paper-with-me

Papers

Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification

2020-09-08 · PACLIC 2020 10 · Samuel Louvan, Bernardo Magnini

Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive. We show that lightweight augmentation, a set of augmentation methods involving word span and sentence level operations, alleviates data scarcity problems. Our experiments on limited data settings show that lightweight augmentation yields significant performance improvement on slot filling on the ATIS and SNIPS datasets, and achieves competitive performance with respect to more complex, state-of-the-art, augmentation approaches. Furthermore, lightweight augmentation is also beneficial when combined with pre-trained LM-based models, as it improves BERT-based joint intent and slot filling models.

📄 PDF Abstract BibTeX arXiv:2009.03695

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGeneral Classificationintent-classificationIntent ClassificationSentenceslot-fillingSlot Filling

Similar Papers 제목 키워드 기반

Improving Micro-Expression Recognition with Phase-Aware Temporal Augmentation

2025-10-17 · Vu Tram Anh Khuong, Luu Tu Nguyen, Thanh Ha Le, Thi Duyen Ngo arxiv

Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, typically lasting less than half a second. Recognizing these subtle expressions is critical for applications in psychology, se…

Micro-Expression Recognition

A Lightweight Method to Generate Unanswerable Questions in English

2023-10-30 · Vagrant Gautam, Miaoran Zhang, Dietrich Klakow

If a question cannot be answered with the available information, robust systems for question answering (QA) should know _not_ to answer. One way to build QA models that do this is with additional training data comprised …

Data AugmentationQuestion AnsweringQuestion GenerationQuestion-Generation

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

2026-03-04 · Youngwon Choi, Jinwoo Oh, Hwayeon Kim, Hyeonyu Kim arxiv

We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically dive…

Data AugmentationSpeech Synthesis

Augment your batch: better training with larger batches

2019-01-27 · Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi 외

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: rep…

MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition

2021-02-25 · Linghui Meng, Jin Xu, Xu Tan, Jindong Wang 외

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognition+1