jointly predicting predicates and arguments in neural
play

Jointly Predicting Predicates and Arguments in Neural Semantic Role - PowerPoint PPT Presentation

Apr 04, 2023 •443 likes •802 views

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling Luheng He*, Kenton Lee*, Omer Levy + , Luke Zettlemoyer University of Washington *Now at Google + Now at Facebook AI Research 1 Semantic Role Labeling (SRL) Find

  1. Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling Luheng He*, Kenton Lee*, Omer Levy + , Luke Zettlemoyer University of Washington *Now at Google + Now at Facebook AI Research 1

  2. Semantic Role Labeling (SRL) • Find out “ who did what to whom ” in text • Capture predicate-argument structures ARG0 eater ARG1 meal I ate pizza with friends AM-COM comitative 2

  3. Semantic Role Labeling (SRL) • Find out “ who did what to whom ” in text • Capture predicate-argument structures ARG0 eater ARG1 meal I ate pizza with friends AM-COM comitative ARG0 eater ARG1 meal I ate pizza with friends 2

  4. SRL as BIO Tagging Output1 ARG0 V ARG1 AM-PRP B-AM- I-AM- I-AM- I-AM- I-AM- I-AM- B-A0 I-A0 B-V B-A1 PRP PRP PRP PRP PRP PRP Many tourists visit Disney to meet their favorite cartoon characters Input1 Needs target predicate as input! (Prior works typically used gold predicates) Collobert et al., 2011, Zhou and Xu, 2015, He et. al, 2017, inter alia 3

  5. SRL as BIO Tagging Output1 ARG0 V ARG1 AM-PRP B-AM- I-AM- I-AM- I-AM- I-AM- I-AM- B-A0 I-A0 B-V B-A1 PRP PRP PRP PRP PRP PRP Many tourists visit Disney to meet their favorite cartoon characters Input1 Output2 ARG0 V ARG1 Needs to re-run the tagger for each predicate B-A0 I-A0 O O B-V B-A1 I-A1 I-A1 I-A1 O Many tourists visit Disney to meet their favorite cartoon characters Input2 4

  6. SRL as Predicting Word-Span Relations AM-PRP ARG0 ARG1 Many tourists visit Disney to meet their favorite cartoon characters ARG1 ARG0 � 5

  7. SRL as Predicting Word-Span Relations AM-PRP ARG0 ARG1 Many tourists visit Disney to meet their favorite cartoon characters ARG1 ARG0 Advantages: * Jointly predict predicates * Span-level features 
 (similar to Punyakanok08, FitzGerald15, inter alia) 
 Challenge: * Too many possible edges (n 2 argument spans x n predicates) � 5

  8. Our Model 6

  9. Our Model: Overview Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters No predicate input! 7

  10. Our Model: Overview tourists visit Disney their favorite cartoon Many tourists Disney to meet their cartoon characters Span Representation (1) Construct span representations Highway for all n 2 spans! BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters 8

  11. Our Model: Overview (2) Local classifier over labels (including NULL) Labeling for all possible (predicate, argument) pairs Softmax … Node & Edge Scores Span Representation (1) Construct span representations Highway for all n 2 spans! BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters 9

  12. Our Model: Overview (2) Local classifier over labels (including NULL) Labeling for all possible (predicate, argument) pairs Softmax … Node & Edge (3) Greedy beam Scores pruning for spans Span Representation (1) Construct span representations Highway for all n 2 spans! BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters 10

  13. (2) Local Label (3) Span (1) Span Representations Classifiers Pruning their favorite cartoon Span Representation Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters (Same as Lee et al., 2017) 11

  14. (2) Local Label (3) Span (1) Span Representations Classifiers Pruning [ BiLstm ( w 1 : w n ) Start , BiLstm ( w 1 : w n ) End ] LSTM boundary points their favorite cartoon Span Representation left context right context Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters (Same as Lee et al., 2017) 11

  15. (2) Local Label (3) Span (1) Span Representations Classifiers Pruning [ BiLstm ( w 1 : w n ) Start , BiLstm ( w 1 : w n ) End ] LSTM boundary points X End i = Start SoftMax ( a Start : a End ) i w i Attention over words their favorite cartoon Span Representation Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters (Same as Lee et al., 2017) 12

