{
  "id": 90335,
  "title": "Solution sharing thread",
  "content": "<p>Our solution was primarily based on the kernel from Matei. We used models using different BERT embeddings (cased, uncased, small / large) and also embeddings from Flair, Fasttext and finally combined them all. We also had some basic meta features to represent the position information. Our KFold CV on all three gap sets put together is ~0.4</p>\n\n<p>Thanks to @mateiionita @kashnitsky @kenkrige  @wochidadonggua @tks0123456789 and many others for their valuable insights </p>\n\n<p>Look forward to the solutions of top people and the tricks to fine tune the BERT for this problem. </p>",
  "comments": [],
  "comment_count": 0,
  "messages": [
    {
      "id": 521461,
      "postDate": "2019-04-23T00:31:20.170Z",
      "content": "<p>Our solution was primarily based on the kernel from Matei. We used models using different BERT embeddings (cased, uncased, small / large) and also embeddings from Flair, Fasttext and finally combined them all. We also had some basic meta features to represent the position information. Our KFold CV on all three gap sets put together is ~0.4</p>\n\n<p>Thanks to @mateiionita @kashnitsky @kenkrige  @wochidadonggua @tks0123456789 and many others for their valuable insights </p>\n\n<p>Look forward to the solutions of top people and the tricks to fine tune the BERT for this problem. </p>",
      "rawMarkdown": "Our solution was primarily based on the kernel from Matei. We used models using different BERT embeddings (cased, uncased, small / large) and also embeddings from Flair, Fasttext and finally combined them all. We also had some basic meta features to represent the position information. Our KFold CV on all three gap sets put together is ~0.4\n\nThanks to @mateiionita @kashnitsky @kenkrige  @wochidadonggua @tks0123456789 and many others for their valuable insights \n\nLook forward to the solutions of top people and the tricks to fine tune the BERT for this problem. \n\n",
      "votes": 7
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T22:44:15Z",
  "competition_id": 12797,
  "competition_slug": "gendered-pronoun-resolution",
  "team_id": 2797880,
  "solution_url": "/competitions/gendered-pronoun-resolution/writeups/srk-mark-solution-sharing-thread"
}