2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
DOI: 10.1109/cvpr.2017.571
|View full text |Cite
|
Sign up to set email alerts
|

Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
159
0
1

Year Published

2017
2017
2021
2021

Publication Types

Select...
5
5

Relationship

0
10

Authors

Journals

citations
Cited by 197 publications
(161 citation statements)
references
References 9 publications
1
159
0
1
Order By: Relevance
“…To select the best P q (x), P c (x) and sampling strategy we conducted the following search. First we explored sampling probabilities 0.2, 0.4, 0.6, 0.8, 1.0 for query and context separately, using random sampling, and subsequently we combined them using values informed from the previous exploration, this time BioASQ (Tsatsaronis et al, 2015) 60.28 71.98 DROP (Dua et al, 2019) 48.50 58.90 DuoRC (Saha et al, 2018) 53.29 63.36 RACE (Lai et al, 2017) 39.35 53.87 RelationExtraction (Levy et al, 2017) 79.20 87.85 TextbookQA (Kembhavi et al, 2017) 56.50 65.54…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…To select the best P q (x), P c (x) and sampling strategy we conducted the following search. First we explored sampling probabilities 0.2, 0.4, 0.6, 0.8, 1.0 for query and context separately, using random sampling, and subsequently we combined them using values informed from the previous exploration, this time BioASQ (Tsatsaronis et al, 2015) 60.28 71.98 DROP (Dua et al, 2019) 48.50 58.90 DuoRC (Saha et al, 2018) 53.29 63.36 RACE (Lai et al, 2017) 39.35 53.87 RelationExtraction (Levy et al, 2017) 79.20 87.85 TextbookQA (Kembhavi et al, 2017) 56.50 65.54…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…The Multi-Output Model (MOM) introduced in DVQA uses an OCR module to read chart specific content. Textbook QA (TQA) [24] considers the task of answering questions from middle-school textbooks, which often require understanding and reasoning about text and diagrams. Similarly, AI2D [23] contains diagram based multiple-choice questions.…”
Section: Related Workmentioning
confidence: 99%
“…The closest works to ours are (Iyyer et al, 2017), (Tapaswi et al, 2016) and (Kembhavi et al, 2017) where data multi-modality is the key aspect. COMICS dataset (Iyyer et al, 2017) focus on comic book narratives and explore visual cloze style questions, introducing a dataset consisting of drawings from comic books.…”
Section: Related Workmentioning
confidence: 99%