# 9th Place Efficiency Solution for CommonLit-Evaluate Student Summaries 

First of all, congratulations to the organizers and winners of the competition.
I am very grateful for the opportunity to have participated in this wonderful contest and to have learned from the other competitors.
Context
Overview
[https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview](https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview)
Data
[https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data](https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data)
Overview of the Approach:
My solution implemented for the efficiency award consists of a pipeline composed of the following steps Feature Engineering followed by the following Pipeline:
![](assets/7da81a360faea376796708d7.png)
The CV by prompt:
![](assets/f3a123436e7ef0a8e04155a7.png)
Public LB 0.45943, private LB 0.51579
Details of the submission:
The best performing features were those that used logarithms of counts words, 2-grams, and 3-grams in the summary text and were not in the prompt text. I tried to extract more features with Distillbert and TfidfVectorizer but didn't work.
Sources:
Some ideas for feature engineering were taken from:
[https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372](https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372)
[https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect](https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect)
[https://www.kaggle.com/code/vassylkorzh/feature-engineering](https://www.kaggle.com/code/vassylkorzh/feature-engineering)
[https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf](https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf)
Codes:
Training:
[https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training](https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training)
Inference:
[https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution](https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution)