NER or TAGGER?

Hello everybody, I have just joined this mailing list! Thank you in advance for your help. I am studying a simple analizer that extracts specific information from a text. The information i would like to extract are: 1. Person 2. Company 3. Email address 4. Zipcode 5. Home address for email addre

Re: NER or TAGGER?

recognize entities of the three types and then do a regular expression > like pattern matching. For example Name>(\\W+)(\\W+)(\\W+) e.t.c. > > > On Mon, Aug 17, 2015 at 2:55 AM, Damiano Porta > wrote: > > > Hello everybody, > > I have just joined this mailing l

Re: NER or TAGGER?

kup. > > You can also use the list to bootstrap the training data. [This is an > advanced way, just ignore if you dont understand] > > On Mon, Aug 17, 2015 at 5:22 PM, Damiano Porta > wrote: > > > Hello Vihari, thank you for your reply! > > > > Are you sure i s

Best way to find Zipcodes and Telephones

Hello, I am thinking about the best method to find zipcodes and telephones inside my text. Zipcodes must have 5 digits and i also have a Dictionary with a list of real zipcodes of my country. So the first questions is: Do i have to train a NER model or use something like RegexNameFinder or Dictio

Re: Best way to find Zipcodes and Telephones

idity, I am sure you > can find a web service that provides this, depending on what country you’re > in. > > Cheers, > > Martin > > > > > Am 21.08.2015 um 20:17 schrieb Damiano Porta : > > > > Hello, > > I am thinking about the best method to find zip

What regex match? (RegexNameFinder)

Hello, i am using RegexNameFinder to extract specific patterns. I have a list of regexs, i would like to understand what regex match, is this possible? Thanks

Extract entities

Hello everybody, Let suppose the following lines are sentences: - Name: Damiano - Surname: Porta - First name: Damiano - Last name: Porta - Name/Surname: Damiano Porta - Name: Damiano Porta - First name and Last name: Damiano Porta - The name is Damiano and the surname is Porta. etc etc I need

Grammars

Hello! Is there a grammar(pattern engine) like https://gate.ac.uk/sale/tao/splitch8.html#chap:jape for OPENNLP ? Thank you!

TokensRegex

Hello, is there a tool like http://nlp.stanford.edu/software/tokensregex.shtml in OpenNLP? Thanks Damiano

Documents categorization

Hello, we need to categorize our documents in 80 sectors. These documents are resumes/cv. We have many documents (more than 30k) but there is a problem. Should we try to extract the job positions inside each resume and categorize them or can we just add the entire document and categorize it in one

Deprecated NameFinderME.train

Hello, looking at the test code of NameFinderME i found the deprecated *train* method (same thing on the official documentation). NameFinderME.train("en", "PERSON", sampleStream, TrainingParameters.defaultParams(), (byte[]) null, Collections.emptyMap()); that should be replaced with NameFinderME

Categorizer

Hello! can i use/pass a list of custom feature generators into a doccat model via XML? Like NER models for example. Thanks Damiano

Re: Categorizer

you. > > HTH, > Jörn > > On Fri, Dec 16, 2016 at 2:34 PM, Damiano Porta > wrote: > > > Hello! > > can i use/pass a list of custom feature generators into a doccat model > via > > XML? > > Like NER models for example. > > > > Thanks > > Damiano > > >

Re: Categorizer

> > > no, sadly this is not possible, you will have to provide a custom > factory > > > class which wires everything up for you. > > > > > > HTH, > > > Jörn > > > > > > On Fri, Dec 16, 2016 at 2:34 PM, Damiano Porta > > > >

Re: OpenNLP on Twitter

Eugene +1 +1 +1 +1 +1 +1 ... Il 01/Gen/2017 20:57, "Eugene Tenkaev" ha scritto: > And also need to be moved to GitHub with issue tracking there + Gitter for > communication with developers. Mailing list is too old, and hard to be used > > 2017-01-01 21:49 GMT+02:00 Rafik NACCACHE : > > > Gre

Re: OpenNLP on Twitter

Why not an official chat too? Mailing list is old Il 01/Gen/2017 21:10, "Joern Kottmann" ha scritto: > We are on Github: > https://github.com/apache/opennlp > > Jörn > > On Sun, 2017-01-01 at 21:56 +0200, Eugene Tenkaev wrote: > > And also need to be moved to GitHub with issue tracking there + >

Speed up training

Hello, I have a very very big training set, is there a way to speed up the training process? I only have changed the Xmx option inside bin/opennlp Thanks Damiano

