Filters








90,508 Hits in 5.1 sec

Continual Domain Adaptation for Machine Reading Comprehension [article]

Lixin Su, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Yanyan Lan, Xueqi Cheng
2020 pre-print
Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems.  ...  To tackle such a challenge, in this work, we introduce the Continual Domain Adaptation (CDA) task for MRC. So far as we know, this is the first study on the continual learning perspective of MRC.  ...  ., machine reading comprehension and continual learning. Then, we introduce various datasets for machine reading comprehension research in detail.  ... 
doi:10.1145/3340531.3412047 arXiv:2008.10874v1 fatcat:e7gbo4qndjejrlltyx23ddblqi

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

Zhijing Wu, Hua Xu, Jingliang Fang, Kai Gao
2022 Findings of the Association for Computational Linguistics: NAACL 2022   unpublished
Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC  ...  In this paper, MA-MRC, a continual MRC model with uncertainty-aware fixed Memory and Adversarial domain adaptation, is proposed.  ...  ., China Joint Research Center for Industrial Intelligence and Internet of Things.  ... 
doi:10.18653/v1/2022.findings-naacl.179 fatcat:2fsfjkbwpjhg7j77ybart3idgm

Task Transfer and Domain Adaptation for Zero-Shot Question Answering [article]

Xiang Pan, Alex Sheng, David Shimshoni, Aditya Singhal, Sara Rosenthal, Avirup Sil
2022 arXiv   pre-print
Our approach outperforms Domain-Adaptive Pretraining on downstream domain-specific reading comprehension tasks in 3 out of 4 domains.  ...  We evaluate zero-shot performance on domain-specific reading comprehension tasks by combining task transfer with domain adaptation to fine-tune a pretrained model with no labelled data from the target  ...  Acknowledgement We thank Sam Bowman for providing key feedback throughout our research.  ... 
arXiv:2206.06705v1 fatcat:wkwwzsnbxngj5g6nfjr7pfkwka

BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task [article]

Maria Mahbub, Sudarshan Srinivasan, Edmon Begoli, Gregory D Peterson
2022 arXiv   pre-print
We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in  ...  Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them.  ...  Figure 1 : 1 Figure 1: BioADAPT-MRC: an adversarial learning-based domain adaptation framework for biomedical machine reading comprehension task.  ... 
arXiv:2202.13174v2 fatcat:3ikhmt2dg5hohbu2wbshl3amw4

Machine Reading Comprehension-Enabled Public Service Information System: A Large-Scale Dataset and Neural Network Models

Changchang Zeng, Shaobo Li, Bin Chen, Mohammad Farukh Hashmi
2022 Wireless Communications and Mobile Computing  
Machine reading comprehension is a new research hotspot in the field of machine learning, which has great application potential in PSIS systems.  ...  In this paper, we explore the application of machine reading comprehension to the field of Chinese public service information systems from scratch.  ...  of machine reading comprehension (MRC) technology in PSIS systems will provide many advantages for public services.  ... 
doi:10.1155/2022/7088126 fatcat:bfrswwv4trhijphozqhavvxeoi

Page 1358 of Linguistics and Language Behavior Abstracts: LLBA Vol. 28, Issue 3 [page]

1994 Linguistics and Language Behavior Abstracts: LLBA  
/strategies differences, linear vs hypertext for- mat; experiments; 9404731 reading experiments, moving window generator use; effective visual field size measurement; college students; 9404755 reading/  ...  ; empirical data; English-speaking Spanish as a for- eign language learners; 9406084 Italian basic vocabulary database structure/fields content; 9406100 machine translation systems, evaluation metrics  ... 

Machine Reading at Scale: A Search Engine for Scientific and Academic Research

Norberto Sousa, Nuno Oliveira, Isabel Praça
2022 Systems  
It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents.  ...  In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research.  ...  In [38] , Cai et al. analyzed the claim that fine-tuning a model for reading comprehension, such as BERT, improves its results on more specific domains.  ... 
doi:10.3390/systems10020043 fatcat:z6pmelshpbfuvdsxe3m6xrejli

Book review on cognitive engineering and safety organization in air traffic management

Pietro Carlo Cacciabue
2018 Cognition, Technology & Work  
This is a very interesting book to read. It demonstrates why Cognitive Science is necessary for dealing with complex environments involving humans and machines.  ...  Therefore, this book is perfect for marrying the human-machine-interaction (HMI) issues of modern technology and domainspecific requirements.  ...  In essence, this book is certainly valuable for achieving a comprehensive view of the Cognitive Science aspects relevant for ATM and of the methods most commonly applied for problem-solving and assessment  ... 
doi:10.1007/s10111-018-0532-9 fatcat:p2d6sqc7prgvbncqcu5rzy2thm