  16. <latexit sha1_base64="nvU6K7Xlec9J/cWdW16/i7BwDY=">ACHicbVDLSsNAFL2pr1pfVZdugkVwVRIRdFlw02UL9gFtKJPJTt0Mgkzk2IJ/QHd6n+4E7f+hb/hFzhts7CtBwYO59zLPXP8hDOlHefbKmxt7+zuFfdLB4dHxyfl07O2ilNJsUVjHsuTxRyJrClmebYTSyOfY8cPc78zQalYLB71NEvIkPBQkaJNlJTDMoVp+osYG8SNycVyNEYlH/6QUzTCIWmnCjVc51EexmRmlGOs1I/VZgQOiZD7BkqSITKyxZBZ/aVUQI7jKV5QtsL9e9GRiKlpFvJiOiR2rdm4v/eb1gwhKV3paHltNosN7L2MiSTUKugwSptzWsT1vxQ6YRKr51BCJTN/semISEK16a5kSnLXK9k7Zuq61Td5m2lVs/rKsIFXMI1uHAHNahDA1pAeEFXuHNerberQ/rczlasPKdc1iB9fULDneauA=</latexit> <latexit sha1_base64="nvU6K7Xlec9J/cWdW16/i7BwDY=">ACHicbVDLSsNAFL2pr1pfVZdugkVwVRIRdFlw02UL9gFtKJPJTt0Mgkzk2IJ/QHd6n+4E7f+hb/hFzhts7CtBwYO59zLPXP8hDOlHefbKmxt7+zuFfdLB4dHxyfl07O2ilNJsUVjHsuTxRyJrClmebYTSyOfY8cPc78zQalYLB71NEvIkPBQkaJNlJTDMoVp+osYG8SNycVyNEYlH/6QUzTCIWmnCjVc51EexmRmlGOs1I/VZgQOiZD7BkqSITKyxZBZ/aVUQI7jKV5QtsL9e9GRiKlpFvJiOiR2rdm4v/eb1gwhKV3paHltNosN7L2MiSTUKugwSptzWsT1vxQ6YRKr51BCJTN/semISEK16a5kSnLXK9k7Zuq61Td5m2lVs/rKsIFXMI1uHAHNahDA1pAeEFXuHNerberQ/rczlasPKdc1iB9fULDneauA=</latexit> <latexit sha1_base64="nvU6K7Xlec9J/cWdW16/i7BwDY=">ACHicbVDLSsNAFL2pr1pfVZdugkVwVRIRdFlw02UL9gFtKJPJTt0Mgkzk2IJ/QHd6n+4E7f+hb/hFzhts7CtBwYO59zLPXP8hDOlHefbKmxt7+zuFfdLB4dHxyfl07O2ilNJsUVjHsuTxRyJrClmebYTSyOfY8cPc78zQalYLB71NEvIkPBQkaJNlJTDMoVp+osYG8SNycVyNEYlH/6QUzTCIWmnCjVc51EexmRmlGOs1I/VZgQOiZD7BkqSITKyxZBZ/aVUQI7jKV5QtsL9e9GRiKlpFvJiOiR2rdm4v/eb1gwhKV3paHltNosN7L2MiSTUKugwSptzWsT1vxQ6YRKr51BCJTN/semISEK16a5kSnLXK9k7Zuq61Td5m2lVs/rKsIFXMI1uHAHNahDA1pAeEFXuHNerberQ/rczlasPKdc1iB9fULDneauA=</latexit> <latexit sha1_base64="nvU6K7Xlec9J/cWdW16/i7BwDY=">ACHicbVDLSsNAFL2pr1pfVZdugkVwVRIRdFlw02UL9gFtKJPJTt0Mgkzk2IJ/QHd6n+4E7f+hb/hFzhts7CtBwYO59zLPXP8hDOlHefbKmxt7+zuFfdLB4dHxyfl07O2ilNJsUVjHsuTxRyJrClmebYTSyOfY8cPc78zQalYLB71NEvIkPBQkaJNlJTDMoVp+osYG8SNycVyNEYlH/6QUzTCIWmnCjVc51EexmRmlGOs1I/VZgQOiZD7BkqSITKyxZBZ/aVUQI7jKV5QtsL9e9GRiKlpFvJiOiR2rdm4v/eb1gwhKV3paHltNosN7L2MiSTUKugwSptzWsT1vxQ6YRKr51BCJTN/semISEK16a5kSnLXK9k7Zuq61Td5m2lVs/rKsIFXMI1uHAHNahDA1pAeEFXuHNerberQ/rczlasPKdc1iB9fULDneauA=</latexit> <latexit