Filters








40 Hits in 6.1 sec

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight [article]

Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin
2020 arXiv   pre-print
In this paper, we propose a data manipulation framework to proactively reshape the data distribution towards reliable samples by augmenting and highlighting effective learning samples as well as reducing  ...  In particular, the data manipulation model selectively augments the training samples and assigns an importance weight to each instance to reform the training data.  ...  Acknowledgments We would like to thank all the reviewers for their insightful and valuable comments and suggestions.  ... 
arXiv:2004.02594v5 fatcat:yxg4fizbgndubh6y62q4sigagy

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight

Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
In this paper, we propose a data manipulation framework to proactively reshape the data distribution towards reliable samples by augmenting and highlighting effective learning samples as well as reducing  ...  In particular, the data manipulation model selectively augments the training samples and assigns an importance weight to each instance to reform the training data.  ...  Acknowledgments We would like to thank all the reviewers for their insightful and valuable comments and suggestions.  ... 
doi:10.18653/v1/2020.acl-main.564 fatcat:fyshulw2vzgdjbc4vexyvmhzii

A Survey of Data Augmentation Approaches for NLP [article]

Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy
2021 arXiv   pre-print
Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training  ...  Overall, our paper aims to clarify the landscape of existing literature in data augmentation for NLP and motivate additional work in this area.  ...  Data manipulation: Towards effective instance learning for neural dialogue generation via learning to aug- ment and reweight.  ... 
arXiv:2105.03075v5 fatcat:fplvosp5h5g5xk7n7yxm7ay7he

Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation [article]

Usama Yaseen, Stefan Langer
2021 arXiv   pre-print
In this work, we adapt backtranslation to generate high quality and linguistically diverse synthetic data for low-resource named entity recognition.  ...  The empirical results demonstrate the effectiveness of our proposed augmentation strategy, particularly in the low-resource scenario.  ...  Data manipulation: Towards effective instance learning for neural dialogue generation via learning to aug- ment and reweight.  ... 
arXiv:2108.11703v1 fatcat:m2ovl4rgizbtxphzeneuhjcouq

Pretrained Transformers for Text Ranking: BERT and Beyond

Andrew Yates, Rodrigo Nogueira, Jimmy Lin
2021 Proceedings of the 14th ACM International Conference on Web Search and Data Mining  
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query for a particular task.  ...  This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example.  ...  However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this survey also attempts to prognosticate where the  ... 
doi:10.1145/3437963.3441667 fatcat:6teqmlndtrgfvk5mneq5l7ecvq

Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification [article]

Shuhuai Ren, Jinchao Zhang, Lei Li, Xu Sun, Jie Zhou
2021 arXiv   pre-print
To overcome the above limitations, we propose a framework named Text AutoAugment (TAA) to establish a compositional and learnable paradigm for data augmentation.  ...  Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations.  ...  Acknowledgements We thank all the anonymous reviewers for their constructive comments, and Xuancheng Ren and Guangxiang Zhao for their valuable suggestions in preparing the manuscript.  ... 
arXiv:2109.00523v1 fatcat:wze5q7y4jzb4fiq34sqdmazhpe

Trustworthy AI: A Computational Perspective [article]

Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang
2021 arXiv   pre-print
Thus, trustworthy AI has attracted immense attention recently, which requires careful consideration to avoid the adverse effects that AI may bring to humans, so that humans can fully trust and live in  ...  We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.  ...  In [216] , it treats the neural dialogue model as a black-box and adopts a reinforcement learning framework to effectively find trigger inputs for targeted responses.  ... 
arXiv:2107.06641v3 fatcat:ymqaxvzsoncqrcosj5mxcvgsuy

Deep Reinforcement Learning: An Overview [article]

Yuxi Li
2018 arXiv   pre-print
After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn.  ...  Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, natural language processing, including dialogue systems, machine translation, and text generation, computer  ...  We have seen generation one dialogue systems: symbolic rule/template based, and generation two: data driven with (shallow) learning.  ... 
arXiv:1701.07274v6 fatcat:x2es3yf3crhqblbbskhxelxf2q

Discovering Invariant Rationales for Graph Neural Networks [article]

Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, Tat-Seng Chua
2022 arXiv   pre-print
Unfortunately, the leading rationalization models often rely on data biases, especially shortcut features, to compose rationales and make predictions without probing the critical and causal patterns.  ...  Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model prediction.  ...  We attribute such improvement to data augmentation via interventional distributions.  ... 
arXiv:2201.12872v1 fatcat:aaktipxdprbwtplkekzi366svu

Teaching Machines to Converse [article]

Jiwei Li
2020 arXiv   pre-print
Recently, the emergence of neural network models the potential to solve many of the problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural frameworks offer the promise  ...  Many systems learn generation rules from a minimal set of authored rules or labels on top of hand-coded rules or templates, and thus are both expensive and difficult to extend to open-domain scenarios.  ...  of feedback via data balancing and exploration, and how to make learning with real humans feasible via data batching.  ... 
arXiv:2001.11701v1 fatcat:ym74xbxnfrea7aaj7y5opnxopy

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research.  ...  With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  Therefore, how to effectively learn new data and meanwhile efficiently avoid forgetting old data is a major challenge for continual learning.  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

Multimodal Research in Vision and Language: A Review of Current and Emerging Trends [article]

Shagun Uppal, Sarthak Bhagat, Devamanyu Hazarika, Navonil Majumdar, Soujanya Poria, Roger Zimmermann, Amir Zadeh
2020 arXiv   pre-print
Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data.  ...  We look at its applications in their task formulations and how to solve various problems related to semantic perception and content generation.  ...  More recently, contrastive learning paradigms have accentuated the competency of self-supervised learning using data augmentations in vision-based applications like image classification.  ... 
arXiv:2010.09522v2 fatcat:l4npstkoqndhzn6hznr7eeys4u

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn.  ...  We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.  ...  PSRO/DCH generalizes previous algorithms, like independent RL, iterative best response, double oracle, and fictitious play.  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems [article]

Sergey Levine, Aviral Kumar, George Tucker, Justin Fu
2020 arXiv   pre-print
Effective offline reinforcement learning methods would be able to extract policies with the maximum possible utility out of the available data, thereby allowing automation of a wide range of decision-making  ...  Offline reinforcement learning algorithms hold tremendous promise for making it possible to turn large datasets into powerful decision making engines.  ...  A number of recent works have illustrated the power of such an approach in enabling data-driven learning of policies for dialogue (Jaques et al., 2019) , robotic manipulation behaviors (Ebert et al.,  ... 
arXiv:2005.01643v3 fatcat:kyw5xc4dijgz3dpuytnbcrmlam

Pretrained Transformers for Text Ranking: BERT and Beyond [article]

Jimmy Lin, Rodrigo Nogueira, Andrew Yates
2021 arXiv   pre-print
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query.  ...  There are two themes that pervade our survey: techniques for handling long documents, beyond typical sentence-by-sentence processing in NLP, and techniques for addressing the tradeoff between effectiveness  ...  Special thanks goes out to two anonymous reviewers for their insightful comments and helpful feedback.  ... 
arXiv:2010.06467v3 fatcat:obla6reejzemvlqhvgvj77fgoy
« Previous Showing results 1 — 15 out of 40 results