Computational Linguistics, Machine Learning, and Text Mining with Groovy (aka Java++)
This talk is a brief introduction to computational linguistics by way of looking at some projects I've worked on over the last year demonstrating Information Extraction, Lexical Analysis (the linguistics rather than compiler kind), an Ensemble Method for Statistical Parsing, and Corpus Construction (which includes parsing some English extracted from Javadoc).
In each case I'll give a very brief description of the motivating problem and then dive into code that deals with some part of it. We'll see how Groovy makes the most out of Java for text processing, simple web browser UIs, and cluster computing. This talk should be of interest both to those curious about what goes on in NLP as well as those who would simply like to get some of their work done faster by using more powerful tools.
Technologies we'll see at work (all of which are Open Source Software):
* Stanford CoreNLP
* GATE (General Architecture for Text Engineering)
* MALLET (MAchine Learning for LanguagE Toolkit)
* DELPH-IN PET
* ERG (English Resource Grammar)
- 6:30 - 7:00 pm - Networking
- 7:00 - 8:30 pm - Presentation
Ray Tayek OCJUG Co-Chair and original author of above text posted on:
Details derived from an OCJUG mailing list email sent by Ray Tayek 11/09/13
(OCJUG(Java) Regular Meeting's OCAndroid listing
- (LTNVQ2 track description=All regular meetings of (OCJUG=Orange County Java User Group http://OCJUG.Org) starting 2011.11.))
- (LTNW5G=We list all OCJUG events on OCAndroid because:
- MMIKPH: 1st: since both:
- (LTNVVT="native" & typical Android programming is done in Java.)
- (LTNVY0=Both groups serve exactly the same region: Orange County.)
- MMIKU1: 2nd:
(LTNVYJ=SoCalAndroid Hack Nights, which OCAndroid re-lists, are scheduled not to be the same week as the OCJUG Regular Meeting.)
- (LTOOCC Occurrences in order, 3-or-more in a row, starting ideally at the last to take place=
- (LVWXQI="Schedule: "We meet in person on the 2nd Thursday of each month and any other time through the OCJUG mailing list." says http://OCJUG.Org/.)
- none before
- MMIK8A: [masked]-present:
backup host of this event re-listing, plus editor of this main event description, is quote:
DestinyArchitect of Laguna Hills;[masked]- 179+rsvps&98+attends; Head&~Founder,
- (LTNU6H=1: 2011.11.10thu
Official listing says " "Craig S. Dickson" <[masked]> Elastic BeanstalkDetails".)
- (LTNW5G=2:pst2011.12.08thu, http://meetu.ps/5SPgj
Official listing says " James Ward [on] Deploying Java and Play Framework Apps to the CloudDetails".)
- (LVWXPX=3:pst[masked]thu, http://meetu.ps/6sY0F
- (LYST9E=4:2012.02.09thu:Spring and Cloud Foundry, a Marriage Made in Heaven,http://meetu.ps/75wms
- See Official listing for abstract & speaker bio.
- (LTNVFM=Leader #1: MEZTO5: "4:pst2012.02.09"-#[masked]: "Ray Tayek of Lakewood; joined[masked]; .. leads ocjug track ")
- MEZO7Q: 5:2012.03.08thu:MongoDB soup to nuts+
- MEZOH6: 6:2012.04.12thu:git
- MEZOL2: 7:2012.05.10thu:hack night
- MEZOP9: 8:2012.06.14thu:"state of the Android" by Jeffrey Peacock
- MEZOZG: 9:2012.07.12thu:none -apparently canceled.
- MEZP43: 10:2012.08.09thu:canceled
- MEZPDC: 11: 2012.09.13thu: canceled
- MEZPQK:12: 2012.10.11thu: none-no main meeting, only the usual (but perhaps earlier) socializing at nearby El Torrito Grill
- MEZRLZ:13: 2012.11.08thu: canceled
- MEZRQ8:14:[masked]thu: panel of 5 discuss Consulting + Phillip's going-away party, http://meetu.ps/qGF0R
- MEZRU7:15: [masked]thu: OCJUG 2013 activities planning,http://meetu.ps/rwKrn
- MGDMI5:#[masked]Thu, http://meetu.ps/vCTGj : Book Review.
- (LTNVECTrack Leaders from our group=
- (LTNVHE=Leader #2:(LTNNOM=Open! Nominate Someone by saying so in the event listing's comments.))
- (LO9QFO=To attend, you must follow the latest version of "info for every Meetup.com/OCAndroid event LEVW4X")
- (LG4OWH=What are these codes as “LG4OWH” on this paragraph? They're short IDs to date-stamp, uniquely-reference, and portably-track content.)
- MEZSDH: Listing Todo
- MEZSBG: Listing history:
- MGDM61: starting from listing creation, I Destiny am the author except as noted here.
- MMIIAL: ...--for prior history, see on prior listing
- ML9CW0: renamed title fr q(on OCAndroid: OCJUG(Java) Std Mtg 2013.04+more) to q(OCJUG(Java) Std Mtg via OCAndroid 2013.05+) as clearer; cut Qs from 8 to 6 by cutting last 2 because of new Meetup limitation; pst[masked]Sun1135.
- MMIIF4: cut prior history; cut todos LYSTFB & MEZSMJ; add next 3 upcoming events so thru MMIJS6; change title fr q(OCJUG(Java) Std Mtg via OCAndroid 2013.05+) to present as a more logical order plus includes present topic; plas LTNW5G to 2nd from top & update; add MMIK8A; update MI8OVH; pst[masked]Wed2156.