I256 Applied Natural Language Processing Fall 2009 Lecture 12 Projects Barbara Rosario.

Slides:



Advertisements
Similar presentations
To Make the Teachers Life Easier Gail Lanham Melanie Roberts KYSTE Conference 2013 FREE APPS & WEBSITES.
Advertisements

The go-to place for all our Extensive Reading needs
Data Mining & Machine Learning Group Ch. EickAssignment 5 Assignment5 Details  The project is a group project; take advantage of your increased man-power.
Project Proposal.
+ Yearbook Class Introduction Rules and Syllabus Give each student their binder which includes: Syllabus Turn in signature sheet Rubric Guide.
NEW! Since the submission of the topic of today’s presentation there have been new features added to FamilySearch.org –General Public can submit trees.
Objectives Moodle is an online learning environment where instructors & their students interact. In this workshop you will learn: 1.Configure system requirements.
Productivity apps and journalism: Putting IFTTT and other apps to work for you Avery Wilks March 27, 2015.
for Teachers, Students and Parents.
1 I256: Applied Natural Language Processing Marti Hearst October 18, 2006.
R EAD & W RITE G OLD : T EXT H ELP S YSTEMS I NC.: T EXT TO S PEECH S OFTWARE By: Ashley, Kathryn, Rine, and Samantha.
COMP 110 Introduction to Programming Mr. Joshua Stough August 22, 2007 Monday/Wednesday/Friday 3:00-4:15 Gardner Hall 307.
COMP 14 – 02: Introduction to Programming Andrew Leaver-Fay August 31, 2005 Monday/Wednesday 3-4:15 pm Peabody 217 Friday 3-3:50pm Peabody 217.
October 2, 2012
1 Mcgill office for students with disabilities Self-Regulation through Assistive Technology.
The 12 screens to follow contain a number of Tool descriptions, some instructions on their use, and in some cases a Task or two. If you dedicate one hour.
This is Google Drive. It stores all the documents you have made here.
Lecture 2 - Variables, program execution, calculations, print() COMPSCI 101 Principles of Programming.
CS598CXZ Course Summary ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.
Mendeley Institutional Edition Hazman Aziz, eProduct Manager (APAC) University Kebangsaan Malaysia.
Introduction CSE 1310 – Introduction to Computers and Programming
FUNDAMENTALS OF WRITING March 24, Today Continue summaries Introduction to Assignment 1.
Introduction CSE 2320 – Algorithms and Data Structures Vassilis Athitsos University of Texas at Arlington 1.
WRA 150: EVOLUTION OF AMERICAN THOUGHT THURSDAY, OCT. 31, 2013.
COMP Introduction to Programming Yi Hong May 13, 2015.
Moodle (Course Management Systems). Assignments 1 Assignments are a refreshingly simple method for collecting student work. They are a simple and flexible.
Unit B: Expanding Your Productivity Page: 24 to 37.
1 Technical & Business Writing (ENG-315) Muhammad Bilal Bashir UIIT, Rawalpindi.
Welcome to Ms. Woods’ 7 th Grade Math My My classroom phone number is
CapturaTalk4Android Demonstration Abi James
CST 229 Introduction to Grammars Dr. Sherry Yang Room 213 (503)
Introduction CSE 1310 – Introduction to Computers and Programming Vassilis Athitsos University of Texas at Arlington 1.
Information Retrieval and Web Search Lecture 1. Course overview Instructor: Rada Mihalcea Class web page:
Data Mining & Machine Learning Group Ch. EickProject COSC 6335 Project4 Fall 2011  Project4 is a group project (we will have 7 groups of 4 students.
Class Experiment Psych 231: Research Methods in Psychology.
MULTIMEDIA DEFINITION OF MULTIMEDIA
LING/C SC/PSYC 438/538 Lecture 2 Sandiway Fong. Today’s Topics Did you read Chapter 1 of JM? – Short Homework 2 (submit by midnight Friday) Today is Perl.
Dana Nau: CMSC 722, AI Planning Licensed under the Creative Commons Attribution-NonCommercial-ShareAlike License:
Tuesday 26 th May Higher Computing Science Days Peter Donaldson and Quintin Cutts.
CSC350: Learning Management Systems COMSATS Institute of Information Technology (Virtual Campus)
COP3502: Introduction to Computer Science Yashas Shankar.
CS 6961: Structured Prediction Fall 2014 Course Information.
Fundamental Programming: Fundamental Programming K.Chinnasarn, Ph.D.
Course grading Project: 75% Broken into several incremental deliverables Paper appraisal/evaluation/project tool evaluation in earlier May: 25%
Chapter 12.  Web/Online  When preparing news for web consider… ▪ Announce the news as soon as possible ▪ Update in increments ▪ Tell when there is more.
Apps Presented by: Michael Quinzi, Trevis Choates, David McElroy, Diego Gac, and Trey Leonard.
CSC USI Class Meeting 9 October 31, 2007.
 Digital Storytelling  Module #3 TIE585AC Integrating Web 2.0 Applications in the Classroom Module #3 Image source:
Intermediate 2 Computing Unit 2 - Software Development.
Windows Movie Maker And iMovie What is Windows Movie Maker: Windows movie maker is a video creating and editing software application included in Microsoft.
CS210: Programming Languages Overview of class Dr. Robert Heckendorn.
Digital Images / Write Copy CUFIMA01A Produce And Manipulate Digital Images CUFWRT05A Write Content And/Or Copy Week 4.
VOLUNTEER CONFERENCE REGIONAL NEWSLETTERS Lesley Lenssen and Andrew Kozman 4 th September 2015.
CSS 290: Video Games and Computer Programming Instructor: Mike Panitz Tuesdays and Thursdays, 1:15pm-3:20pm UW
Dana Nau: CMSC 722, AI Planning Licensed under the Creative Commons Attribution-NonCommercial-ShareAlike License:
Social Media Whats Out? What’s In? What’s New?. Social Media- What’s Out: Ask.fm Tumblr Facebook.
Blog A Web site that contains dated text entries in reverse chronological order (most recent first) about a particular topic. Blogs serve many purposes.
Lights, Camera, Action! How and Why to Make Association Videos.
Back to School Night 2 nd Grade Barb Strueby
Blue Ridge Unified School District.  How will this help me? My Family Link  Where do I get started? Personal Profile Page  How do I manage my webpage?
Christa Marsh Southern Arkansas University Biology Professor.
Whats Out? What’s In? What’s New?
Helping you succeed in promoting your club
Top 10 Technology Tools for Teaching and Learning
Melksham Oak Community School 12 November, 2018
Welcome to Junior High ELA
How do I research effectively? Part 2
The ultimate in data organization
for Teachers, Students and Parents.
Online Safety Evening 2019.
Presentation transcript:

