Recognition Master s Thesis Presentation Aleksandr Diment 1 1 Tampere niversity of Technology, Finland Supervisors: Adj.Prof. Tuomas Virtanen, MSc Toni Heittola 17 May
More informationAnalysis of Cancon Facebook pages and posts
15.2.2016/Leena Vuorenmaa (cancon@cancer.fi) Analysis of Cancon Facebook pages and posts 16.10.2015-15.1.2016 Figure 1. Cancon Facebook pages (www.facebook.com/cancon2014) Cancon Facebook pages (www.facebook.com/cancon2014)
More informationYour Sentiment Precedes You: Using an author s historical tweets to predict sarcasm
Your Sentiment Precedes You: Using an author s historical tweets to predict sarcasm Anupam Khattri 1 Aditya Joshi 2,3,4 Pushpak Bhattacharyya 2 Mark James Carman 3 1 IIT Kharagpur, India, 2 IIT Bombay,
More informationIntroduction to Natural Language Processing This week & next week: Classification Sentiment Lexicons
Introduction to Natural Language Processing This week & next week: Classification Sentiment Lexicons Center for Games and Playable Media http://games.soe.ucsc.edu Kendall review of HW 2 Next two weeks
More informationA QUERY BY EXAMPLE MUSIC RETRIEVAL ALGORITHM
A QUER B EAMPLE MUSIC RETRIEVAL ALGORITHM H. HARB AND L. CHEN Maths-Info department, Ecole Centrale de Lyon. 36, av. Guy de Collongue, 69134, Ecully, France, EUROPE E-mail: {hadi.harb, liming.chen}@ec-lyon.fr
More informationIntroduction to WordNet, HowNet, FrameNet and ConceptNet
Introduction to WordNet, HowNet, FrameNet and ConceptNet Zi Lin the Department of Chinese Language and Literature August 31, 2017 Zi Lin (PKU) Intro to Ontologies August 31, 2017 1 / 25 WordNet Begun in
More informationNYU Scholars for Individual & Proxy Users:
NYU Scholars for Individual & Proxy Users: A Technical and Editorial Guide This NYU Scholars technical and editorial reference guide is intended to assist individual users & designated faculty proxy users
More informationgresearch Focus Cognitive Sciences
Learning about Music Cognition by Asking MIR Questions Sebastian Stober August 12, 2016 CogMIR, New York City sstober@uni-potsdam.de http://www.uni-potsdam.de/mlcog/ MLC g Machine Learning in Cognitive
More informationNYU Scholars for Department Coordinators:
NYU Scholars for Department Coordinators: A Technical and Editorial Guide This NYU Scholars technical and editorial reference guide is intended to assist editors and coordinators for multiple faculty members
More informationCRIS with in-text citations as interactive entities. Sergey Parinov CEMI RAS and RANEPA
CRIS with in-text citations as interactive entities Sergey Parinov CEMI RAS and RANEPA In-text citations as interactive elements, why? Location of mentioning Frequency of mentioning Style of mentioning
More informationFOIL it! Find One mismatch between Image and Language caption
FOIL it! Find One mismatch between Image and Language caption ACL, Vancouver, 31st July, 2017 Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich, Aurelie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi
More informationHIT SONG SCIENCE IS NOT YET A SCIENCE
HIT SONG SCIENCE IS NOT YET A SCIENCE François Pachet Sony CSL pachet@csl.sony.fr Pierre Roy Sony CSL roy@csl.sony.fr ABSTRACT We describe a large-scale experiment aiming at validating the hypothesis that
More information2 o Semestre 2013/2014
Departamento de Engenharia Informática Instituto Superior Técnico 2 o Semestre 2013/2014 Bibliography AnHai Doan, Raghu Ramakrishnan, and Shivakumar Vaithyanathan. Managing information extraction: state
More informationThe Million Song Dataset
The Million Song Dataset AUDIO FEATURES The Million Song Dataset There is no data like more data Bob Mercer of IBM (1985). T. Bertin-Mahieux, D.P.W. Ellis, B. Whitman, P. Lamere, The Million Song Dataset,
More informationLife Domain: Income, Standard of Living, and Consumption Patterns Goal Dimension: Objective Living Conditions. Income Level
Life Domain: Income, Standard of Living, and Consumption Patterns Goal Dimension: Objective Living Conditions Measurement Dimension: Subdimension: Indicator: Definition: Population: Income Level I1113
More informationChinese Word Sense Disambiguation with PageRank and HowNet
Chinese Word Sense Disambiguation with PageRank and HowNet Jinghua Wang Beiing University of Posts and Telecommunications Beiing, China wh_smile@163.com Jianyi Liu Beiing University of Posts and Telecommunications
More informationSupervised Learning in Genre Classification
Supervised Learning in Genre Classification Introduction & Motivation Mohit Rajani and Luke Ekkizogloy {i.mohit,luke.ekkizogloy}@gmail.com Stanford University, CS229: Machine Learning, 2009 Now that music
More informationFigures in Scientific Open Access Publications
Figures in Scientific Open Access Publications Lucia Sohmen 2[0000 0002 2593 8754], Jean Charbonnier 1[0000 0001 6489 7687], Ina Blümel 1,2[0000 0002 3075 7640], Christian Wartena 1[0000 0001 5483 1529],
More informationSupplementary Note. Supplementary Table 1. Coverage in patent families with a granted. all patent. Nature Biotechnology: doi: /nbt.
