paper-with-me

Papers

A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding

2021-08-01 · ACL 2021 5 · Khalil Mrini, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole

Users of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval. To alleviate this problem, we propose a novel Multi-Task Learning (MTL) method with data augmentation for medical question understanding. We first establish an equivalence between the tasks of question summarization and Recognizing Question Entailment (RQE) using their definitions in the medical domain. Based on this equivalence, we propose a data augmentation algorithm to use just one dataset to optimize for both tasks, with a weighted MTL loss. We introduce gradually soft parameter-sharing: a constraint for decoder parameters to be close, that is gradually loosened as we move to the highest layer. We show through ablation studies that our proposed novelties improve performance. Our method outperforms existing MTL methods across 4 datasets of medical question pairs, in ROUGE scores, RQE accuracy and human evaluation. Finally, we show that our method fares better than single-task learning under 4 low-resource settings.

📄 PDF Abstract BibTeX

Code (1)

khalilmrini/medical-question-understanding 공식 구현 pytorch

Tasks

Data AugmentationDecoderMedical Question AnsweringMulti-Task LearningQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

Immersive Language Exploration with Object Recognition and Augmented Reality

2020-05-01 · LREC 2020 5 · Benny Platte, Anett Platte, Christian Roschke, Rico Thomanek 외

The use of Augmented Reality (AR) in teaching and learning contexts for language is still young. The ideas are endless, the concrete educational offers available emerge only gradually. Educational opportunities that were…

ObjectObject Recognition

Planning-Augmented Sampling with Early Guidance for High-Reward Discovery

2025-10-01 · Rui Zhu, Yudong Zhang, Xuan Yu, Chen Zhang 외 arxiv

Generative Flow Networks (GFlowNets) enable structured generation with inherent diversity, but existing sampling strategies often rely on weak guided exploration, slowing early discovery of high-reward candidates. In tas…

Active Sample Selection and Correction Propagation on a Gradually-Augmented Graph

2015-06-01 · CVPR 2015 6 · Hang Su, Zhaozheng Yin, Takeo Kanade, Seungil Huh

When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small numb…

General Classification

Consolidated Adaptive T-soft Update for Deep Reinforcement Learning

2022-02-25 · Taisuke Kobayashi

Demand for deep reinforcement learning (DRL) is gradually increased to enable robots to perform complex tasks, while DRL is known to be unstable. As a technique to stabilize its learning, a target network that slowly and…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Generalization in Reinforcement Learning by Soft Data Augmentation

2020-11-26 · Nicklas Hansen, Xiaolong Wang

Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during tr…

Data Augmentationreinforcement-learningReinforcement LearningReinforcement Learning (RL)