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
Multi-Perspective Fusion Network for Commonsense Reading Comprehension
[article]
2019
arXiv
pre-print
Preserved Fulltext
The experimental result also shows that our MPFN model achieves the state-of-the-art with an accuracy of 83.52% on the official test set. ...
Commonsense Reading Comprehension (CRC) is a significantly challenging task, aiming at choosing the right answer for the question referring to a narrative passage, which may require commonsense knowledge ...
commonsense knowledge and the understanding of the passage. ...
arXiv:1901.02257v1
fatcat:hc4coir5zvapxbxd7txv4y7vhe
A Roadmap for Big Model
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2203.14101v2 fatcat:zjl2fte3njc43cxbtjhcp5ypwuOther Versions
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. ...
We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability ...
We first give some preliminaries for knowledge graph and explain the knowledge fusion methods. Then the big model based knowledge acquisition approaches are described. ...
arXiv:2203.14101v4
fatcat:rdikzudoezak5b36cf6hhne5u4
From Recognition to Cognition: Visual Commonsense Reasoning
[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.
Other Versions
Experimental results show that while humans find VCR easy (over 90% accuracy), state-of-the-art vision models struggle (~45%). ...
Next, we introduce a new dataset, VCR, consisting of 290k multiple choice QA problems derived from 110k movie scenes. ...
The views and conclusions contained herein are those of the authors and should not be interpreted as representing endorsements of IARPA, DOI/IBC, or the U.S. Government. ...
arXiv:1811.10830v2
fatcat:nlfdm7uw2zg6fm6eywqlmpvooa
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
[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.
Other Versions
It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs ...
Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. ...
We also acknowledge the use of Oxford's Advanced Research Computing (ARC) facility, of the EPSRC-funded Tier 2 facility JADE (EP/P020275/1), and of GPU computing support by Scan Computers International ...
arXiv:2105.03761v2
fatcat:tujds362fjca3akncfhzlrumi4
Explainable Deep Learning: A Field Guide for the Uninitiated
[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.
Other Versions
As a black-box model, it remains difficult to diagnose what aspects of the model's input drive the decisions of a DNN. ...
The field guide: i) Introduces three simple dimensions defining the space of foundational methods that contribute to explainable deep learning, ii) discusses the evaluations for model explanations, iii ...
Acknowledgments We acknowledge project support from the Ohio Federal Research Network, the Multidisciplinary Research Program of the Department of Defense (MURI N00014-00-1-0637), and the organizers and ...
arXiv:2004.14545v2
fatcat:4qvtfw6unbfgpkqmeosq737ghq
Explainable Deep Learning: A Field Guide for the Uninitiated
2022
The Journal of Artificial Intelligence Research
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.
The field guide: i) Introduces three simple dimensions defining the space of foundational methods that contribute to explainable deep learning, ii) discusses the evaluations for model explanations, iii ...
The development of methods and studies enabling the explanation of a DNN's decisions has thus blossomed into an active and broad area of research. ...
knowledge base constructed by domain experts. ...
doi:10.1613/jair.1.13200
fatcat:qylru2n7tbepljxi72qah62bzy
Representation and contextualization for document understanding
[article]
2019
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.
There is a multitude of problems that need to be dealt with to solve this task. ...
With the goal of improving document understanding, we identify three main problems to study within the scope of this thesis. ...
We denote our proposed models as Multihop-MLP-LSTM, Multihop-Bilinear-LSTM, Multihop-Sequential-LSTM and Multihop-Self-LSTM which are MANs based on additive attention, bilinear attention, sequential attention ...
doi:10.15488/4440
fatcat:2igvuxyo6vcyffhspf3xtwbiru