sha1_base64="Cl3SwRPAtZyFQe08H+ihuTViBc=">ACnicbVDLSsNAFL2pr1pfVZduBovgqiRF0GXBTZcV7QPaWCaTSTt0Mgkzk2IJ/QPd6n+4E7f+hL/hFzhNs7CtBwYO59zLPXO8mDOlbfvbKmxsbm3vFHdLe/sHh0fl45O2ihJaItEPJdDyvKmaAtzTSn3VhSHqcdrzx7dzvTKhULBIPehpTN8RDwQJGsDbSvXisDcoVu2pnQOvEyUkFcjQH5Z+H5EkpEITjpXqOXas3RLzQins1I/UTGZIyHtGeowCFVbpFnaELo/goiKR5QqNM/buR4lCpaeiZyRDrkVr15uJ/Xs+fsFjlt54Wx5aT6ODGTZmIE0FWQJEo50hOa9IJ9JSjSfGoKJZOYviIywxESb9kqmJGe1knXSrlUdu+rcXVXqjbyuIpzBOVyCA9dQhwY0oQUEhvACr/BmPVv1of1uRgtWPnOKSzB+voFRgqbXA=</latexit> <latexit sha1_base64="Cl3SwRPAtZyFQe08H+ihuTViBc=">ACnicbVDLSsNAFL2pr1pfVZduBovgqiRF0GXBTZcV7QPaWCaTSTt0Mgkzk2IJ/QPd6n+4E7f+hL/hFzhNs7CtBwYO59zLPXO8mDOlbfvbKmxsbm3vFHdLe/sHh0fl45O2ihJaItEPJdDyvKmaAtzTSn3VhSHqcdrzx7dzvTKhULBIPehpTN8RDwQJGsDbSvXisDcoVu2pnQOvEyUkFcjQH5Z+H5EkpEITjpXqOXas3RLzQins1I/UTGZIyHtGeowCFVbpFnaELo/goiKR5QqNM/buR4lCpaeiZyRDrkVr15uJ/Xs+fsFjlt54Wx5aT6ODGTZmIE0FWQJEo50hOa9IJ9JSjSfGoKJZOYviIywxESb9kqmJGe1knXSrlUdu+rcXVXqjbyuIpzBOVyCA9dQhwY0oQUEhvACr/BmPVv1of1uRgtWPnOKSzB+voFRgqbXA=</latexit> <latexit sha1_base64="Cl3SwRPAtZyFQe08H+ihuTViBc=">ACnicbVDLSsNAFL2pr1pfVZduBovgqiRF0GXBTZcV7QPaWCaTSTt0Mgkzk2IJ/QPd6n+4E7f+hL/hFzhNs7CtBwYO59zLPXO8mDOlbfvbKmxsbm3vFHdLe/sHh0fl45O2ihJaItEPJdDyvKmaAtzTSn3VhSHqcdrzx7dzvTKhULBIPehpTN8RDwQJGsDbSvXisDcoVu2pnQOvEyUkFcjQH5Z+H5EkpEITjpXqOXas3RLzQins1I/UTGZIyHtGeowCFVbpFnaELo/goiKR5QqNM/buR4lCpaeiZyRDrkVr15uJ/Xs+fsFjlt54Wx5aT6ODGTZmIE0FWQJEo50hOa9IJ9JSjSfGoKJZOYviIywxESb9kqmJGe1knXSrlUdu+rcXVXqjbyuIpzBOVyCA9dQhwY0oQUEhvACr/BmPVv1of1uRgtWPnOKSzB+voFRgqbXA=</latexit> <latexit sha1_base64="Cl3SwRPAtZyFQe08H+ihuTViBc=">ACnicbVDLSsNAFL2pr1pfVZduBovgqiRF0GXBTZcV7QPaWCaTSTt0Mgkzk2IJ/QPd6n+4E7f+hL/hFzhNs7CtBwYO59zLPXO8mDOlbfvbKmxsbm3vFHdLe/sHh0fl45O2ihJaItEPJdDyvKmaAtzTSn3VhSHqcdrzx7dzvTKhULBIPehpTN8RDwQJGsDbSvXisDcoVu2pnQOvEyUkFcjQH5Z+H5EkpEITjpXqOXas3RLzQins1I/UTGZIyHtGeowCFVbpFnaELo/goiKR5QqNM/buR4lCpaeiZyRDrkVr15uJ/Xs+fsFjlt54Wx5aT6ODGTZmIE0FWQJEo50hOa9IJ9JSjSfGoKJZOYviIywxESb9kqmJGe1knXSrlUdu+rcXVXqjbyuIpzBOVyCA9dQhwY0oQUEhvACr/BmPVv1of1uRgtWPnOKSzB+voFRgqbXA=</latexit> (1) Span (3) Span (2) Local Label Classifiers Representations Pruning ARG0 Labeling ARG1 Softmax ARG2 … Node & Edge AM-TMP n 2 Scores … n 𝜗 (No Edge) Span argument predicate Representation Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters 13

