R3: Reinforced Ranker-Reader for open-domain Question Answering

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected pas...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG, Shuohang, YU, Mo, GUO, Xiaoxiao, WANG, Zhiguo, KLINGER, Tim, ZHANG, Wei, CHANG, Shiyu, TESAURO, Gerald, ZHOU, Bowen, JIANG, Jing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2018
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4237
https://ink.library.smu.edu.sg/context/sis_research/article/5240/viewcontent/Reinforced_Reader_Ranker_2018_AAAI_afv.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5240
record_format dspace
spelling sg-smu-ink.sis_research-52402025-02-10T08:14:24Z R3: Reinforced Ranker-Reader for open-domain Question Answering WANG, Shuohang YU, Mo GUO, Xiaoxiao WANG, Zhiguo KLINGER, Tim ZHANG, Wei CHANG, Shiyu TESAURO, Gerald ZHOU, Bowen JIANG, Jing In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that “reads” the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R3), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets. 2018-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4237 info:doi/10.1609/aaai.v32i1.12053 https://ink.library.smu.edu.sg/context/sis_research/article/5240/viewcontent/Reinforced_Reader_Ranker_2018_AAAI_afv.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Answer extraction Ground truth Neural network method Open domain question answering Question Answering Reading comprehension Databases and Information Systems Theory and Algorithms
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Answer extraction
Ground truth
Neural network method
Open domain question answering
Question Answering
Reading comprehension
Databases and Information Systems
Theory and Algorithms
spellingShingle Answer extraction
Ground truth
Neural network method
Open domain question answering
Question Answering
Reading comprehension
Databases and Information Systems
Theory and Algorithms
WANG, Shuohang
YU, Mo
GUO, Xiaoxiao
WANG, Zhiguo
KLINGER, Tim
ZHANG, Wei
CHANG, Shiyu
TESAURO, Gerald
ZHOU, Bowen
JIANG, Jing
R3: Reinforced Ranker-Reader for open-domain Question Answering
description In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that “reads” the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R3), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.
format text
author WANG, Shuohang
YU, Mo
GUO, Xiaoxiao
WANG, Zhiguo
KLINGER, Tim
ZHANG, Wei
CHANG, Shiyu
TESAURO, Gerald
ZHOU, Bowen
JIANG, Jing
author_facet WANG, Shuohang
YU, Mo
GUO, Xiaoxiao
WANG, Zhiguo
KLINGER, Tim
ZHANG, Wei
CHANG, Shiyu
TESAURO, Gerald
ZHOU, Bowen
JIANG, Jing
author_sort WANG, Shuohang
title R3: Reinforced Ranker-Reader for open-domain Question Answering
title_short R3: Reinforced Ranker-Reader for open-domain Question Answering
title_full R3: Reinforced Ranker-Reader for open-domain Question Answering
title_fullStr R3: Reinforced Ranker-Reader for open-domain Question Answering
title_full_unstemmed R3: Reinforced Ranker-Reader for open-domain Question Answering
title_sort r3: reinforced ranker-reader for open-domain question answering
publisher Institutional Knowledge at Singapore Management University
publishDate 2018
url https://ink.library.smu.edu.sg/sis_research/4237
https://ink.library.smu.edu.sg/context/sis_research/article/5240/viewcontent/Reinforced_Reader_Ranker_2018_AAAI_afv.pdf
_version_ 1823807414975070208