Piush Aggarwal

Dimension of Topic Vector

1

According to LDA algorithm, dimension of topic vector (word probabilities) should be K X V. K is number of topics and V is vocabulary size (http://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf). But here dimension is...

Hi, Thanks for such an awesome library. I want to apply VL-BERT for different German downstream tasks. Due to data scarcity, I want to use VL-BERT in zero shot settings....

#1454 - German OpenNLP chunker model

19

PR is created - to implement the German chunker model for OpenNLP (request raised in issue [#1454](https://github.com/dkpro/dkpro-core/issues/1454)). - to fix existing bugs available - update ixa en perceptron model -...

High level helper functions for extracting typesystem independent annotations

12

Hi, We are trying to extract token's text_strings and pos tags from cas objects. Also, different type systems lead to return different pos tags formats. @zesch Please correct me here...

Hi, I have found many tweets ids which are available in both datasets (NAACL_SRW_2016 and NLP+CSS_2016). Some of these tweet ids are 572342978255048705 572341498827522049 Both tweet ids are labelled with...