I256 Applied Natural Language Processing Fall 2009 Lecture 12 Projects Barbara Rosario

2 Today Special guest: Rob Ennals, Intel Labs Berkeley More project ideas Next class –Finish up classification –Information extraction

3 Announcements Tuesday October 20 assignment 4 due –5% more if submitted at least 24 hours in advance –We’ll accept late submissions if: 1)You haven’t submitted late a previous homework And 2) You let me know in advance (by the day before) Thursday October 15 project proposal due ments/project_proposal.html ments/project_proposal.html –1 page –General idea/topic –(If you know already) what kind of data/resources would you like to use? –(If you know already) what methods do you think you'll use?

4 Projects important dates Thursday Oct 15: Proposal Due Thursday October 22: Receive Feedback on Proposal Thursday October 29: Turn in revised proposal (if required) Thursday November 12: Check point (more information later) Dec 1 and 3: Class Presentations Thursday Dec 10 (subject to change): Final Project Write- up due

5 Rob Ennals

6 Project ideas Whatever you like and are interested in! Ideally, it should have at least one of the following elements: Interesting, novel application and/or data –i.e. topic classification for reuter wouldn’t count…. –Twitter? New algorithm –Then you can use reuter data… Linguistic analysis –To inform the NLP! (i.e. analysis to be useful to a NLP algorithm task/algorithm) Implementation for novel use (iPhone?)

