• Publications
  • Influence
Three New Probabilistic Models for Dependency Parsing: An Exploration
TLDR
Preliminary empirical results from evaluating the three models' parsing performance on annotated Wall Street Journal training text (derived from the Penn Treebank) suggest the generative model performs significantly better than the others, and does about equally well at assigning part-of-speech tags.
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
TLDR
This generative model allows past events to influence the future in complex and realistic ways, by conditioning future event intensities on the hidden state of a recurrent neural network that has consumed the stream of past events.
Using “Annotator Rationales” to Improve Machine Learning for Text Categorization
TLDR
It is hypothesize that in some situations, providing rationales is a more fruitful use of an annotator's time than annotating more examples, and presents a learning method that exploits the rationales during training to boost performance significantly on a sample task, namely sentiment classification of movie reviews.
The SIGMORPHON 2016 Shared Task—Morphological Reinflection
TLDR
The 2016 SIGMORPHON Shared Task was devoted to the problem of morphological reinflection and introduced morphological datasets for 10 languages with diverse typological characteristics, showing a strong state of the art.
Contrastive Estimation: Training Log-Linear Models on Unlabeled Data
TLDR
A novel approach, contrastive estimation, is described, which outperforms EM, is more robust to degradations of the dictionary, and can largely recover by modeling additional features.
Learning to Search in Branch and Bound Algorithms
TLDR
This work addresses the key challenge of learning an adaptive node searching order for any class of problem solvable by branch-and-bound by applying its algorithm to linear programming based branch- and-bound for solving mixed integer programs (MIP).
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests
TLDR
A novel second-order expectation semiring is introduced, which computes second- order statistics and is essential for many interesting training paradigms such as minimum risk, deterministic annealing, active learning, and semi-supervised learning, where gradient descent optimization requires computing the gradient of entropy or risk.
Learning Non-Isomorphic Tree Mappings for Machine Translation
TLDR
This work reformulates synchronous TSG to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.
...
1
2
3
4
5
...