Search Results for author:
Found 6 papers, 2 papers with code
Learning GFlowNets from partial episodes for improved convergence and stability
Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks.
Do sequence-to-sequence VAEs learn global features of sentences?
Using this method, we find that VAEs are prone to memorizing the first words and the sentence length, producing local features of limited usefulness.
Auto-Encoding Dictionary Definitions into Consistent Word Embeddings
Monolingual dictionaries are widespread and semantically rich resources.
Learning to Compute Word Embeddings On the Fly
Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare.
Ranked #48 on
Question Answering
on SQuAD1.1 dev
Learning to Learn Neural Networks
In an experiment, we learn a learning algorithm for a one-hidden layer Multi-Layer Perceptron (MLP) on non-linearly separable datasets.
DART: a Dataset of Arguments and their Relations on Twitter
The problem of understanding the stream of messages exchanged on social media such as Facebook and Twitter is becoming a major challenge for automated systems.
