Developing artificial learning systems that can understand and generate natural language
has been one of the long-standing goals of artificial intelligence. Recent decades have …

Generating texts with a large language model (LLM) consumes massive amounts of
memory. Apart from the already-large model parameters, the key/value (KV) cache that …

Attention-based neural machine translation (NMT) models selectively focus on specific
source positions to produce a translation, which brings significant improvements over pure …

In this paper, we aim to create weak alignment supervision to aid the end-to-end modeling.
Towards this end, we use the existing hybrid ASR system to produce triphone alignments of …

Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been
proposed for bi/multilingual text-to-speech systems. Although they have achieved great …

Neural Machine Translation (NMT) is known to suffer from a beam-search problem: after a
certain point, increasing beam size causes an overall drop in translation quality. This effect …

A language can be described by its rules or its symbols. Making computers understand
sentences or words written in human languages is the goal of natural language processing …

Label smoothing is ubiquitously applied in Neural Machine Translation (NMT) training.
While label smoothing offers a desired regularization effect during model training, in this …

Neural machine translation often suffers from an under-translation problem owing to its
limited modeling of the output sequence lengths. In this study, we propose a novel approach …

Natural Language Processing (NLP) is defined as a method for computers to intelligently
analyze, understand, and derive meaning from human language. Machine translation is a …