activity
20152026
most citeddeltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

95 citations · 318 across the 35 of their papers we have counts for

collaborators
Showing 2018Show all

7 papers · 1 filter

cs.LG2018

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes +3

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understa…

cs.CL2018

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

Yikang Shen, Shawn Tan, Alessandro Sordoni +1

Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger constituent ends, all of the smaller cons…

cs.LG2018

VFunc: a Deep Generative Model for Functions

Philip Bachman, Riashat Islam, Alessandro Sordoni +1

We introduce a deep generative model for functions. Our model provides a joint distribution p(f, z) over functions f and latent variables z which lets us efficiently sample from th…

stat.ML2018

Focused Hierarchical RNNs for Conditional Sequence Processing

Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni +6

Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of enco…

cs.CL2018

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Yikang Shen, Zhouhan Lin, Athul Paul Jacob +3

In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input se…

cs.CL2018

Counting to Explore and Generalize in Text-based Games

Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni +4

We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. We show promising results on a set of g…