A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
[article]
2019
arXiv
pre-print
Preserved Fulltext
Other Versions
In this work, we propose the Coarse-grain Fine-grain Coattention Network (CFC), a new question answering model that combines information from evidence across multiple documents. ...
The CFC consists of a coarse-grain module that interprets documents with respect to the query then finds a relevant answer, and a fine-grain module which scores each candidate answer by comparing its occurrences ...
ACKNOWLEDGEMENT The authors thank Luke Zettlemoyer for his feedback and advice and Sewon Min for her help in preprocessing the TriviaQA dataset. ...
arXiv:1901.00603v2
fatcat:lrj7qkfmtrbazhixas4x4eigrm
XTQA: Span-Level Explanations of the Textbook Question Answering
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.12662v2 fatcat:giqf2qmpjng67fqtpuhleqvaqmOther Versions
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. ...
To address this issue, we devise a novel architecture towards span-level eXplanations of the TQA (XTQA) based on our proposed coarse-to-fine grained algorithm, which can provide not only the answers but ...
We propose a coarse-to-fine grained algorithm to provide the evidence spans of questions for students. ...
arXiv:2011.12662v3
fatcat:owfnq3q6kfdlxpxoyd53g3stl4
MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. ...
Compared with Visual Question Answering (VQA), TQA contains a large number of uncommon terminologies and various diagram inputs. ...
is proposed to address multimodal fusion challenges. • XTQA (Ma et al. 2020): It designs a coarse-to-fine algo- rithm to generate span-level evidences. • RAFR (Ma et al. 2021): A fine-grained reasoning ...
arXiv:2112.02839v1
fatcat:waw2igbhozfvxfxnun2ncnobbq
Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2004.13821v1 fatcat:6dvbem5m2ndkposuhhc7gcfrkm
In this paper, we present a two stage model for multi-hop question answering. ...
The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of granularity using the nature structure(i.e., paragraphs, questions ...
Coarse-grain fine-grain coattention network for multi-evidence question answering. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. ...
arXiv:2004.13821v2
fatcat:cl5z74cbzze2rkwjvqajhhugwe
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2019 pre-print arXiv:1905.07374v1 fatcat:twlhdgpa4vgovpnjq3xqx6psfi
We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. ...
Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. ...
Acknowledgements We would like to thank Johannes Welbl for running evaluation on our submitted model. ...
arXiv:1905.07374v2
fatcat:epznpgcp7vgovminxdcn53t5yq
The Natural Language Decathlon: Multitask Learning as Question Answering
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We cast all tasks as question answering over a context. ...
Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. ...
The multitask question answering network (MQAN) is designed for decaNLP and makes use of a novel dual coattention and multi-pointer-generator decoder to multitask across all tasks in decaNLP. ...
arXiv:1806.08730v1
fatcat:pdvwr3fqfrdnjdzwotzahsjf3e
Smarnet: Teaching Machines to Read and Comprehend Like Human
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We then guide the machines to read in an interactive way with attention mechanism and memory network. Finally we add a checking layer to refine the answer for insurance. ...
Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question. ...
Therefore, we propose a multi-hop memory network which allows to reread the question and answer. ...
arXiv:1710.02772v1
fatcat:hkdqwqvxtzecdpti5jpl2cogfa
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. ...
Multi-hop reading comprehension (RC) across documents poses new challenge over singledocument RC because it requires reasoning over multiple documents to reach the final answer. ...
Acknowledgements We would like to thank Johannes Welbl from University College London for running evaluation on our submitted model. ...
doi:10.18653/v1/p19-1260
dblp:conf/acl/TuWHTHZ19
fatcat:os2vkhkzynh5bl2xk44yzhdpkq
Complex Factoid Question Answering with a Free-Text Knowledge Graph
2020
Proceedings of The Web Conference 2020
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2103.12876v1 fatcat:aw5ruztdnbc25mdislhix5m2ty
Experiments on three question answering datasets show DELFT can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. ...
A novel graph neural network reasons over the free-text graph-combining evidence on the nodes via information along edge sentences-to select a final answer. ...
Fine-grain Coattention Network for Multi-evidence Question An-
and Quoc V Le. 2019. ...
doi:10.1145/3366423.3380197
dblp:conf/www/ZhaoXQB20
fatcat:ahvzga5qdjdfph36gpkuikn4oe
Ask to Understand: Question Generation for Multi-hop Question Answering
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. ...
Graph Network (GN) and Question Decomposition (QD) are two common approaches at present. ...
Related Work Multi-hop QA In multi-hop QA, the evidence for reasoning answers is scattered across multiple sentences. ...
arXiv:2203.09073v1
fatcat:3i34k5linfbfxppvv5mu7ub5g4
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. ...
Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. ...
Acknowledgement We would like to thank Johannes Welbl for helping test our system on WikiHop and MedHop. We thank the reviewers for their helpful comments. ...
doi:10.18653/v1/p19-1261
dblp:conf/acl/JiangJCB19
fatcat:wxedrdchgzgehbybckxisks76e
Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
For instance, graphic news contains plenty of images in addition to text. ...
We construct a largescale dataset for this task and explore several representative methods. ...
Acknowledgement We thank the anonymous reviewers for their thoughtful comments. Xu Sun is the contact author of this paper. ...
doi:10.18653/v1/p19-1257
dblp:conf/acl/YangZLLHS19
fatcat:jfvat3ij5bg25fgwrfo6san7me
Question-Driven Purchasing Propensity Analysis for Recommendation
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To address this recommendation problem, we propose a novel Question-Driven Attentive Neural Network (QDANN) to assess the instant demands of questioners and the eligibility of products based on user generated ...
The attention mechanisms can be used to provide explanations for recommendations. We evaluate QDANN in three domains of Taobao. ...
(Chen et al. 2019 ) proposed a multi-task attentive network for plausible answer identification from reviews. ...
doi:10.1609/aaai.v34i01.5331
fatcat:aipdzryhybexhcmmb4yvfzwuui
New Ideas and Trends in Deep Multimodal Content Understanding: A Review
2020
Neurocomputing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
These models go beyond the simple image classifiers in which they can do uni-directional (e.g. image captioning, image generation) and bi-directional (e.g. cross-modal retrieval, visual question answering ...
Finally, we include several promising directions for future research. ...
For example, some fine-grained attributes including texture, shape and color can be specified during deep network training. ...
doi:10.1016/j.neucom.2020.10.042
fatcat:hyjkj5enozfrvgzxy6avtbmoxu
New Ideas and Trends in Deep Multimodal Content Understanding: A Review
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These models go beyond the simple image classifiers in which they can do uni-directional (e.g. image captioning, image generation) and bi-directional (e.g. cross-modal retrieval, visual question answering ...
Finally, we include several promising directions for future research. ...
For example, some fine-grained attributes including texture, shape and color can be specified during deep network training. ...
arXiv:2010.08189v1
fatcat:2l7molbcn5hf3oyhe3l52tdwra
« Previous
Showing results 1 — 15 out of 28 results