Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives
This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on...
Saved in:
Main Authors: | TAY, Yi, WANG, Shuohang, LUU, Anh Tuan, FU, Jie, PHAN, Minh C., YUAN, Xingdi, RAO, Jinfeng, HUI, Siu Cheung, ZHANG, Aston |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2019
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/scis_studentpub/1 https://ink.library.smu.edu.sg/context/scis_studentpub/article/1000/viewcontent/P19_1486.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Machine comprehension using match-LSTM and answer pointer
by: WANG, Shuohang, et al.
Published: (2017) -
CLAIM: Curriculum learning policy for influence maximization in unknown social networks
by: LI, Dexun, et al.
Published: (2021) -
Listening and reading comprehension: The modality proficiencies in the comprehension of narratives of different types of learners
by: Elicaño, Maria Cristina Amor Chavez
Published: (2007) -
Hardware-driven prefetching for pointer data references
by: Chi, Chi-Hung, et al.
Published: (2014) -
A co-matching model for multi-choice reading comprehension
by: WANG, Shuohang, et al.
Published: (2018)