https://jasonlunder.com/tags/deep-learning/ Recent content in Deep Learning on Jason Lunder Hugo en-us Sun, 08 Feb 2026 00:00:00 +0000 https://jasonlunder.com/post/tree-matching-networks/ Sun, 08 Feb 2026 00:00:00 +0000 https://jasonlunder.com/post/tree-matching-networks/ <p>When we feed text to a transformer, the model has to figure out the structure of language entirely from data. Subject-verb relationships, modifier scope, negation boundaries: all of it must be learned implicitly from millions (or billions) of examples. But what if we just&hellip; told the model the structure upfront?</p> <p>That&rsquo;s the core idea behind <a href="https://arxiv.org/abs/2512.00204">Tree Matching Networks</a> (TMN), my recent research exploring whether dependency parse trees can serve as an efficient structural prior for natural language inference. The short version: a graph neural network operating on parse trees achieved 75.20% accuracy on the SNLI benchmark versus 35.38% for a BERT baseline of comparable size, both trained from scratch on the same data and the same hardware.</p>