{
  "id": 448862,
  "title": "9th Place Efficiency Solution for CommonLit-Evaluate Student Summaries ",
  "content": "<p>First of all, congratulations to the organizers and winners of the competition. <br>\nI am very grateful for the opportunity to have participated in this wonderful contest and to have learned from the other competitors.</p>\n<h1>Context</h1>\n<ul>\n<li>Overview <a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview</a></li>\n<li>Data <a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data</a></li>\n</ul>\n<h1>Overview of the Approach:</h1>\n<p>My solution implemented for the efficiency award consists of a pipeline composed of the following steps Feature Engineering followed by the following Pipeline:</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F64b8524f73ff2bb814cc907c4952f502%2Fpipe.png?generation=1697930928007385&amp;alt=media\" alt=\"\"></p>\n<p>The CV by prompt:</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F9adc3576d7b060c04cd91902cf924b1b%2Ftable.PNG?generation=1697930966613777&amp;alt=media\" alt=\"\"></p>\n<p>Public LB 0.45943, private LB 0.51579</p>\n<h1>Details of the submission:</h1>\n<p>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.</p>\n<h1>Sources:</h1>\n<p>Some ideas for feature engineering were taken from:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372</a></li>\n<li><a href=\"https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect\" target=\"_blank\">https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect</a></li>\n<li><a href=\"https://www.kaggle.com/code/vassylkorzh/feature-engineering\" target=\"_blank\">https://www.kaggle.com/code/vassylkorzh/feature-engineering</a></li>\n<li><a href=\"https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf\" target=\"_blank\">https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf</a></li>\n</ul>\n<h1>Codes:</h1>\n<ul>\n<li>Training: <a href=\"https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training\" target=\"_blank\">https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training</a></li>\n<li>Inference: <a href=\"https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution\" target=\"_blank\">https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution</a></li>\n</ul>",
  "comments": [],
  "comment_count": 0,
  "messages": [
    {
      "id": 2491712,
      "postDate": "2023-10-21T23:32:41.030Z",
      "content": "<p>First of all, congratulations to the organizers and winners of the competition. <br>\nI am very grateful for the opportunity to have participated in this wonderful contest and to have learned from the other competitors.</p>\n<h1>Context</h1>\n<ul>\n<li>Overview <a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview</a></li>\n<li>Data <a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data</a></li>\n</ul>\n<h1>Overview of the Approach:</h1>\n<p>My solution implemented for the efficiency award consists of a pipeline composed of the following steps Feature Engineering followed by the following Pipeline:</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F64b8524f73ff2bb814cc907c4952f502%2Fpipe.png?generation=1697930928007385&amp;alt=media\" alt=\"\"></p>\n<p>The CV by prompt:</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F9adc3576d7b060c04cd91902cf924b1b%2Ftable.PNG?generation=1697930966613777&amp;alt=media\" alt=\"\"></p>\n<p>Public LB 0.45943, private LB 0.51579</p>\n<h1>Details of the submission:</h1>\n<p>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.</p>\n<h1>Sources:</h1>\n<p>Some ideas for feature engineering were taken from:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372\" target=\"_blank\">https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372</a></li>\n<li><a href=\"https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect\" target=\"_blank\">https://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect</a></li>\n<li><a href=\"https://www.kaggle.com/code/vassylkorzh/feature-engineering\" target=\"_blank\">https://www.kaggle.com/code/vassylkorzh/feature-engineering</a></li>\n<li><a href=\"https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf\" target=\"_blank\">https://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf</a></li>\n</ul>\n<h1>Codes:</h1>\n<ul>\n<li>Training: <a href=\"https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training\" target=\"_blank\">https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training</a></li>\n<li>Inference: <a href=\"https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution\" target=\"_blank\">https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution</a></li>\n</ul>",
      "rawMarkdown": "First of all, congratulations to the organizers and winners of the competition. \nI am very grateful for the opportunity to have participated in this wonderful contest and to have learned from the other competitors.\n\n# Context \n\n- Overview https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/overview\n- Data https://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/data\n\n# Overview of the Approach: \n\nMy solution implemented for the efficiency award consists of a pipeline composed of the following steps Feature Engineering followed by the following Pipeline:\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F64b8524f73ff2bb814cc907c4952f502%2Fpipe.png?generation=1697930928007385&alt=media)\n\nThe CV by prompt:\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1647119%2F9adc3576d7b060c04cd91902cf924b1b%2Ftable.PNG?generation=1697930966613777&alt=media)\n\nPublic LB 0.45943, private LB 0.51579\n\n# Details of the submission: \n\nThe 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.\n\n# Sources:\n Some ideas for feature engineering were taken from:\n\n-\thttps://www.kaggle.com/competitions/commonlit-evaluate-student-summaries/discussion/424372\n-\thttps://www.kaggle.com/code/cody11null/tuned-debertav3-lgbm-autocorrect\n-\thttps://www.kaggle.com/code/vassylkorzh/feature-engineering\n-\thttps://www.kaggle.com/code/gusthema/commonlit-evaluate-student-summaries-w-tfdf\n\n\n# Codes:\n-\tTraining: https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution-training\n-\tInference: https://www.kaggle.com/code/jhony1/9th-place-efficiency-solution\n\n\n",
      "votes": 4
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T23:08:11Z",
  "competition_id": 53482,
  "competition_slug": "commonlit-evaluate-student-summaries",
  "team_id": 10783405,
  "solution_url": "/competitions/commonlit-evaluate-student-summaries/writeups/jhonny-escalona-9th-place-efficiency-solution-for-"
}