DOM-LM: Learning Generalizable Representations for HTML Documents — mentioned by Mathnerd314

Sat, 18 May 2024 15:14:30 GMT

That does a list of blocks and "cheats" by using heavily-engineereed features such as Readability's algorithm. It is suitable for some purposes, I guess. But the paper I am talking about, https://arxiv.org/pdf/2201.10608, does self-supervised learning.

Paper and discussion history. A mention is not an endorsement.

DOM-LM: Learning Generalizable Representations for HTML Documents — mentioned by PaulHoule

Sun, 12 Feb 2023 14:12:23 GMT

I found these papers: https://arxiv.org/abs/2210.03945 https://arxiv.org/abs/2202.00217 https://arxiv.org/abs/2201.10608 My take is that fine-tuning a language model to parse HTML shouldn't be terribly difficult but you probably do need a computer with a good GPU. The one problem that current LLMs have is that they all have a limited attention window. BERT has a 512 token window and ChatGPT has a 4096 token window, where typically a token is less than a word. There are models with much longer windows (reformer) but those don't work as well as the state-of-the-art models, at least not yet.…

Paper and discussion history. A mention is not an endorsement.

DOM-LM: Learning Generalizable Representations for HTML Documents · HackerPapers discussions

DOM-LM: Learning Generalizable Representations for HTML Documents — mentioned by Mathnerd314

DOM-LM: Learning Generalizable Representations for HTML Documents — mentioned by PaulHoule