Supplementary Note Of the 100 million patent documents residing in The Lens, there are 7.6 million patent documents that contain non patent literature citations as strings of free text. These strings have
More informationYOU ARE WHAT YOU LIKE INFORMATION LEAKAGE THROUGH USERS INTERESTS
NDSS Symposium 2012 YOU ARE WHAT YOU LIKE INFORMATION LEAKAGE THROUGH USERS INTERESTS Abdelberi (Beri) Chaabane, Gergely Acs, Mohamed Ali Kaafar Internet = Online Social Networks? Most visited websites:
More informationNatural Language Processing (CSE 517): Predicate-Argument Semantics
Natural Language Processing (CSE 517): Predicate-Argument Semantics Noah Smith c 2016 University of Washington nasmith@cs.washington.edu February 29, 2016 1 / 61 Semantics vs. Syntax Syntactic theories
More informationPrimary and Secondary Sources of information
Primary and Secondary Sources of information What are primary sources? Original records from the past recorded by people who were: Involved in the event Witnessed the event, OR Knew the persons involved
More informationOn Meaning. language to establish several definitions. We then examine the theories of meaning
Aaron Tuor Philosophy of Language March 17, 2014 On Meaning The general aim of this paper is to evaluate theories of linguistic meaning in terms of their success in accounting for definitions of meaning
More informationAn Impact Analysis of Features in a Classification Approach to Irony Detection in Product Reviews
Universität Bielefeld June 27, 2014 An Impact Analysis of Features in a Classification Approach to Irony Detection in Product Reviews Konstantin Buschmeier, Philipp Cimiano, Roman Klinger Semantic Computing
More informationBrowsing News and Talk Video on a Consumer Electronics Platform Using Face Detection
Browsing News and Talk Video on a Consumer Electronics Platform Using Face Detection Kadir A. Peker, Ajay Divakaran, Tom Lanning Mitsubishi Electric Research Laboratories, Cambridge, MA, USA {peker,ajayd,}@merl.com
More informationMulti-modal Analysis for Person Type Classification in News Video
Multi-modal Analysis for Person Type Classification in News Video Jun Yang, Alexander G. Hauptmann School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave, PA 15213, USA {juny, alex}@cs.cmu.edu,
More informationMusic Emotion Recognition. Jaesung Lee. Chung-Ang University
Music Emotion Recognition Jaesung Lee Chung-Ang University Introduction Searching Music in Music Information Retrieval Some information about target music is available Query by Text: Title, Artist, or
More informationhit), and assume that longer incidental sounds (forest noise, water, wind noise) resemble a Gaussian noise distribution.
CS 229 FINAL PROJECT A SOUNDHOUND FOR THE SOUNDS OF HOUNDS WEAKLY SUPERVISED MODELING OF ANIMAL SOUNDS ROBERT COLCORD, ETHAN GELLER, MATTHEW HORTON Abstract: We propose a hybrid approach to generating
More informationFirst Step Towards Enhancing Word Embeddings with Pitch Accents for DNN-based Slot Filling on Recognized Text
First Step Towards Enhancing Word Embeddings with Pitch Accents for DNN-based Slot Filling on Recognized Text Sabrina Stehwien, Ngoc Thang Vu IMS, University of Stuttgart March 16, 2017 Slot Filling sequential
More informationPredicting Time-Varying Musical Emotion Distributions from Multi-Track Audio
Predicting Time-Varying Musical Emotion Distributions from Multi-Track Audio Jeffrey Scott, Erik M. Schmidt, Matthew Prockup, Brandon Morton, and Youngmoo E. Kim Music and Entertainment Technology Laboratory
More informationA Generic Semantic-based Framework for Cross-domain Recommendation
A Generic Semantic-based Framework for Cross-domain Recommendation Ignacio Fernández-Tobías, Marius Kaminskas 2, Iván Cantador, Francesco Ricci 2 Escuela Politécnica Superior, Universidad Autónoma de Madrid,
More informationAutomatic Music Clustering using Audio Attributes
Automatic Music Clustering using Audio Attributes Abhishek Sen BTech (Electronics) Veermata Jijabai Technological Institute (VJTI), Mumbai, India abhishekpsen@gmail.com Abstract Music brings people together,
More informationMusic Information Retrieval Community
Music Information Retrieval Community What: Developing systems that retrieve music When: Late 1990 s to Present Where: ISMIR - conference started in 2000 Why: lots of digital music, lots of music lovers,