  17. (1) Span (3) Span (2) Local Label Classifiers Representations Pruning ARG0 Labeling ARG1 Softmax ARG2 … Node & Edge AM-TMP Scores … 𝜗 (No Edge) Span many tourists meet Representation Highway BiLSTMs Word & Char Embeddings Input sentence Many tourists visit Disney to meet their favorite cartoon characters 14

Recommend

Classical arguments that for us is a PP complement of easy The following arguments are the

Classical arguments that for us is a PP complement of easy The following arguments are the

Classical arguments that for us is a PP complement of easy The following arguments are the principle bases for the claim that tough predicates select the control complement structure, along with a brief indication of why these arguments fail to

330 views • 8 slides
Lecture 3 Predicates and Their Arguments 7/14/2017 Happy Bastille Day! From L0 to L1

Lecture 3 Predicates and Their Arguments 7/14/2017 Happy Bastille Day! From L0 to L1

Lecture 3 Predicates and Their Arguments 7/14/2017 Happy Bastille Day! From L0 to L1 Categories and Types From L0 to L1 Syntactic Rules (Binary Branching of Arguments + Lambda) From L0 to L1 Composition Rules The Lambda

349 views • 15 slides
Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel,

Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel,

Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel, Charles Elkan, Julian McAuley, Zachary Lipton https://arxiv.org/abs/1702.05386 Predicting Surgery Duration Surgeries are expensive, partly due to

465 views • 10 slides
Predicates Reading: EC 1.4 Peter J. Haas INFO 150 Fall Semester 2019 Lecture 3 1/ 15

Predicates Reading: EC 1.4 Peter J. Haas INFO 150 Fall Semester 2019 Lecture 3 1/ 15

Predicates Reading: EC 1.4 Peter J. Haas INFO 150 Fall Semester 2019 Lecture 3 1/ 15 Predicates Simple Predicates and Their Negations Predicates and Sets Quantified Predicates Negating Quantified Predicates Multiple Quantifiers and Their

479 views • 22 slides
MINING USER INTENTIONS FROM MEDICAL QUERIES: A NEURAL NETWORK BASED HETEROGENEOUS JOINTLY

MINING USER INTENTIONS FROM MEDICAL QUERIES: A NEURAL NETWORK BASED HETEROGENEOUS JOINTLY

MINING USER INTENTIONS FROM MEDICAL QUERIES: A NEURAL NETWORK BASED HETEROGENEOUS JOINTLY MODELING APPROACH Source: WWW16 Advisor: Jia-Lin,Koh Speaker: Ming-Chieh,Chiang Date: 2017/12/05 Outline Introduction Method Experiment

487 views • 24 slides
Co-inductive predicates and bisimilarity CoqArt section 13.613.7 Koen Timmermans and

Co-inductive predicates and bisimilarity CoqArt section 13.613.7 Koen Timmermans and

Co-inductive predicates and bisimilarity CoqArt section 13.613.7 Koen Timmermans and Marnix Suilen 1 Definitions Recall the definition of LList : Set Implicit Arguments. CoInductive LList (A:Set) : Set := LNil : LList A | LCons : A

655 views • 43 slides
Jointly Learning Word and Phrase Embeddings Using Neural Networks and Implicit Tensor

Jointly Learning Word and Phrase Embeddings Using Neural Networks and Implicit Tensor

Jointly Learning Word and Phrase Embeddings Using Neural Networks and Implicit Tensor Factorization Kazuma Hashimoto Tsuruoka Laboratory, University of Tokyo 19/06/2015 Talk@UCL Machine Reading Lab. Self Introduction Name Kazuma

726 views • 39 slides
Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM

Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM Transactions on Graphics, Publication date: November 2017 Presenter: MinKu Kang In Previous Talk

911 views • 21 slides
Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 20), August 23 27, 2020, Virtual Event, CA, USA. Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

440 views • 18 slides
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov ICCV 2015 Presenter: Fartash Faghri Zero-shot Learning Classify images of an unseen class

156 views • 12 slides
Conjunctive Predicates 1 Goals of the lecture: Conjunctive Predicates Direct dep

Conjunctive Predicates 1 Goals of the lecture: Conjunctive Predicates Direct dep

Conjunctive Predicates 1 Goals of the lecture: Conjunctive Predicates Direct dep endency algo rithm T ok en based decentralized algo rithm Channel Predicates Reference: Chapter 5. Vija c y K. Ga rg

228 views • 19 slides
DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks Fabien Geyer 1,2 and Steffen Bondorf 3 INFOCOM 2019 Wednesday 1 st May, 2019 1 Chair of Network Architectures and Services 3 Dept. of Information

