# 2nd place solution - brief overview

First of all, 1 week is definitely not enough for such a competition. The task is generally the same as at my work, so I would've been much more motivated to try a lot of approaches if the competition were held at least for 6 weeks. Including those approaches that I know working for sure.
But in this format I spent overall ~ 5 hours and my final solution was the following:
 - ULMFiT as in this
[Kernel](https://www.kaggle.com/kashnitsky/ulmfit-starter)
but with encoder trained with full available text data. I concatenated titles and texts from all files (train + valid + test + unlabeled) to get a 114k-length set to train a LM. A classifier finetuned on top of this LM produces 0.81 OOF F1 score (5-fold CV over train.csv + valid.csv), 0.85537 Public LB score and 0.85745 Private LB score. To build OOFs, I run 5 identical Kaggle Kernels (only fold ids differed) which is sort of having 5 GPUs - very convenient even when I have a powerful Quadro P6000 at work :)
 - Simple pipeline (Tf-Idf for titles + Tf-Idf for texts + logistic regression) was not tuned at all, taken basically again from my
[Kernel](https://www.kaggle.com/kashnitsky/eda-logit-tf-idf-starter)
. ~ 0.77 OOF F1 score, around 0.825 LB score (didn't make submissions with it's latest version)
 - Probabilities for each class  output by ULMFiT and logistic regression were then blended with weights tuned on OOF. 0.6 *
ulmfit_pred_probs
+ 0.4
logit_pred_probs
, after applying with argmax, yield 0.86452 Public and 0.86852 Private LB score. Actually, an optimal weight for ULMFiT was 0.9, according to OOF, but 0.6 gave a better LB score, and I decided not to spend time improving the validation scheme. Typically, in such situation, you'd probably switch to multiple 10-fold CVs with different seeds, and would make many more submissions to make sure that CV improvements correlate with LB improvements.
So this was a pretty simple solution, still I'm open to share ideas due to ~ the same task at work. But with Dutch language, logit + Tf-Idf is the best thing so far :)