English
Related papers

Related papers: Transformers as Neural Augmentors: Class Condition…

200 papers

In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we…

Computation and Language · Computer Science 2018-07-05 Yutai Hou , Yijia Liu , Wanxiang Che , Ting Liu

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…

Computer Vision and Pattern Recognition · Computer Science 2017-10-31 Toan Tran , Trung Pham , Gustavo Carneiro , Lyle Palmer , Ian Reid

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

Computation and Language · Computer Science 2021-04-19 Akhila Yerukola , Mason Bretan , Hongxia Jin

A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model…

Sound · Computer Science 2024-03-26 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka

There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher…

Computation and Language · Computer Science 2021-04-13 Nandan Thakur , Nils Reimers , Johannes Daxenberger , Iryna Gurevych

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Computation and Language · Computer Science 2025-09-09 Manuel Frank , Haithem Afli

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned on both a short…

Computation and Language · Computer Science 2019-11-25 Xinyi Wang , Jason Weston , Michael Auli , Yacine Jernite

The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of…

Computation and Language · Computer Science 2021-03-12 Baolin Peng , Chenguang Zhu , Michael Zeng , Jianfeng Gao

Significant advances are being made in speech emotion recognition (SER) using deep learning models. Nonetheless, training SER systems remains challenging, requiring both time and costly resources. Like many other machine learning tasks,…

Sound · Computer Science 2023-09-18 Tiantian Feng , Shrikanth Narayanan

The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets, facilitating the accurate classification of modulation…

Machine Learning · Computer Science 2023-11-08 Tao Chen , Shilian Zheng , Kunfeng Qiu , Luxin Zhang , Qi Xuan , Xiaoniu Yang

Text classification is a representative downstream task of natural language processing, and has exhibited excellent performance since the advent of pre-trained language models based on Transformer architecture. However, in pre-trained…

Computation and Language · Computer Science 2022-04-07 Byeong-Cheol Jo , Tak-Sung Heo , Yeongjoon Park , Yongmin Yoo , Won Ik Cho , Kyungsun Kim

Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…

Computation and Language · Computer Science 2023-10-17 Dustin Axman , Avik Ray , Shubham Garg , Jing Huang

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

As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the…

Computation and Language · Computer Science 2023-03-20 Xiuying Chen , Mingzhe Li , Jiayi Zhang , Xiaoqiang Xia , Chen Wei , Jianwei Cui , Xin Gao , Xiangliang Zhang , Rui Yan

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work…

Computation and Language · Computer Science 2020-03-31 Zhaojiang Lin , Genta Indra Winata , Peng Xu , Zihan Liu , Pascale Fung

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

Computation and Language · Computer Science 2020-06-03 Shi-Yan Weng , Tien-Hong Lo , Berlin Chen

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

Computation and Language · Computer Science 2019-08-22 Rongxiang Weng , Heng Yu , Shujian Huang , Weihua Luo , Jiajun Chen

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Computation and Language · Computer Science 2021-07-05 Yu Shi

We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training…

Computation and Language · Computer Science 2020-05-20 Jacob Andreas

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-21 Vahid Noroozi , Zhehuai Chen , Somshubra Majumdar , Steve Huang , Jagadeesh Balam , Boris Ginsburg