User profiles for Dan Klein
Daniel N. Kleinstony brook university Verified email at stonybrook.edu Cited by 53229 |
[PDF][PDF] Accurate unlexicalized parsing
D Klein, CD Manning - Proceedings of the 41st annual meeting of …, 2003 - aclanthology.org
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously
shown, by making use of simple, linguistically motivated state splits, which break down …
shown, by making use of simple, linguistically motivated state splits, which break down …
Neural module networks
…, M Rohrbach, T Darrell, D Klein - Proceedings of the …, 2016 - openaccess.thecvf.com
Visual question answering is fundamentally compositional in nature---a question like" where
is the dog?" shares substructure with questions like" what color is the dog?" and" where is …
is the dog?" shares substructure with questions like" what color is the dog?" and" where is …
[PDF][PDF] Feature-rich part-of-speech tagging with a cyclic dependency network
K Toutanova, D Klein, CD Manning… - Proceedings of the 2003 …, 2003 - aclanthology.org
We present a new part-of-speech tagger that demonstrates the following ideas:(i) explicit
use of both preceding and following tag contexts via a dependency network representation,(ii) …
use of both preceding and following tag contexts via a dependency network representation,(ii) …
[PDF][PDF] Learning accurate, compact, and interpretable tree annotation
…, L Barrett, R Thibaux, D Klein - Proceedings of the 21st …, 2006 - aclanthology.org
We present an automatic approach to tree annotation in which basic nonterminal symbols are
alternately split and merged to maximize the likelihood of a training treebank. Starting with …
alternately split and merged to maximize the likelihood of a training treebank. Starting with …
Fast exact inference with a factored model for natural language parsing
D Klein, CD Manning - Advances in neural information …, 2002 - proceedings.neurips.cc
We present a novel generative model for natural language tree structures in which semantic
(lexical dependency) and syntactic (PCFG) structures are scored with separate models. This …
(lexical dependency) and syntactic (PCFG) structures are scored with separate models. This …
Learning dependency-based compositional semantics
Suppose we want to build a system that answers a natural language question by representing
its semantics as a logical forxm and computing the answer given a structured database of …
its semantics as a logical forxm and computing the answer given a structured database of …
[PDF][PDF] Learning semantic correspondences with less supervision
A central problem in grounded language acquisition is learning the correspondences between
a rich world state and a stream of text which references that world state. To deal with the …
a rich world state and a stream of text which references that world state. To deal with the …
[PDF][PDF] Improved inference for unlexicalized parsing
S Petrov, D Klein - … Technologies 2007: The Conference of the …, 2007 - aclanthology.org
We present several improvements to unlexicalized parsing with hierarchically state-split
PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarchical …
PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarchical …
[PDF][PDF] Corpus-based induction of syntactic structure: Models of dependency and constituency
D Klein, CD Manning - Proceedings of the 42nd annual meeting of …, 2004 - aclanthology.org
We present a generative model for the unsupervised learning of dependency structures. We
also describe the multiplicative combination of this dependency model with a model of …
also describe the multiplicative combination of this dependency model with a model of …
Calibrate before use: Improving few-shot performance of language models
GPT-3 can perform numerous tasks when provided a natural language prompt that contains
a few training examples. We show that this type of few-shot learning can be unstable: the …
a few training examples. We show that this type of few-shot learning can be unstable: the …