47 citations · 51 across the 9 of their papers we have counts for
9 papers
IDAS: Intent Discovery with Abstractive Summarization
Maarten De Raedt, Fréderic Godin, Thomas Demeester +1
Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We sh…
Linear pretraining in recurrent mixture density networks
Hubert Normandin-Taillon, Frédéric Godin, Chun Wang
We present a method for pretraining a recurrent mixture density network (RMDN). We also propose a slight modification to the architecture of the RMDN-GARCH proposed by Nikolaev et…
Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals
Maarten De Raedt, Fréderic Godin, Chris Develder +1
For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on o…
A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders
Maarten De Raedt, Fréderic Godin, Pieter Buteneers +2
Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations.…
Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering
Fréderic Godin, Anjishnu Kumar, Arpit Mittal
In this paper, we investigate the challenges of using reinforcement learning agents for question-answering over knowledge graphs for real-world applications. We examine the perform…
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?
Fréderic Godin, Kris Demuynck, Joni Dambre +2
Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns th…
Predefined Sparseness in Recurrent Sequence Models
Thomas Demeester, Johannes Deleu, Fréderic Godin +1
Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is ty…
Improving Language Modeling using Densely Connected Recurrent Neural Networks
Fréderic Godin, Joni Dambre, Wesley De Neve
In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeli…
Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks
Fréderic Godin, Jonas Degrave, Joni Dambre +1
In this paper, we introduce a novel type of Rectified Linear Unit (ReLU), called a Dual Rectified Linear Unit (DReLU). A DReLU, which comes with an unbounded positive and negative…