Related papers: Generative Pretrained Structured Transformers: Uns…

Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without…

Pre-trained Language Models (PLMs), such as ChatGPT, have significantly advanced the field of natural language processing. This progress has inspired a series of innovative studies that explore the adaptation of PLMs to time series…

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to…

Unsupervised neural machine translation(NMT) is associated with noise and errors in synthetic data when executing vanilla back-translations. Here, we explicitly exploits language model(LM) to drive construction of an unsupervised NMT…

Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional…

Although Large Language Models (LLMs) excel at addressing straightforward reasoning tasks, they frequently struggle with difficulties when confronted by more complex multi-step reasoning due to a range of factors. Firstly, natural language…

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion…

Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable…

We challenge the prevailing assumption that LLMs must rely fully on sub-word tokens for high-quality text generation. To this end, we propose the "Generative Pretrained Thoughtformer" (GPTHF), a hierarchical transformer language model…

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Syntactic structure of a sentence text is correlated with the prosodic structure of the speech that is crucial for improving the prosody and naturalness of a text-to-speech (TTS) system. Nowadays TTS systems usually try to incorporate…

Text generation has become one of the most important yet challenging tasks in natural language processing (NLP). The resurgence of deep learning has greatly advanced this field by neural generation models, especially the paradigm of…

The mathematical formula is the human language to describe nature and is the essence of scientific research. Finding mathematical formulas from observational data is a major demand of scientific research and a major challenge of artificial…

Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often…

In this paper, we propose a new paradigm for paraphrase generation by treating the task as unsupervised machine translation (UMT) based on the assumption that there must be pairs of sentences expressing the same meaning in a large-scale…

Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. In this paper, we introduce a lightweight, modular SLT framework, Spotter+GPT, that leverages the power of…