7 Scaling Up to Large Datasets System calls to external software Python is not able to perform the numerically intensive calculations required by machine learning methods nearly as quickly as lower-level languages such as C. On large datasets, you may find that the learning algorithm takes an unreasonable amount of time and memory to complete if you use the pure-Python machine learning implementations NLTK's facilities for interfacing with external machine learning packages. Once these packages have been installed, NLTK can transparently invoke them (via system calls) to train classifier models significantly faster than the pure-Python classifier implementations. See the NLTK webpage for a list of recommended machine learning packages that are supported by NLTK.

8 Software If you need some fancy (i.e. expensive) software, let me know asap –I may be able to buy it and let you use it for the projects An annotated list of resources

9 Final Project Ideas NLP with me all the time: Interfaces 90% useful 90% of the time What are the NLP problems for a speech interfaces that is always with me? Take an audio recorder with you for a whole day. Record all the speech commands you would give to your perfect interface –Call mike –Write this message to sally hi sally movie tonight? –Remind me to buy milk when I go to the store –Put dentist on tue on the calendar –Where can I buy a bluetooth device nearby? –Set facebook status class today sucked glad is over –Twitter class today sucked glad is over

10 NLP with me all the time Analysis –Analyze the commands –How many types of actions/classes? –What NLP apps (translations? extractions, etc) –Call [Mike]: action/class = phone, argument = Mike NLP tasks: classification and extraction –Set Facebook status [class today sucked glad is over]: action/class = facebook, argument = [class today sucked glad is over] NLP tasks: classification and extraction Build a NLP algorithm for this data

11 NLP with me all the time Additional: note the context of what you were doing while you said the commands (we are interested in how the context can inform the NLP) –For example: send this picture to Annette –Context: Annette is in front of me

12 Final Project Ideas NLP summarization for audio interfaces –Summarize , blogs, news article –Different lengths or incremental (tell me more, or tell me less –get to the point!) –(Are audio summaries different from written ones?)

13 Final Project Ideas Intel® Reader To assist people with various disabilities (blindness, dyslexia) The Intel Reader performs text-to-speech (TTS) on captured images (with OCR) and downloaded text files

14

15 Intel® Reader Text to speech: Improved Speech Output –Contextual Pronunciation TTS engines still relatively poor on context-based pronunciation variations –Examples: “LIVE” “LEAD” “I live in California” vs. “I watched the live performance of the concert” “That battery is made from lead” vs. “I will lead the troops into battle”

16 Final Project Ideas Two NLP problems for Intel® Reader Contextual Pronunciation –Identify words that have ambiguous pronunciation –Choose the right pronunciation OCR errors –Identify words that are mistakes (o-c, miso, misc) –Choose the right words

17 Final Project Ideas Blog analysis –Categorize blog topics (maybe including link analysis) –Segment blogs into pieces based on topics –Do blog author analysis –Summarize blog reaction to some event, e.g., what did people think of “An Inconvenient Truth” There is a contest on this: –

18 Final Project Ideas Create a Negativity/Emotion/Flame Recognizer –There is some related work, but this is somewhat under-explored –Emotions in , blogs, facebook statuses…

19 Previous Final Project HomeSkim (2005) –Chan, Lib, Mittal, Poon –Apartment search mashup –Extracted fields from Craigslist listings – kimhttp:// kim Orpheus (2004) –Maury, Viswanathan, Yang –Tool for discovering new and independent recording artists –Extracted artists, links, reviews from music websites – Breaking Story (2002) –Reffell, Fitzpatrick, Aydelott –Summarize trends in news feeds –Categories and entities assigned to all news articles –

20

21

22 HomeSkim Craigslist Analysis

23

24

25

26