paper-with-me

홈 › Papers

Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading

2021-06-08 · Hoang Van, Vikas Yadav, Mihai Surdeanu

We propose a simple and effective strategy for data augmentation for low-resource machine reading comprehension (MRC). Our approach first pretrains the answer extraction components of a MRC system on the augmented data that contains approximate context of the correct answers, before training it on the exact answer spans. The approximate context helps the QA method components in narrowing the location of the answers. We demonstrate that our simple strategy substantially improves both document retrieval and answer extraction performance by providing larger context of the answers and additional training data. In particular, our method significantly improves the performance of BERT based retriever (15.12\%), and answer extractor (4.33\% F1) on TechQA, a complex, low-resource MRC task. Further, our data augmentation strategy yields significant improvements of up to 3.9\% exact match (EM) and 2.7\% F1 for answer extraction on PolicyQA, another practical but moderate sized QA dataset that also contains long answer spans.

📄 PDF Abstract BibTeX arXiv:2106.04134

Code (1)

vanh17/techqa 공식 구현 pytorch

Tasks

Data AugmentationMachine Reading ComprehensionReading ComprehensionRetrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Adam 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

2023-10-03 · NeurIPS 2023 11 · Chanakya Ekbote, Ajinkya Pankaj Deshpande, Arun Iyer, Ramakrishna Bairi 외

Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that mimic low-pass filters, limiting their …

Contrastive Learning

Effective Data Augmentation for Sentence Classification Using One VAE per Class

2022-10-01 · COLING 2022 10 · Frédéric Piedboeuf, Philippe Langlais

In recent years, data augmentation has become an important field of machine learning. While images can use simple techniques such as cropping or rotating, textual data augmentation needs more complex manipulations to ens…

Binary ClassificationData AugmentationSentenceSentence Classification

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment

2024-11-05 · Jason Vega, Junsheng Huang, Gaokai Zhang, Hangoo Kang 외

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through vario…

QuantizationSafety Alignment

PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization

2022-12-02 · ICCV 2023 1 · Prithvijit Chattopadhyay, Kartik Sarangmath, Vivek Vijaykumar, Judy Hoffman

Synthetic data offers the promise of cheap and bountiful training data for settings where labeled real-world data is scarce. However, models trained on synthetic data significantly underperform when evaluated on real-wor…

Domain Generalizationobject-detectionObject DetectionObject Recognition+1

Good-Enough Example Extrapolation

2021-09-12 · EMNLP 2021 11 · Jason Wei

This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data a…

Data AugmentationInductive Biastext-classificationText Classification+1