English
Related papers

Related papers: Levenshtein Transformer

200 papers

In the Levenshtein's sequence reconstruction problem a codeword is transmitted through $N$ channels and in each channel a set of errors is introduced to the transmitted word. In previous works, the restriction that each channel provides a…

Information Theory · Computer Science 2024-06-21 Ville Junnila , Tero Laihonen , Tuomo Lehtilä

Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…

Computation and Language · Computer Science 2022-03-07 Xiaoyu Shen

This paper presents a systematic survey on recent development of neural text generation models. Specifically, we start from recurrent neural network language models with the traditional maximum likelihood estimation training scheme and…

Computation and Language · Computer Science 2018-03-21 Sidi Lu , Yaoming Zhu , Weinan Zhang , Jun Wang , Yong Yu

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc…

Machine Learning · Computer Science 2019-02-25 Yingtao Tian , Jesse Engel

Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. However, current RNN models are ill-suited to process irregularly sampled data triggered by events generated in…

Machine Learning · Computer Science 2016-11-01 Daniel Neil , Michael Pfeiffer , Shih-Chii Liu

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…

Computation and Language · Computer Science 2022-04-14 Qingyang Wu , Zhenzhong Lan , Kun Qian , Jing Gu , Alborz Geramifard , Zhou Yu

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…

Computation and Language · Computer Science 2020-06-09 Dongling Xiao , Han Zhang , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang

The encoder-decoder based neural machine translation usually generates a target sequence token by token from left to right. Due to error propagation, the tokens in the right side of the generated sequence are usually of poorer quality than…

Computation and Language · Computer Science 2019-08-27 Xu Tan , Yingce Xia , Lijun Wu , Tao Qin

The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies. This work proposes an…

Computation and Language · Computer Science 2020-12-08 Yuntian Deng , Alexander M. Rush

Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant discrepancy between the reconstruction and generation…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Kai Qiu , Xiang Li , Hao Chen , Jason Kuen , Xiaohao Xu , Jiuxiang Gu , Yinyi Luo , Bhiksha Raj , Zhe Lin , Marios Savvides

We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence separately, our proposed framework utilizes both sequences…

Computation and Language · Computer Science 2019-06-05 Jihun Choi , Taeuk Kim , Sang-goo Lee

Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector. By contrast, Transformers have little inductive bias…

Machine Learning · Computer Science 2022-10-26 Aniket Didolkar , Kshitij Gupta , Anirudh Goyal , Nitesh B. Gundavarapu , Alex Lamb , Nan Rosemary Ke , Yoshua Bengio

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive…

Computation and Language · Computer Science 2023-11-14 Siyang Liu , Naihao Deng , Sahand Sabour , Yilin Jia , Minlie Huang , Rada Mihalcea

Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling…

Computation and Language · Computer Science 2020-05-29 Hendra Setiawan , Matthias Sperber , Udhay Nallasamy , Matthias Paulik

Retrieval-Augmented Machine Translation (RAMT) is attracting growing attention. This is because RAMT not only improves translation metrics, but is also assumed to implement some form of domain adaptation. In this contribution, we study…

Computation and Language · Computer Science 2023-10-16 Maxime Bouthors , Josep Crego , François Yvon

The Transformer translation model is easier to parallelize and provides better performance compared to recurrent seq2seq models, which makes it popular among industry and research community. We implement the Neutron in this work, including…

Computation and Language · Computer Science 2020-03-23 Hongfei Xu , Qiuhui Liu

We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage. We suggest four…

Computation and Language · Computer Science 2019-09-24 Amit Moryossef , Ido Dagan , Yoav Goldberg

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length.…

Computation and Language · Computer Science 2021-09-21 Jungo Kasai , Hao Peng , Yizhe Zhang , Dani Yogatama , Gabriel Ilharco , Nikolaos Pappas , Yi Mao , Weizhu Chen , Noah A. Smith

Dominant sequence models like the Transformer represent structure implicitly through dense attention weights, incurring quadratic complexity. We propose RewriteNets, a novel neural architecture built on an alternative paradigm: explicit,…

Machine Learning · Computer Science 2026-01-14 Harshil Vejendla