Cut to the Chase: A Context Zoom-in Network for Reading Comprehension
By Sathish Reddy Indurthi, Seunghak Yu, Seohyun Back, Heriberto Cuayáhuitl. 2018
18 citations recorded by the source corpus.
In recent years many deep neural networks have been proposed to solve Reading Comprehension (RC) tasks. Most of these models suffer from reasoning over long documents and do not trivially generalize to cases where the answer is not present as a span in a given document. We present a novel neural-based architecture that is capable of extracting relevant regions based on a given question-document pair and generating a well-formed answer. To show the effectiveness of our architecture, we conducted several experiments on the recently proposed and challenging RC dataset ‘NarrativeQA’. The proposed architecture outperforms state-of-the-art results by 12.62% (ROUGE-L) relative improvement.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Kosuke Nishida
- Kyosuke Nishida
- Itsumi Saito
- Greg Durrett
- Jifan Chen
- Atsushi Otsuka
- Shih-Ting Lin
- Hisako Asano
Citations in the corpus
- PALM: Pre-training an Autoencoding&autoregressive Language Model for Context-conditioned Generation (2020, neutral): “ConZNet (Indurthi et al., 2018) 0.”
- Multi-hop Question Answering via Reasoning Chains (2019, background): “Another line of work proposes to use the answer prediction score as supervision to the sentence extractor (Wang et al., 2018; Indurthi et al., 2018; Min et al., 2018).”
- Multi-style Generative Reading Comprehension (2019, methodology): “(2018), and Indurthi et al. (2018) used an RNN-based pointer-generator mechanism for single-passage RC.”