• Publications
  • Influence
Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization
TLDR
A novel abstractive model is proposed which is conditioned on the article’s topics and based entirely on convolutional neural networks, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans. Expand
Ranking Sentences for Extractive Summarization with Reinforcement Learning
TLDR
This paper conceptualize extractive summarization as a sentence ranking task and proposes a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. Expand
An Incremental Parser for Abstract Meaning Representation
TLDR
A transition-based parser for AMR that parses sentences left-to-right, in linear time is described and it is shown that this parser is competitive with the state of the art on the LDC2015E86 dataset and that it outperforms state-of-the-art parsers for recovering named entities and handling polarity. Expand
Split and Rephrase
TLDR
A new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences, which could be used as a preprocessing step which facilitates and improves the performance of parsers, semantic role labellers and machine translation systems. Expand
Stock Movement Prediction from Tweets and Historical Prices
TLDR
This work presents a novel deep generative model jointly exploiting text and price signals for stock movement prediction and introduces recurrent, continuous latent variables for a better treatment of stochasticity and uses neural variational inference to address the intractable posterior inference. Expand
Proceedings of NIPS
Logistic Normal Priors for Unsupervised Probabilistic Grammar Induction
TLDR
A new Bayesian model for probabilistic grammars is explored, exploiting the logistic normal distribution as a prior over the grammar parameters, and it is shown that the model achieves superior results over previous models that use different priors. Expand
Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance
We describe a method for prediction of linguistic structure in a language for which only unlabeled data is available, using annotated data from a set of one or more helper languages. Our approach isExpand
...
1
2
3
4
5
...