More informationWHAT'S HOT: LINEAR POPULARITY PREDICTION FROM TV AND SOCIAL USAGE DATA Jan Neumann, Xiaodong Yu, and Mohamad Ali Torkamani Comcast Labs
WHAT'S HOT: LINEAR POPULARITY PREDICTION FROM TV AND SOCIAL USAGE DATA Jan Neumann, Xiaodong Yu, and Mohamad Ali Torkamani Comcast Labs Abstract Large numbers of TV channels are available to TV consumers
More informationMethodologies for Creating Symbolic Early Music Corpora for Musicological Research
Methodologies for Creating Symbolic Early Music Corpora for Musicological Research Cory McKay (Marianopolis College) Julie Cumming (McGill University) Jonathan Stuchbery (McGill University) Ichiro Fujinaga
More informationVFA Participation Agreement 2018 (Year 5)
1 VFA Participation Agreement 2018 (Year 5) The VFA Participation Agreement is updated and approved by the VFA Oversight Board. This agreement s terms and conditions supersede any earlier VFA Participation
More informationPrecision testing methods of Event Timer A032-ET
Precision testing methods of Event Timer A032-ET Event Timer A032-ET provides extreme precision. Therefore exact determination of its characteristics in commonly accepted way is impossible or, at least,
More informationMULTIPLE TPS REHOST FROM GENRAD 2235 TO S9100
MULTIPLE TPS REHOST FROM GENRAD 2235 TO S9100 AL L I A N C E S U P P O R T PAR T N E R S, I N C. D AV I D G U I N N ( D AV I D. G U I N N @ A S P - S U P P O R T. C O M ) L I N YAN G ( L I N. YAN G @ A
More informationTHE USE OF THOMSON REUTERS RESEARCH ANALYTIC RESOURCES IN ACADEMIC PERFORMANCE EVALUATION DR. EVANGELIA A.E.C. LIPITAKIS SEPTEMBER 2014
THE USE OF THOMSON REUTERS RESEARCH ANALYTIC RESOURCES IN ACADEMIC PERFORMANCE EVALUATION DR. EVANGELIA A.E.C. LIPITAKIS SEPTEMBER 2014 Agenda Academic Research Performance Evaluation & Bibliometric Analysis
More informationCHAPTER 2 REVIEW OF RELATED LITERATURE. advantages the related studies is to provide insight into the statistical methods
CHAPTER 2 REVIEW OF RELATED LITERATURE The review of related studies is an essential part of any investigation. The survey of the related studies is a crucial aspect of the planning of the study. The advantages
More informationDrum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods
Drum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods Kazuyoshi Yoshii, Masataka Goto and Hiroshi G. Okuno Department of Intelligence Science and Technology National
More informationStructured training for large-vocabulary chord recognition. Brian McFee* & Juan Pablo Bello
Structured training for large-vocabulary chord recognition Brian McFee* & Juan Pablo Bello Small chord vocabularies Typically a supervised learning problem N C:maj C:min C#:maj C#:min D:maj D:min......
More informationjsymbolic 2: New Developments and Research Opportunities
jsymbolic 2: New Developments and Research Opportunities Cory McKay Marianopolis College and CIRMMT Montreal, Canada 2 / 30 Topics Introduction to features (from a machine learning perspective) And how
More informationUsing Genre Classification to Make Content-based Music Recommendations
Using Genre Classification to Make Content-based Music Recommendations Robbie Jones (rmjones@stanford.edu) and Karen Lu (karenlu@stanford.edu) CS 221, Autumn 2016 Stanford University I. Introduction Our
More informationRelease Year Prediction for Songs
Release Year Prediction for Songs [CSE 258 Assignment 2] Ruyu Tan University of California San Diego PID: A53099216 rut003@ucsd.edu Jiaying Liu University of California San Diego PID: A53107720 jil672@ucsd.edu
More informationDetecting Hoaxes, Frauds and Deception in Writing Style Online
Detecting Hoaxes, Frauds and Deception in Writing Style Online Sadia Afroz, Michael Brennan and Rachel Greenstadt Privacy, Security and Automation Lab Drexel University What do we mean by deception? Let
More informationCTP431- Music and Audio Computing Music Information Retrieval. Graduate School of Culture Technology KAIST Juhan Nam
CTP431- Music and Audio Computing Music Information Retrieval Graduate School of Culture Technology KAIST Juhan Nam 1 Introduction ü Instrument: Piano ü Genre: Classical ü Composer: Chopin ü Key: E-minor
More information