paper-with-me

Papers

Byte-Level Recursive Convolutional Auto-Encoder for Text

2018-02-06 · ICLR 2018 1 · Xiang Zhang, Yann Lecun

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 non-sequential fashion through the simple task of auto-encoding. We show that non-sequential text generation from a fixed-length representation is not only possible, but also achieved much better auto-encoding results than recurrent networks. The proposed model is a multi-stage deep convolutional encoder-decoder framework using residual connections, containing up to 160 parameterized layers. Each encoder or decoder contains a shared group of modules that consists of either pooling or upsampling layers, making the network recursive in terms of abstraction levels in representation. Results for 6 large-scale paragraph datasets are reported, in 3 languages including Arabic, Chinese and English. Analyses are conducted to study several properties of the proposed model.

📄 PDF Abstract BibTeX arXiv:1802.01817

Code (1)

smalik169/recursive-convolutional-autoencoder pytorch

Tasks

DecoderText Generation

Similar Papers 제목 키워드 기반

Efficient Purely Convolutional Text Encoding

2018-08-03 · Szymon Malik, Adrian Lancucki, Jan Chorowski

In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our wo…

Optimizing Byte-level Representation for End-to-end ASR

2024-06-14 · Roger Hsiao, Liuhui Deng, Erik McDermott, Ruchir Travadi 외

We propose a novel approach to optimizing a byte-level representation for end-to-end automatic speech recognition (ASR). Byte-level representation is often used by large scale multilingual ASR systems when the character …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Quantizationspeech-recognition+1

Neural Machine Translation in Linear Time

2016-10-31 · Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan, Aaron van den Oord 외

We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the targe…

DecoderLanguage ModellingMachine TranslationMemorization+1

On the Properties of Neural Machine Translation: Encoder-Decoder Approaches

2014-09-03 · Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, Yoshua Bengio

Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder ext…

DecoderMachine TranslationSentenceTranslation

Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision

2023-11-04 · Aditya Malusare, Harish Kothandaraman, Dipesh Tamboli, Nadia A. Lanman 외

This paper presents the Ensemble Nucleotide Byte-level Encoder-Decoder (ENBED) foundation model, analyzing DNA sequences at byte-level precision with an encoder-decoder Transformer architecture. ENBED uses a sub-quadrati…

DecoderLanguage ModelingLanguage ModellingMasked Language Modeling