I have trained Stanford NER to extract the organization names from text. I used IO tagging format. It works fine. However, I wonder if changing the tag format to IOB (or other formats) might improve the scores. ?
Suppose you have a sentence that lacks normal punctuation, like this:
John Sam Ted are all here.
If you don't have a B tag you won't be able to tell if this should be three entities or one entity with three words.
On the other hand, for many common types of entities, they can't just run together in normal English text since you'll at least have a comma between them.
If you can set it up, using IOB is better in case you have entities run together, but depending on your data set it may not be an issue. You'll have to look at the data to tell.
Related
When training a doc2vec model using a corpus in the TaggedDocument class, you can provide a list of tags. When the doc2vec model is trained it learns a vector representation for the tags. For example you could have one tag representing the document, and another representing some classification that can be shared between documents.
How would one provide additional tags when streaming a corpus using TaggedLineDocument?
The TaggedLineDocument class only considers documents to be one per line, with a single tag that is their line-number.
If you want more tags, you'll have to provide your own iterable which does that. It should only be a few lines of code, depending on where your other tags come from. You can use the source for TaggedLineDocument – which is itself only 9 lines of Python code –as a model to build on:
https://github.com/RaRe-Technologies/gensim/blob/e4199cb4e9a90df44ca59c1d0505b138caa21951/gensim/models/doc2vec.py#L1126
Note: while supplying ore than one tag per document is a natural extension of the original 'Paragraph Vectors' approach, and often can provide benefits, sometimes it also 'dilutes' the salience of each tag's vector – which will be a special concern as the average number of tags per document grows, or the model acquires many more tags than unique documents. So be sure to comparatively evaluate whether any multiple-tag strategy is helping or hurting, in different modes, and whether things like pre-known categories work better as extra tags or known-labels for some later steps.
I'm looking into creating training data for a Japanese NER.
Wondering if I need to pre-tokenize the training data or is there a way to specify a Tokenizer during model creation?
In the example below Japanese doesn't have any whitespace:
<START:person> Pierre Vinken <END> 61 years old will join the board as a nonexecutive director Nov. 29 .
<START:person> Pierre Vinken <END> は11月29日、非執行取締役として理事に就任する。
Will this work for training a model or do I need provide the training sentences tokenized?
It was a little hard to find the documentation on this but OpenNLP expects the training data to be pre-tokenized, see here:
The data can be converted to the OpenNLP name finder training format. Which is one sentence per line. Some other formats are available as well. The sentence must be tokenized and contain spans which mark the entities.
This could be also inferred from the english example you gave since there's a space before the final period. As a rule, CRF training data is usually pre-tokenized, as that makes evaluation across software packages easier.
Once the sentences are tokenized OpenNLP should work fine with Japanese, since it doesn't really care what the strings are.
https://www.rondhuit.com/apache-opennlp-1-9-0-ja-ner.html
I found this link which could be useful for your purpose.There is a pretrained NRE for the Japanese language which you can download
I know how to train an NER model as specified here and have a very successful one in fact. I also know about the 3 provided caseless models as talked about here. But what if I want to train my own caseless model, what is the trick there? I have a bunch of all uppercase documents for training. Do I use the same training process or are there special/different features for the caseless models or are there properties that need to be set? I can't find a description as to how the provided caseless models were created.
There is only one property change in our models, which is that you want to have it invoke a function that removes case information before words are processed for classification. We do that with this property value (which also maps some words to American spelling):
wordFunction = edu.stanford.nlp.process.LowercaseAndAmericanizeFunction
but there is also simply:
wordFunction = edu.stanford.nlp.process.LowercaseFunction
Having more automatic stuff for deciding document format (hard/soft line breaks), case, or even language would be nice, but at present we don't have any of those....
I have been using the Stanford NER tagger to find the named entities in a document. The problem that I am facing is described below:-
Let the sentence be The film is directed by Ryan Fleck-Anna Boden pair.
Now the NER tagger marks Ryan as one entity, Fleck-Anna as another and Boden as a third entity. The correct marking should be Ryan Fleck as one and Anna Boden as another.
Is this a problem of the NER tagger and if it is then can it be handled?
How about
take your data and run it through Stanford NER or some other NER.
look at the results and find all the mistakes
correctly tag the incorrect results and feed them back into your NER.
lather, rinse, repeat...
This is a sort of manual boosting technique. But your NER probably won't learn too much this way.
In this case it looks like there is a new feature, hyphenated names, the the NER needs to learn about. Why not make up a bunch of hyphenated names, put them in some text, and tag them and train your NER on that?
You should get there by adding more features, more data and training.
Instead of using stanford-coreNLP you could try Apache opeNLP. There is option available to train your model based on your training data. As this model is dependent on the names supplied by you, it able to detect names of your interest.
I want to experiment NER on a specific domain, that is location names extraction from travel offers in Italian language.
So far I've got that I need to prepare the training set by myself, so I'm going to put the
<START:something><END>
tags in some offers from my training set.
But looking at OpenNLP documentation on how to train for NER, I ended up in having a couple of questions:
1) When defining the START/END tags, I'm I free to use whatever name inside the tags (where I wrote "something" a few line above) or is there a restricted set to be bound?
2) I noticed that the call to the training tool
opennlp TokenNameFinderTrainer
takes a string representing the language as the first argument. What is that for? Considering I want to train a model on Italian language that is NOT supported, is there any additional task to be done before I could train for NER?
1) Yes, you can specify multiple types. If the training file contains multiple types, the created model will also be able to detect these multiple types.
2) I think that "lang" parameter has the same meaning/use of other commands (e.g. opennlp TokenizerTrainer -lang it ...)