Model Architecture

Part-of-speech (POS) tag distributions are known to exhibit sparsity — a word is likely to take a single predominant tag in a corpus. Recent research has demonstrated that incor- porating …...

AbstractWhile state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, …...

AbstractIn this paper we demonstrate our (OPPO’s) machine translation systems for the WMT20 Shared Task on News Translation for all the 22 language pairs. We will give an overview of …...

AbstractDeep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to using them in …...

AbstractA large number of conflict events are affecting the world all the time. In order to analyse such conflict events effectively, this paper presents a Classification-Aware Neural Topic Model (CANTM-IA) …...