English
Related papers

Related papers: A Framework for Bidirectional Decoding: Case Study…

200 papers

We present an algorithm for error correction in topological codes that exploits modern machine learning techniques. Our decoder is constructed from a stochastic neural network called a Boltzmann machine, of the type extensively used in deep…

Quantum Physics · Physics 2017-07-20 Giacomo Torlai , Roger G. Melko

Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design…

Machine Learning · Computer Science 2020-02-03 Antonio Carta , Alessandro Sperduti , Davide Bacciu

In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the…

Computation and Language · Computer Science 2019-07-19 Gongbo Tang , Rico Sennrich , Joakim Nivre

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information…

Computation and Language · Computer Science 2018-06-14 Junyang Lin , Xu Sun , Shuming Ma , Qi Su

While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical…

Computation and Language · Computer Science 2022-06-28 Klaudia-Doris Thellmann , Bernhard Stadler , Ricardo Usbeck , Jens Lehmann

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

Computation and Language · Computer Science 2026-01-15 Giorgio Franceschelli , Mirco Musolesi

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens…

Sound · Computer Science 2021-01-08 Wen-Yi Hsiao , Jen-Yu Liu , Yin-Cheng Yeh , Yi-Hsuan Yang

We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the…

Computation and Language · Computer Science 2019-09-25 Ekin Akyürek , Erenay Dayanık , Deniz Yuret

Masked diffusion language models (MDLMs) are trained to in-fill positions in randomly masked sequences, in contrast to next-token prediction models. Discussions around MDLMs focus on two benefits: (1) any-order decoding and 2) multi-token…

Machine Learning · Computer Science 2025-10-24 Zachary Horvitz , Raghav Singhal , Hao Zou , Carles Domingo-Enrich , Zhou Yu , Rajesh Ranganath , Kathleen McKeown

This paper proposes a novel bidirectional neural vocoder, named BiVocoder, capable both of feature extraction and reverse waveform generation within the short-time Fourier transform (STFT) domain. For feature extraction, the BiVocoder takes…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Hui-Peng Du , Ye-Xin Lu , Yang Ai , Zhen-Hua Ling

Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods. It's obvious that the quality of the semantic representations from encoding is very…

Computation and Language · Computer Science 2020-01-15 Boyuan Pan , Yazheng Yang , Zhou Zhao , Yueting Zhuang , Deng Cai

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…

Machine Learning · Computer Science 2024-05-17 Tsuyoshi Idé , Jokin Labaien , Pin-Yu Chen

Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…

Computation and Language · Computer Science 2023-03-15 Kamil Bujel , Andrew Caines , Helen Yannakoudakis , Marek Rei

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…

Computation and Language · Computer Science 2022-03-16 Xiangyang Mou , Mo Yu , Bingsheng Yao , Lifu Huang

The large language model (LLM) community focuses almost exclusively on decoder-only language models, since they are easier to use for text generation. However, a large subset of the community still uses encoder-only models for tasks such as…

Computation and Language · Computer Science 2026-03-13 Orion Weller , Kathryn Ricci , Marc Marone , Antoine Chaffin , Dawn Lawrie , Benjamin Van Durme

We explore the task of multi-source morphological reinflection, which generalizes the standard, single-source version. The input consists of (i) a target tag and (ii) multiple pairs of source form and source tag for a lemma. The motivation…

Computation and Language · Computer Science 2017-01-24 Katharina Kann , Ryan Cotterell , Hinrich Schütze

This paper presents a new sequence-to-sequence (seq2seq) pre-training method PoDA (Pre-training of Denoising Autoencoders), which learns representations suitable for text generation tasks. Unlike encoder-only (e.g., BERT) or decoder-only…

Computation and Language · Computer Science 2019-08-23 Liang Wang , Wei Zhao , Ruoyu Jia , Sujian Li , Jingming Liu

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

Computation and Language · Computer Science 2017-10-31 Sharath T. S. , Shubhangi Tandon , Ryan Bauer

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Computation and Language · Computer Science 2020-11-20 John Wieting , Graham Neubig , Taylor Berg-Kirkpatrick