Christopher Manning
Fri 13 May 2016, 14:00 - 15:30
Informatics Forum (IF-4.31/4.33)

If you have a question about this talk, please contact: Diana Dalla Costa (ddallac)

Abstract:

Much of computational linguistics and text understanding is either towards one end of the spectrum where there is no representation of compositional linguistic structure (bag-of-words models) or near the other extreme where complex (baroque?) representations are employed (first order logic, AMR, HPSG, ...). A unifying theme of much of my recent work is to explore models with just a little bit of appropriate linguistic structure. I will focus here on two recent case studies in question answering, one using deep learning and the other using natural logic for common sense inference and information extraction.

Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet still unsolved goal of NLP. In this talk, I’ll first introduce our recent work on the Deepmind QA dataset - a recently released dataset of millions of examples constructed from news articles. On the one hand, we show that (simple) neural network models are surprisingly good at solving this task and achieving state-of-the-art accuracies; on the other hand, we did a careful hand-analysis of a small subset of the problems, and we argue that we are quite close to a performance ceiling on this dataset, and it is still quite far from genuine deep / complex understanding.

I will then turn to the use of Natural Logic, a weak proof theory on surface linguistic forms which can nevertheless model many of the common-sense inferences that we wish to make over human language material. I will show how it can support common-sense reasoning and be part of a more linguistically based approach to open information extraction which outperforms previous systems. I show how to augment this approach with a shallow lexical classifier to handle situations where we cannot find any supporting premises. With this augmentation, the system gets very promising results on answering 4th grade science questions, improving over both the classifier in isolation, a strong IR baseline, and prior work.

Joint work with Gabor Angeli and Danqi Chen.

Bio:

Christopher Manning is a professor of computer science and linguistics at Stanford University. His Ph.D. is from Stanford in 1995, and he held faculty positions at Carnegie Mellon University and the University of Sydney before returning to Stanford.  His research goal is computers that can intelligently process, understand, and generate human language material.  Manning concentrates on machine learning approaches to computational linguistic problems, including syntactic parsing, computational semantics and pragmatics, textual inference, machine translation, and compositional deep learning for NLP. He is an ACM Fellow, a AAAI Fellow, and an ACL Fellow, and has coauthored leading textbooks on statistical natural language processing and information retrieval. He is a member of the Stanford NLP group (@stanfordnlp).