Re: Speed up training

I am training a new postagger and lemmatizer. 2017-01-03 19:24 GMT+01:00 Russ, Daniel (NIH/CIT) [E] : > Can you be a little more specific? What trainer are you using? > Thanks > Daniel > > On 1/3/17, 1:22 PM, "Damiano Porta" wrote: > > Hello, > I hav

Re: Speed up training

nnlp-tools/opennlp/tools/util/TrainingParameters.html#THREADS_PARAM > > William > > 2017-01-03 16:27 GMT-02:00 Damiano Porta : > > > I am training a new postagger and lemmatizer. > > > > 2017-01-03 19:24 GMT+01:00 Russ, Daniel (NIH/CIT) [E] < > dr...@mail.nih.gov

Re: Speed up training

Ok, i think the best value is matching the number of CPU cores, right? 2017-01-03 19:47 GMT+01:00 Russ, Daniel (NIH/CIT) [E] : > I do not believe the perceptron trainer is multithreaded. But it should > be fast. > > On 1/3/17, 1:44 PM, "Damiano Porta" wrote: > &g

Re: Speed up training

I always get Exception in thread "main" java.lang.OutOfMemoryError: GC overhead limit exceeded I am using 5GB on Xmx for a 1GB training data...i will try adding 7GB for training. Could the number of threads helps? 2017-01-03 19:57 GMT+01:00 Damiano Porta : > Ok, i think the

Re: Speed up training

your context generator. Maybe it is getting too many features. Try > to keep the strings small in the context generator. > > > 2017-01-03 17:02 GMT-02:00 Damiano Porta : > > > I always get Exception in thread "main" java.lang.OutOfMemoryError: GC > > overhead

Re: Speed up training

I am training the model in this way: opennlp POSTaggerTrainer -type maxent -model /home/damiano/it-pos-maxent-new.bin -lang it -data /home/damiano/postagger.train -encoding UTF-8 2017-01-03 21:01 GMT+01:00 Damiano Porta : > I am using the default postagger tool. > > I have many sente

Re: OpenNLP, telephone numbers, ticker symbols and URLs

Hello Chris, You do not need an extension. There is the RegexNameFinder that can match your entities as well here: https://github.com/apache/opennlp/blob/trunk/opennlp-tools/src/main/java/opennlp/tools/namefind/RegexNameFinder.java Damiano 2017-01-03 22:25 GMT+01:00 Christopher Hansen : > Hello

Proper way to extract name/surname from PERSON entity

Hello everybody, I have trained my NER (maxent) model and fortunately i have a good PERSON accuracy. My problem is when i need to split/extract the name and the surname from the person entity. What way can i follow to do this step? I thought about a classifier that tell me the class of each word

Custom tokenizer?

Hello everybody, I have to build a custom tokenizer that has one more class NOSPLIT. At the moment the current tokenizer supports SPLIT class, i should extend it because i have special code/products that must be in single token (but unfortunately they have whitespaces inside). What approach shoul

Custom features for sentence detector

Hello, can we add custom features on the sentence detector? Thanks Damiano

Re: Custom features for sentence detector

Thank you! 2018-02-14 9:44 GMT+01:00 Aliaksandr Autayeu : > Yes, you can. See SentenceDetectorFactory.getSDContextGenerator() method. > And respectively SDContextGenerator interface and the default > implementation in DefaultSDContextGenerator. > > On 7 February 2018 at 12:17

Re: Opennlp NER with Gazetteer

Hi Sohini, take a look at *DictionaryNameFinder* (https://github.com/apache/opennlp/blob/master/opennlp-tools/src/main/java/opennlp/tools/namefind/DictionaryNameFinder.java) Damiano Il 05/04/2018 17:57, Sohini Bagchi ha scritto: Hi, Has anyone used opennlp NER with gazetteer? If yes then

Should i escape new line?

Hello, i need new lines in my document. Should i escape it with a custom token like ? Thanks

Re: Should i escape new line?

Pardon, i did not explain "where"... i am talking about the training of a NER model 2018-04-12 12:05 GMT+02:00 Damiano Porta : > Hello, > i need new lines in my document. Should i escape it with a custom token > like ? > Thanks >

no roadmap?

Greetings to all! in spite of myself that the library is going very slow about development. I would like to understand if it is your intention to follow the development perhaps integrating more advanced solutions like neural networks or not. I have been using OpenNLP for a long time, but the advanc