English
Related papers

Related papers: EdiT5: Semi-Autoregressive Text-Editing with T5 Wa…

200 papers

Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the former. Despite promising results, Seq2Edit approaches still…

Computation and Language · Computer Science 2023-10-13 Yu Zhang , Yue Zhang , Leyang Cui , Guohong Fu

Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…

Computation and Language · Computer Science 2022-05-11 Kostiantyn Omelianchuk , Vipul Raheja , Oleksandr Skurzhanskyi

Recent advances in Transformer-based Large Language Models have made great strides in natural language generation. However, to decode K tokens, an autoregressive model needs K sequential forward passes, which may be a performance bottleneck…

Computation and Language · Computer Science 2023-11-16 Mahmoud G. Salem , Jiayu Ye , Chu-Cheng Lin , Frederick Liu

We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding. Unlike the previous efforts (e.g., non-autoregressive decoding) speeding up seq2seq generation at the cost of quality loss, our…

Computation and Language · Computer Science 2022-05-23 Tao Ge , Heming Xia , Xin Sun , Si-Qing Chen , Furu Wei

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

We present Felix --- a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pre-training. In contrast to conventional…

Computation and Language · Computer Science 2020-03-25 Jonathan Mallinson , Aliaksei Severyn , Eric Malmi , Guillermo Garrido

Generating faithful and readable styled text images (especially for Styled Handwritten Text generation - HTG) is an open problem with several possible applications across graphic design, document understanding, and image editing. A lot of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Carmine Zaccagnino , Fabio Quattrini , Vittorio Pippi , Silvia Cascianelli , Alessio Tonioni , Rita Cucchiara

Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-11 Zhijun Liu , Shuai Wang , Sho Inoue , Qibing Bai , Haizhou Li

Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel…

Software Engineering · Computer Science 2022-09-15 Jiyang Zhang , Sheena Panthaplackel , Pengyu Nie , Junyi Jessy Li , Milos Gligoric

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as duration model, text encoder, and phoneme alignment, the text…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-21 Yushen Chen , Zhikang Niu , Ziyang Ma , Keqi Deng , Chunhui Wang , Jian Zhao , Kai Yu , Xie Chen

Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level…

Computation and Language · Computer Science 2025-04-03 Julie Kallini , Shikhar Murty , Christopher D. Manning , Christopher Potts , Róbert Csordás

Pre-trained encoder-decoder transformer architectures have become increasingly popular recently with the advent of T5 models. T5 has also become more favorable over other architectures like BERT due to the amount of data that it is…

Computation and Language · Computer Science 2022-10-25 Frederick Liu , Terry Huang , Shihang Lyu , Siamak Shakeri , Hongkun Yu , Jing Li

Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edit Flows, a non-autoregressive model that overcomes these…

Machine Learning · Computer Science 2025-11-13 Marton Havasi , Brian Karrer , Itai Gat , Ricky T. Q. Chen

There has been growing interest in automatically predicting missing type annotations in programs written in Python and JavaScript. While prior methods have achieved impressive accuracy when predicting the most common types, they often…

Software Engineering · Computer Science 2023-03-20 Jiayi Wei , Greg Durrett , Isil Dillig

Deep learning (DL) techniques are gaining more and more attention in the software engineering community. They have been used to support several code-related tasks, such as automatic bug fixing and code comments generation. Recent studies in…

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase…

Computation and Language · Computer Science 2019-09-04 Eric Malmi , Sebastian Krause , Sascha Rothe , Daniil Mirylenka , Aliaksei Severyn

Modern embedding-based metrics for evaluation of generated text generally fall into one of two paradigms: discriminative metrics that are trained to directly predict which outputs are of higher quality according to supervised human…

Computation and Language · Computer Science 2022-12-13 Yiwei Qin , Weizhe Yuan , Graham Neubig , Pengfei Liu

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in…

Computation and Language · Computer Science 2018-11-13 Jindřich Libovický , Jindřich Helcl

Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage. In this work, we propose a novel decoding…

Computation and Language · Computer Science 2024-03-25 Yunqi Zhu , Xuebing Yang , Yuanyuan Wu , Wensheng Zhang

Building huge and highly capable language models has been a trend in the past years. Despite their great performance, they incur high computational cost. A common solution is to apply model compression or choose light-weight architectures,…

Computation and Language · Computer Science 2022-03-03 Mohammad Akbari , Amin Banitalebi-Dehkordi , Yong Zhang
‹ Prev 1 2 3 10 Next ›