Diana Inkpen

On the Softmax Bottleneck of Recurrent Language Models

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Recent research has pointed to a limitation of word-level neural language models with softmax outputs. This limitation, known as the softmax bottleneck refers to the inability of these models to produce high-rank log probability (log …

SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media

2023 · Natural Language Engineering

Abstract Anti-Asian speech during the COVID-19 pandemic has been a serious problem with severe consequences. A hate speech wave swept social media platforms. The timely detection of Anti-Asian COVID-19-related hate speech is of utmost importance, …

Enhanced LSTM for Natural Language Inference

2017

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data In this paper, we present a new state-of-the-art result, achieving …

Neural Natural Language Inference Models Enhanced with External Knowledge

2018

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve …