Commentary on X
@chrmanning that 2006 paper title still feels ahead of its time local textual inference is basically what we want from every llm now
5:57 PM · Jul 14, 2026I would too! I have written very few papers solo in the 21st century and I’m quietly pleased with how all of them have aged. 💅 Probabilistic syntax 2003 https://nlp.stanford.edu/~manning/papers/probsyntax.pdf Local Textual Inference: It’s hard to circumscribe, but you know it when you see it – and NLP needs it 2006 https://nlp.stanford.edu/~manning/papers/LocalTextualInference.pdf Part-of-speech tagging from 97% to 100%: Is it time for some linguistics? 2011 https://nlp.stanford.edu/pubs/CICLing2011-manning-tagging.pdf Last words: Computational linguistics and deep learning 2015 https://aclanthology.org/J15-4006.pdf Human language understanding & reasoning 2022 https://www.amacad.org/sites/default/files/publication/downloads/Daedalus_Sp22_09_Manning.pdf
I would encourage everyone to re-read @chrmanning 's own opinion piece from nearly 10 years ago where he warns about the "Deep learning tsunami" and NLP being sort of a rabbit in the headlights. In 2015 we were discussing context-free word embeddings. Now we have usable coding agents. https://direct.mit.edu/coli/article/41/4/701/1512/Computational-Linguistics-and-Deep-Learning
Combined views
32.1K
2 posts, first seen 5h ago