I have been trying to use NER feature of NLTK. I want to extract such entities from the articles. I know that it can not be perfect in doing so but I wonder if there is human intervention in between to manually tag NEs, will it improve?
If yes, is it possible with present model in NLTK to continually train the model. (Semi-Supervised Training)
The plain vanilla NER chunker provided in nltk internally uses maximum entropy chunker trained on the ACE corpus. Hence it is not possible to identify dates or time, unless you train it with your own classifier and data(which is quite a meticulous job).
You could refer this link for performing he same.
Also, there is a module called timex in nltk_contrib which might help you with your needs.
If you are interested to perform the same in Java better look into Stanford SUTime, it is a part of Stanford CoreNLP.
Related
I am working on a Named Entity Recognition (NER) project in which I got a large amount of text in the sense that it is too much to read or skim read. Therefore, I want to create an overview of what is mentioned by extracting named entities (places, names, times, maybe topics) and create an index of kind (entity, list of pages/lines where it is mentioned). I have worked through Standford's NLP lecture, (parts of) Eisenstein's Introduction to NLP book found some literature and systems for English texts. As my corpus is in German, I would like to ask how I can approach this problem. Also, this is my first NLP project, so I would not know if I could solve this challenge even if texts were in English.
As a first step
are there German NER systems out there which I could use?
The further roadmap of my project is:
How can I avoid mapping misspellings or rare names to a NUL/UNK token? This is relevant because there are also some historic passages that use words no longer in use or that follow old orthography. I think the relevant terms are tokenisation or stemming.
I thought about fine-tuning or transfer learning the base NER model to a corpus of historic texts to improve NER.
A major challenge is that there is no annotated dataset for my corpus available and I could only manually annotate a tiny fraction of it. So I would be happy for hints on German annotated datasets which I could incorporate into my project.
Thank you in advance for your inputs and fruitful discussions.
Most good NLP toolkits can perform NER in German:
Stanford NLP
Spacy
probably NLTK and OpenNLP as well
What is crucial to understand is that using NER software like the above means using a pretrained model, i.e. a model which has been previously trained on some standard corpus with standard annotated entities.
Btw you can usually find the original annotated dataset by looking at the documentation. There's one NER corpus here.
This is convenient and might suit your goal, but sometimes it doesn't collect exactly every that you would like it to collect, especially if your corpus is from a very specific domain. If you need more specific NER, you must train your own model and this requires obtaining some annotated data (i.e. manually annotating or paying somebody to do it).
Even in this case, a NER model is statistical and it will unavoidably make some mistakes, don't expect perfect results.
About misspellings or rare names: a NER model doesn't care (or not too much) about the actual entity, because it's not primarily based on the words in the entity. It's based on indications in the surrounding text, for example in the sentence "It was announced by Mr XYZ that the event would take place in July", the NER model should find 'Mr XYZ' as a person due to "announced by" and 'July' as a date because of "take place in". However if the language used in the corpus is very different from the training data used for the model, the performance could be very bad.
I want to fine tune BERT on a specific domain. I have texts of that domain in text files. How can I use these to fine tune BERT?
I am looking here currently.
My main objective is to get sentence embeddings using BERT.
The important distinction to make here is whether you want to fine-tune your model, or whether you want to expose it to additional pretraining.
The former is simply a way to train BERT to adapt to a specific supervised task, for which you generally need in the order of 1000 or more samples including labels.
Pretraining, on the other hand, is basically trying to help BERT better "understand" data from a certain domain, by basically continuing its unsupervised training objective ([MASK]ing specific words and trying to predict what word should be there), for which you do not need labeled data.
If your ultimate objective is sentence embeddings, however, I would strongly suggest you to have a look at Sentence Transformers, which is based on a slightly outdated version of Huggingface's transformers library, but primarily tries to generate high-quality embeddings. Note that there are ways to train with surrogate losses, where you try to emulate some form ofloss that is relevant for embeddings.
Edit: The author of Sentence-Transformers recently joined Huggingface, so I expect support to greatly improve over the upcoming months!
#dennlinger gave an exhaustive answer. Additional pretraining is also referred as "post-training", "domain adaptation" and "language modeling fine-tuning". here you will find an example how to do it.
But, since you want to have good sentence embeddings, you better use Sentence Transformers. Moreover, they provide fine-tuned models, which already capable of understanding semantic similarity between sentences. "Continue Training on Other Data" section is what you want to further fine-tune the model on your domain. You do have to prepare training dataset, according to one of available loss functions. E.g. ContrastLoss requires a pair of texts and a label, whether this pair is similar.
I believe transfer learning is useful to train the model on a specific domain. First you load the pretrained base model and freeze its weights, then you add another layer on top of the base model and train that layer based on your own training data. However, the data would need to be labelled.
Tensorflow has some useful guide on transfer learning.
You are talking about pre-training. Fine-tuning on unlabeled data is called pre-training and for getting started, you can take a look over here.
When we train custom model, I do see we have dropout and n_iter parameters to tune, but which deep learning algorithm does Spacy Uses to train Custom Models? Also, when Adding new Entity type is it good to create blank or train it on existing model?
Which learning algorithm does spaCy use?
spaCy has its own deep learning library called thinc used under the hood for different NLP models. for most (if not all) tasks, spaCy uses a deep neural network based on CNN with a few tweaks. Specifically for Named Entity Recognition, spacy uses:
A transition based approach borrowed from shift-reduce parsers, which is described in the paper Neural Architectures for Named Entity Recognition by Lample et al.
Matthew Honnibal describes how spaCy uses this on a YouTube video.
