Filters








10,152 Hits in 4.6 sec

Separating Answers from Queries for Neural Reading Comprehension [article]

Dirk Weissenborn
2016 arXiv   pre-print
We present a novel neural architecture for answering queries, designed to optimally leverage explicit support in the form of query-answer memories.  ...  On recent benchmark datasets for reading comprehension, our model achieves state-of-the-art results.  ...  Acknowledgments We thank Thomas Demeester, Thomas Werkmeister, Sebastian Krause, Tim Rocktäschel and Sebastian Riedel for their comments on an early draft of this work.  ... 
arXiv:1607.03316v3 fatcat:lmyfzbkmcfg2zj34fc5wmn5owu

Consensus Attention-based Neural Networks for Chinese Reading Comprehension [article]

Yiming Cui, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu
2018 arXiv   pre-print
Also, we propose a consensus attention-based neural network architecture to tackle the Cloze-style reading comprehension problem, which aims to induce a consensus attention over every words in the query  ...  Furthermore, we setup a baseline for Chinese reading comprehension task, and hopefully this would speed up the process for future research.  ...  Acknowledgements We would like to thank the anonymous reviewers for their thorough reviewing and proposing thoughtful comments to improve our paper.  ... 
arXiv:1607.02250v3 fatcat:og73ebwwhffzvkggzzx3xtuhne

Reasoning with Memory Augmented Neural Networks for Language Comprehension [article]

Tsendsuren Munkhdalai, Hong Yu
2017 arXiv   pre-print
We apply the proposed approach to language comprehension task by using Neural Semantic Encoders (NSE).  ...  In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks.  ...  ACKNOWLEDGMENTS We would like to thank Abhyuday Jagannatha, Jesse Lingeman and the reviewers for their insightful comments and suggestions.  ... 
arXiv:1610.06454v2 fatcat:oqrccebymzetfcs3c554qn3duq

Dataset for the First Evaluation on Chinese Machine Reading Comprehension [article]

Yiming Cui, Ting Liu, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu
2018 arXiv   pre-print
To add diversity in reading comprehension datasets, in this paper we propose a new Chinese reading comprehension dataset for accelerating related research in the community.  ...  The proposed dataset contains two different types: cloze-style reading comprehension and user query reading comprehension, associated with large-scale training data as well as human-annotated validation  ...  We thank the Sixteenth China National Conference on Computational Linguistics (CCL 2017) and Nanjing Normal University for providing space for evaluation workshop.  ... 
arXiv:1709.08299v2 fatcat:wwfwkc7725akxkuv6blogjdtsi

Teaching Machines to Read and Comprehend [article]

Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom
2015 arXiv   pre-print
This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.  ...  for this type of evaluation.  ...  Our first neural model for reading comprehension tests the ability of Deep LSTM encoders to handle significantly longer sequences.  ... 
arXiv:1506.03340v3 fatcat:6qdst7ekxrcflobqjpfhscn7iq

Iterative Alternating Neural Attention for Machine Reading [article]

Alessandro Sordoni and Philip Bachman and Adam Trischler and Yoshua Bengio
2016 arXiv   pre-print
We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document.  ...  Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the  ...  Our architecture deploys a novel alternating attention mechanism, and tightly integrates successful ideas from past works in machine reading comprehension to obtain state-of-the-art results on three datasets  ... 
arXiv:1606.02245v4 fatcat:j4qxnjewbfawpog4l5xdvtkgwy

CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension [article]

Simon Šuster, Walter Daelemans
2018 arXiv   pre-print
We present a new dataset for machine comprehension in the medical domain. Our dataset uses clinical case reports with around 100,000 gap-filling queries about these cases.  ...  We analyze the skills required for successful answering and show how reader performance varies depending on the applicable skills.  ...  Acknowledgments We would like to thank Madhumita Sushil and the anonymous reviewers for useful comments. We are also grateful to BMJ Case Reports for allowing the collection of case reports.  ... 
arXiv:1803.09720v1 fatcat:vbgvcjt4lrbqrpzxfomamumuky

CliCR: a Dataset of Clinical Case Reports for Machine Reading Comprehension

Simon Suster, Walter Daelemans
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
We present a new dataset for machine comprehension in the medical domain. Our dataset uses clinical case reports with around 100,000 gap-filling queries about these cases.  ...  We analyze the skills required for successful answering and show how reader performance varies depending on the applicable skills.  ...  Acknowledgments We would like to thank Madhumita Sushil and the anonymous reviewers for useful comments. We are also grateful to BMJ Case Reports for allowing the collection of case reports.  ... 
doi:10.18653/v1/n18-1140 dblp:conf/naacl/SusterD18 fatcat:ve32i5ptyrdzzfztshhypqi2jq

WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval [article]

Daniel Cohen, Liu Yang, W. Bruce Croft
2018 arXiv   pre-print
With the rise in mobile and voice search, answer passage retrieval acts as a critical component of an effective information retrieval system for open domain question answering.  ...  In this paper, we introduce a new Wikipedia based collection specific for non-factoid answer passage retrieval containing thousands of questions with annotated answers and show benchmark results on a variety  ...  ACKNOWLEDGEMENTS This work was supported in part by the Center for Intelligent Information Retrieval, in part by NSF #IIS-1160894, and in part by NSF grant #IIS-1419693.  ... 
arXiv:1805.03797v1 fatcat:q3a6yszqbnc7tgtjbtr6nrgvnq

Enhancing Machine Reading Comprehension with Position Information

Yajing Xu, Weijie Liu, Guang Chen, Boya Ren, Siman Zhang, Sheng Gao, Jun Guo
2019 IEEE Access  
Therefore, the position information may be helpful in finding the answer rapidly and is useful for reading comprehension.  ...  When people do the reading comprehension, they often try to find the words from the passages which are similar to the question words first.  ...  Benefiting from the introduction of many large datasets, machine reading comprehension neural model made rapid progress in recently.  ... 
doi:10.1109/access.2019.2930407 fatcat:fw2cabd6evamxcotnsdsmwi6ja

The NarrativeQA Reading Comprehension Challenge [article]

Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gábor Melis, Edward Grefenstette
2017 arXiv   pre-print
To encourage progress on deeper comprehension of language, we present a new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts.  ...  Question answering is conventionally used to assess RC ability, in both artificial agents and children learning to read.  ...  A common strategy for assessing the language understanding capabilities of comprehension models is to demonstrate that they can answer questions about documents they read, akin to how reading comprehension  ... 
arXiv:1712.07040v1 fatcat:4vjf4yx6f5gadjpynnxb2mrp5y

The NarrativeQA Reading Comprehension Challenge

Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gáabor Melis, Edward Grefenstette
2018 Transactions of the Association for Computational Linguistics  
To encourage progress on deeper comprehension of language, we present a new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts.  ...  Question answering is conventionally used to assess RC ability, in both artificial agents and children learning to read.  ...  A common strategy for assessing the language understanding capabilities of comprehension models is to demonstrate that they can answer questions about documents they read, akin to how reading comprehension  ... 
doi:10.1162/tacl_a_00023 fatcat:nuieq445d5ao5ndvm5hburluty

Dependent Gated Reading for Cloze-Style Question Answering [article]

Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi, Prasad Tadepalli
2018 arXiv   pre-print
Existing approaches employ reading mechanisms that do not fully exploit the interdependency between the document and the query.  ...  In this paper, we propose a novel dependent gated reading bidirectional GRU network (DGR) to efficiently model the relationship between the document and the query during encoding and decision making.  ...  Attention-over-attention neural networks for reading comprehension.  ... 
arXiv:1805.10528v2 fatcat:cg6kv3h6tzbajfxtefnp35deyu

Entity Tracking Improves Cloze-style Reading Comprehension

Luong Hoang, Sam Wiseman, Alexander Rush
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Reading comprehension tasks test the ability of models to process long-term context and remember salient information.  ...  Recent work has shown that relatively simple neural methods such as the Attention Sum-Reader can perform well on these tasks; however, these systems still significantly trail human performance.  ...  Related Work The first popular neural network reading comprehension models were the Attentive Reader and its variant Impatient Reader (Hermann et al., 2015) .  ... 
doi:10.18653/v1/d18-1130 dblp:conf/emnlp/HoangWR18 fatcat:qy7zp2htwvh4fcxtingaubmcee

Entity Tracking Improves Cloze-style Reading Comprehension [article]

Luong Hoang, Sam Wiseman, Alexander M. Rush
2018 arXiv   pre-print
Reading comprehension tasks test the ability of models to process long-term context and remember salient information.  ...  Recent work has shown that relatively simple neural methods such as the Attention Sum-Reader can perform well on these tasks; however, these systems still significantly trail human performance.  ...  Related Work The first popular neural network reading comprehension models were the Attentive Reader and its variant Impatient Reader (Hermann et al., 2015) .  ... 
arXiv:1810.02891v1 fatcat:gwl7seembvd3hmofrnmtllga3q
« Previous Showing results 1 — 15 out of 10,152 results