Kaushik Acharya

I have the following observations while [using](https://github.com/ncbi-nlp/NegBio/issues/27) PyStanfordDependencies in flask app, based on the argument passed in run() function of Flask app. Case 1: **_threaded=False_** This runs fine without making...

> Yeah for some reason the sutime.py file in the repo and the one after doing pip install don't match even though they are the same version. The code in...

@moushumimahato In case you have sequence of sentences: Have a look at the paper: [Automatic classification of sentences to support Evidence Based Medicine by Su Nam Kim et al(2011)](https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-S2-S5) For...

@purohitvivek8 @Anticsss **CoNLL-2003 format**: https://www.clips.uantwerpen.be/conll2003/ner/ - "Software and Data" section explains the format. https://sites.google.com/site/ermasoftware/getting-started/ne-tagging-conll2003-data - This explains with an example. - Also mentions about the DOCSTART line. But as per...

@Mary63 You only need to download pre-trained word embeddings and pass the file path of embeddings as a parameter. As an example, you can download gloVe word embeddings from https://nlp.stanford.edu/projects/glove/...

@svanhviti16 My understanding is that the improvement is due to **character embedding**. https://arxiv.org/abs/1606.03475 The paper mentions: > While the token embeddings capture the semantics of tokens to some degree, they...

> File "D:\PhD\Literature\NeuroNER-master\src\utils_nlp.py", line 54, in get_parsed_conll_output > line = conll_output[1].split() > > IndexError: list index out of range https://github.com/Franck-Dernoncourt/NeuroNER/blob/master/neuroner/utils_nlp.py#L54 ``` conll_output = [l.rstrip().replace('%','').replace(';','').replace(':', '').strip() for l in codecs.open(conll_output_filepath, 'r',...

> Hi, any body knows if the dataset 'cui2vec' is available?? > @souravsingh share the vector in csv, but i don know how to load that in gensim and start...

Hi @yfpeng I checked the output of MetaMap and found that the issue is in NegBio. There are four different ways of **Positional Information** as mentioned in [Metamap documentation](https://metamap.nlm.nih.gov/Docs/MMI_Output_2016.pdf). https://github.com/ncbi-nlp/NegBio/blob/master/negbio/pipeline/dner_mm.py#L58...

@coolabhishek You can use [BioWordVec from BioSentVec](https://github.com/ncbi-nlp/BioSentVec#biowordvec) which the authors claim as extension of the work in the [current repository](https://github.com/ncbi-nlp/BioWordVec). Wiki page explains how to load the BioWordVec: https://github.com/ncbi-nlp/BioSentVec/wiki