End-to-End QA on COVID-19: Domain Adaptation with Synthetic Training [article]

Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan, Rong Zhang, Avi Sil, Vittorio Castelli, Radu Florian, Salim Roukos
2020 arXiv   pre-print
End-to-end question answering (QA) requires both information retrieval (IR) over a large document collection and machine reading comprehension (MRC) on the retrieved passages.  ...  Furthermore, given little or no labeled data, effective adaptation of QA systems can also be challenging in such target domains.  ...  Hence they must include both an information retrieval (IR) and a machine reading comprehension (MRC) component.  ... 
arXiv:2012.01414v1 fatcat:rq7l4dvycrbnvpvdujxokeqgoa

Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension [article]

Y. Xu, X. Zhong, A. J. J. Yepes, J. H. Lau
2020 arXiv   pre-print
The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results.  ...  We introduce new auxiliary penalty terms and observe the best performance when a combination of auxiliary penalty terms is used to regularise the fine-tuning process for adapting comprehension models.  ...  (Wiese, Weissenborn, and Neves 2017) explore supervised domain adaptation for reading comprehension, by pretraining their model first on large open-domain comprehension data and fine-tuning it further  ... 
arXiv:1911.00202v3 fatcat:rkhc5v2bkzflhdoww2u7mts3pq

From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap [article]

Shuyang Gao, Sanchit Agarwal, Tagyoung Chung, Di Jin, Dilek Hakkani-Tur
2020 arXiv   pre-print
More importantly, by leveraging machine reading comprehension datasets, our method outperforms the existing approaches by many a large margin in few-shot scenarios when the availability of in-domain data  ...  In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets.  ...  Accordingly, we propose two machine reading comprehension models for dialogue state tracking.  ... 
arXiv:2004.05827v1 fatcat:ybzyjysxenh4dp55yurmarviuu

Advances in Multi-turn Dialogue Comprehension: A Survey [article]

Zhuosheng Zhang, Hai Zhao
2021 arXiv   pre-print
Among these studies, the fundamental yet challenging type of task is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding.  ...  In this paper, we review the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task.  ...  machine reading comprehension , in which way we bridge the gap between the dialogue modeling and com-prehension, and hopefully benefit the future researches with the cutting-edge PrLMs.  ... 
arXiv:2110.04984v2 fatcat:4i4svd2oyvdhhasqx2ungtppue

Advances in Multi-turn Dialogue Comprehension: A Survey [article]

Zhuosheng Zhang, Hai Zhao
2021 arXiv   pre-print
Among these studies, the fundamental yet challenging type of task is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding.  ...  In this paper, we review the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task.  ...  machine reading comprehension , in which way we bridge the gap between the dialogue modeling and com-prehension, and hopefully benefit the future researches with the cutting-edge PrLMs.  ... 
arXiv:2103.03125v2 fatcat:62p6ase66jbhnhm77xlp5ulvre

Computer games for the teaching of reading

Alan M. Lesgold
1982 Behavior Research Methods  
Second, I discuss several issues of man-machine interaction that are particularly appropriate in building programs for people who do not read well.  ...  After that, I briefly address the issue of adapting to individual style differences.  ...  For example, perhaps the machine could pronounce any word the child touched. allowing the child to continue understanding text even if he is tripped up by a word or two.  ... 
doi:10.3758/bf03202157 fatcat:n5g62vrxozcndaqkos3553ie3u

Real-Time Scoring of an Oral Reading Assessment on Mobile Devices

Jian Cheng
2018 Interspeech 2018  
By combining features derived from word embedding with the normalized number of common types, we achieved a human-machine correlation coefficient of 0.90 at the participant level for comprehension scores  ...  We discuss the real-time scoring logic for a self-administered oral reading assessment on mobile devices (Moby.Read) to measure the three components of children's oral reading fluency skills: words correct  ...  Scoring of expression and comprehension will emphasize reading for meaning instead of reading for speed. Automatic scoring can reduce the need for teacher training and help ensure consistency.  ... 
doi:10.21437/interspeech.2018-34 dblp:conf/interspeech/Cheng18 fatcat:svdvngaoovc7rkhoievajhm5qy
« Previous Showing results 1 — 15 out of 90,508 results