Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing最新文献

Meta-Learning for Few-Shot Named Entity Recognition 基于元学习的少镜头命名实体识别

Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.metanlp-1.6

Cyprien de Lichy, Hadrien Glaude, W. Campbell

引用次数: 9

Multi-Pair Text Style Transfer for Unbalanced Data via Task-Adaptive Meta-Learning 基于任务自适应元学习的非平衡数据多对文本风格迁移

Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.metanlp-1.4

Xing Han, J. Lundin

引用次数: 1

Semi-supervised Meta-learning for Cross-domain Few-shot Intent Classification 基于半监督元学习的跨域少射意图分类

Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.metanlp-1.8

Judith Yue Li, Jiong Zhang

{"title":"Semi-supervised Meta-learning for Cross-domain Few-shot Intent Classification","authors":"Judith Yue Li, Jiong Zhang","doi":"10.18653/v1/2021.metanlp-1.8","DOIUrl":"https://doi.org/10.18653/v1/2021.metanlp-1.8","url":null,"abstract":"Meta learning aims to optimize the model’s capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world few shot learning scenarios. Recent studies have proposed unsupervised approaches to create meta-training tasks from unlabeled data for free, e.g., the SMLMT method (Bansal et al., 2020a) constructs unsupervised multi-class classification tasks from the unlabeled text by randomly masking words in the sentence and let the meta learner choose which word to fill in the blank. This study proposes a semi-supervised meta-learning approach that incorporates both the representation power of large pre-trained language models and the generalization capability of prototypical networks enhanced by SMLMT. The semi-supervised meta training approach avoids overfitting prototypical networks on a small number of labeled training examples and quickly learns cross-domain task-specific representation only from a few supporting examples. By incorporating SMLMT with prototypical networks, the meta learner generalizes better to unseen domains and gains higher accuracy on out-of-scope examples without the heavy lifting of pre-training. We observe significant improvement in few-shot generalization after training only a few epochs on the intent classification tasks evaluated in a multi-domain setting.","PeriodicalId":171906,"journal":{"name":"Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing","volume":"2 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120816607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Meta-Reinforcement Learning for Mastering Multiple Skills and Generalizing across Environments in Text-based Games 在基于文本的游戏中掌握多种技能和跨环境推广的元强化学习

Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.metanlp-1.1

Zhenjie Zhao, Mingfei Sun, Xiaojuan Ma

{"title":"Meta-Reinforcement Learning for Mastering Multiple Skills and Generalizing across Environments in Text-based Games","authors":"Zhenjie Zhao, Mingfei Sun, Xiaojuan Ma","doi":"10.18653/v1/2021.metanlp-1.1","DOIUrl":"https://doi.org/10.18653/v1/2021.metanlp-1.1","url":null,"abstract":"Text-based games can be used to develop task-oriented text agents for accomplishing tasks with high-level language instructions, which has potential applications in domains such as human-robot interaction. Given a text instruction, reinforcement learning is commonly used to train agents to complete the intended task owing to its convenience of learning policies automatically. However, because of the large space of combinatorial text actions, learning a policy network that generates an action word by word with reinforcement learning is challenging. Recent research works show that imitation learning provides an effective way of training a generation-based policy network. However, trained agents with imitation learning are hard to master a wide spectrum of task types or skills, and it is also difficult for them to generalize to new environments. In this paper, we propose a meta reinforcement learning based method to train text agents through learning-to-explore. In particular, the text agent first explores the environment to gather task-specific information and then adapts the execution policy for solving the task with this information. On the publicly available testbed ALFWorld, we conducted a comparison study with imitation learning and show the superiority of our method.","PeriodicalId":171906,"journal":{"name":"Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116096856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2