A framework that's called "Embed. Encode. Attend. Predict" (Starting here on the video), slides here.
Embed: Words are embedded using a Bloom filter, which means that word hashes are kept as keys in the embedding dictionary, instead of the word itself. This maintains a more compact embeddings dictionary, with words potentially colliding and ending up with the same vector representations.
Encode: List of words is encoded into a sentence matrix, to take context into account. spaCy uses CNN for encoding.
Attend: Decide which parts are more informative given a query, and get problem specific representations.
Predict: spaCy uses a multi layer perceptron for inference.
Advantages of this framework, per Honnibal are:
Mostly equivalent to sequence tagging (another task spaCy offers models for)
Shares code with the parser
Easily excludes invalid sequences
Arbitrary features are easily defined
For a full overview, Matthew Honnibal describes how the model works in this YouTube video. Slides could be found here.
Note: This information is based on slides from 2017. The engine might have changed since then.
When adding a new entity type, should we create a blank model or train an existing one?
Theoretically, when fine-tuning a spaCy model with new entities, you have to make sure the model doesn't forget representations for previously learned entities. The best thing, if possible, is to train a model from scratch, but that might not be easy or possible due to lack of data or resources.
EDIT Feb 2021: spaCy version 3 now uses the Transformer architecture as its deep learning model.
I am new to stackoverflow. Please forgive my bad English.
I am using word2vec for a school project. I want to work with a domain specific corpus (like Physics Textbook) for creating the word vectors using Word2Vec. This standalone does not provide good results due to lesser size of the corpus. This especially hurts as we want to evaluate on words that may very well be outside the vocabulary of the text book.
We want the textbook to encode the domain specific relationships and semantic "nearness". "Quantum" and "Heisenberg" are especially close in this textbook for eg. which may not hold true for background corpus. To handle the generic words (like "any") we need the basic background model(like the one provided by Google on word2vec site).
Is there any way that we can supplant to the background model using our newer corpus. Just training on the corpus etc. doesnot work well.
Are there any attempts to combine vector representations from two corpus- general and specific. I could not find any in my searches.
Let's talk about gensim since you tagged you question with it. You can load a previously trained model in python using gensim. Then you continue training it. Would it be useful?
# load from previous gensim file:
model = gensim.models.Word2Vec.load(fname)
# or from word2vec c format:
# model = gensim.models.Word2Vec.load_word2vec_format('/path/vectors.bin', binary=True)
# continue training:
model.train(other_sentences)
model.save(fname)
So, this question might be a little naive, but I thought asking the friendly people of Stackoverflow wouldn't hurt.
My current company has been using a third party API for NLP for a while now. We basically URL encode a string and send it over, and they extract certain entities for us (we have a list of entities that we're looking for) and return a json mapping of entity : sentiment. We've recently decided to bring this project in house instead.
I've been studying NLTK, Stanford NLP and lingpipe for the past 2 days now, and can't figure out if I'm basically reinventing the wheel doing this project.
We already have massive tables containing the original unstructured text and another table containing the extracted entities from that text and their sentiment. The entities are single words. For example:
Unstructured text : Now for the bed. It wasn't the best.
Entity : Bed
Sentiment : Negative
I believe that implies we have training data (unstructured text) as well as entity and sentiments. Now how I can go about using this training data on one of the NLP frameworks and getting what we want? No clue. I've sort of got the steps, but not sure:
Tokenize sentences
Tokenize words
Find the noun in the sentence (POS tagging)
Find the sentiment of that sentence.
But that should fail for the case I mentioned above since it talks about the bed in 2 different sentences?
So the question - Does any one know what the best framework would be for accomplishing the above tasks, and any tutorials on the same (Note: I'm not asking for a solution). If you've done this stuff before, is this task too large to take on? I've looked up some commercial APIs but they're absurdly expensive to use (we're a tiny startup).
Thanks stackoverflow!
OpenNLP may also library to look at. At least they have a small tutuorial to train the name finder and to use the document categorizer to do sentiment analysis. To trtain the name finder you have to prepare training data by taging the entities in your text with SGML tags.
http://opennlp.apache.org/documentation/1.5.3/manual/opennlp.html#tools.namefind.training
NLTK provides a naive NER tagger along with resources. But It doesnt fit into all cases (including finding dates.) But NLTK allows you to modify and customize the NER Tagger according to the requirement. This link might give you some ideas with basic examples on how to customize. Also if you are comfortable with scala and functional programming this is one tool you cannot afford to miss.
Cheers...!
I have discovered spaCy lately and it's just great ! In the link you can find comparative for performance in term of speed and accuracy compared to NLTK, CoreNLP and it does really well !
Though to solve your problem task is not a matter of a framework. You can have two different system, one for NER and one for Sentiment and they can be completely independent. The hype these days is to use neural network and if you are willing too, you can train a recurrent neural network (which has showed best performance for NLP tasks) with attention mechanism to find the entity and the sentiment too.
There are great demo everywhere on the internet, the last two I have read and found interesting are [1] and [2].
Similar to Spacy, TextBlob is another fast and easy package that can accomplish many of these tasks.
I use NLTK, Spacy, and Textblob frequently. If the corpus is simple, generic, and straightforward, Spacy and Textblob work well OOTB. If the corpus is highly customized, domain-specific, messy (incorrect spelling or grammar), etc. I'll use NLTK and spend more time customizing my NLP text processing pipeline with scrubbing, lemmatizing, etc.
NLTK Tutorial: http://www.nltk.org/book/
Spacy Quickstart: https://spacy.io/usage/
Textblob Quickstart: http://textblob.readthedocs.io/en/dev/quickstart.html