711 views • 57 slides
Back to the future Back to the future Pointcuts as Pointcuts as Predicates over Predicates

Back to the future Back to the future Pointcuts as Pointcuts as Predicates over Predicates

Back to the future Back to the future Pointcuts as Pointcuts as Predicates over Predicates over Traces Traces Karl Klose, Klaus Ostermann Darmstadt University of Technology, Germany Back to the Future Pointcuts as Predicates over

295 views • 16 slides
Complex Predicates in Urdu Tafseer Ahmed Universitaet Konstanz July 2011 Outline Complex

Complex Predicates in Urdu Tafseer Ahmed Universitaet Konstanz July 2011 Outline Complex

Complex Predicates in Urdu Tafseer Ahmed Universitaet Konstanz July 2011 Outline Complex Predicates Lights verbs used in Complex Predicates Complex Predicates and Verb Classes Conclusion and Future Work Outline Complex Predicates Lights

842 views • 46 slides
Jointly and the Jointly ecosystem Madeleine Starr Director of Business Development and

Jointly and the Jointly ecosystem Madeleine Starr Director of Business Development and

Jointly and the Jointly ecosystem Madeleine Starr Director of Business Development and Innovation Carers UK Our vision A society that respects, values and supports carers . Jointly is an innovative mobile and online app that makes

551 views • 17 slides
Predicting structures: Practical concerns CS 6355: Structured Prediction 1 So far What are

Predicting structures: Practical concerns CS 6355: Structured Prediction 1 So far What are

Predicting structures: Practical concerns CS 6355: Structured Prediction 1 So far What are structures? A graph A collection of parts that are scored jointly A collection of interconnected decisions Conditional

496 views • 31 slides
Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius

Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius

Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius Lindauer &amp; Frank Hutter Paper ID #2772 Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 IJCAI2018 Motivation

588 views • 27 slides
Delay and laziness no not ea eager er ... When are expressions

Delay and laziness no not ea eager er ... When are expressions

11/1/15 Ea Eager evaluation: evaluate arguments first call-by-value semantics When do arguments/subexpressions evaluate (ML, Racket, ...)? Function arguments: once, before calling

157 views • 4 slides
Predicting Regulatory Elements Predicting Regulatory Elements in P. falciparum in P. falciparum

Predicting Regulatory Elements Predicting Regulatory Elements in P. falciparum in P. falciparum

Predicting Regulatory Elements Predicting Regulatory Elements in P. falciparum in P. falciparum Chengyong Yang Erliang Zeng Giri Narasimhan BioInformatics Research Group (BioRG) School of Computer Science Florida International University,

525 views • 31 slides
Predicting Min Predicting Min-Bias and the Bias and the Underlying Event at

Predicting Min Predicting Min-Bias and the Bias and the Underlying Event at

Predicting Min Predicting Min-Bias and the Bias and the Underlying Event at the LHC Underlying Event at the LHC Extrapolations from the Tevatron to RHIC and the LHC Rick Field University of Florida Outline of Talk

679 views • 49 slides
Network Verification Using Atomic Network Verification Using Atomic Predicates Predicates Ne

Network Verification Using Atomic Network Verification Using Atomic Predicates Predicates Ne

Network Verification Using Atomic Network Verification Using Atomic Predicates Predicates Ne two rk Ve rific atio n U sing Ato mic Pre dic ate s (S. S. L am) 1 3/ 28/ 2017 Difficulty in Managing Large Networks Difficulty in Managing Large

760 views • 44 slides
Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology

Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology

Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology Evolution During Electropolishing Joel Thomas 1 , Charles Reece 2 and Stanko R. Brankovic 1,* 1 Cullen College of Engineering University of Houston

399 views • 12 slides
A Heuristic Approach to Detect Opaque Predicates that Disrupt Static Disassembly By: Yu-Jye

A Heuristic Approach to Detect Opaque Predicates that Disrupt Static Disassembly By: Yu-Jye

A Heuristic Approach to Detect Opaque Predicates that Disrupt Static Disassembly By: Yu-Jye Tung, Ian G. Harris Opaque Predicates Defini nition: n: conditional branches that always evaluate to true or false. Thus, one of their branches is

570 views • 23 slides
Predicting and modeling water chemistry Predicting and modeling water chemistry associated with

Predicting and modeling water chemistry Predicting and modeling water chemistry associated with

EPA Workshop Webinar Series on Hardrock Mining Geochemistry and Hydrology: Theme #1 Evaluating water chemistry predictions at Hardrock Mine Sites February 13, 2013 Predicting and modeling water chemistry Predicting and modeling water chemistry

761 views • 46 slides

More recommend