Related papers: Character Transformations for Non-Autoregressive G…
In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translation model, to…
Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…
Foundation models trained with self-supervised objectives are increasingly applied to brain recordings, but autoregressive generation of realistic multichannel neural time series remains comparatively underexplored, particularly for…
Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…
Due to advances in Large Language Models (LLMs) such as ChatGPT, the boundary between human-written text and AI-generated text has become blurred. Nevertheless, recent work has demonstrated that it is possible to reliably detect…
Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance degradation. This vulnerability primarily stems from the…
Although existing neural network approaches have achieved great success on Chinese spelling correction, there is still room to improve. The model is required to avoid over-correction and to distinguish a correct token from its phonological…
Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with…
This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a…
Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn…
Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented…
Neural Machine Translation (NMT) on logographic source languages struggles when translating `unseen' characters, which never appear in the training data. One possible approach to this problem uses sub-character decomposition for training…
Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve…
This article proposes to auto-encode text at byte-level using convolutional networks with a recursive architecture. The motivation is to explore whether it is possible to have scalable and homogeneous text generation at byte-level in a…
Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…
Error correction codes (ECC) are crucial for ensuring reliable information transmission in communication systems. Choukroun & Wolf (2022b) recently introduced the Error Correction Code Transformer (ECCT), which has demonstrated promising…
Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint…
Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system makes a certain correction, the causes of errors (evidence…
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…