Web Table Retrieval using Multimodal Deep Learning

Roee Shraga; Haggai Roitman; Guy Feigenblat; Mustafa Cannim

doi:10.1145/3397271.3401120

Web Table Retrieval using Multimodal Deep Learning

Roee Shraga, Haggai Roitman, Guy Feigenblat, Mustafa Cannim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

38 Scopus citations

Abstract

We address the web table retrieval task, aiming to retrieve and rank web tables as whole answers to a given information need. To this end, we formally define web tables as multimodal objects. We then suggest a neural ranking model, termed MTR, which makes a novel use of Gated Multimodal Units (GMUs) to learn a joint-representation of the query and the different table modalities. We further enhance this model with a co-learning approach which utilizes automatically learned query-independent and query-dependent "helper" labels. We evaluate the proposed solution using both ad hoc queries (WikiTables) and natural language questions (GNQtables). Overall, we demonstrate that our approach surpasses the performance of previously studied state-of-the-art baselines.

Original language	English
Title of host publication	SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher	Association for Computing Machinery, Inc
Pages	1399-1408
Number of pages	10
ISBN (Electronic)	9781450380164
DOIs	https://doi.org/10.1145/3397271.3401120
State	Published - 25 Jul 2020
Externally published	Yes
Event	43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 - Virtual, Online, China Duration: 25 Jul 2020 → 30 Jul 2020

Publication series

Name	SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference	43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020
Country/Territory	China
City	Virtual, Online
Period	25/07/20 → 30/07/20

Bibliographical note

Publisher Copyright:
© 2020 ACM.

Keywords

experimentation
multimodal deep-learning
table retrieval

Access to Document

10.1145/3397271.3401120

Cite this

Shraga, R., Roitman, H., Feigenblat, G., & Cannim, M. (2020). Web Table Retrieval using Multimodal Deep Learning. In SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1399-1408). (SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval). Association for Computing Machinery, Inc. https://doi.org/10.1145/3397271.3401120

Shraga, Roee ; Roitman, Haggai ; Feigenblat, Guy et al. / Web Table Retrieval using Multimodal Deep Learning. SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2020. pp. 1399-1408 (SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval).

@inproceedings{09fcf6fdd62f4b86bde78cfbae7b74b5,

title = "Web Table Retrieval using Multimodal Deep Learning",

abstract = "We address the web table retrieval task, aiming to retrieve and rank web tables as whole answers to a given information need. To this end, we formally define web tables as multimodal objects. We then suggest a neural ranking model, termed MTR, which makes a novel use of Gated Multimodal Units (GMUs) to learn a joint-representation of the query and the different table modalities. We further enhance this model with a co-learning approach which utilizes automatically learned query-independent and query-dependent {"}helper{"} labels. We evaluate the proposed solution using both ad hoc queries (WikiTables) and natural language questions (GNQtables). Overall, we demonstrate that our approach surpasses the performance of previously studied state-of-the-art baselines.",

keywords = "experimentation, multimodal deep-learning, table retrieval",

author = "Roee Shraga and Haggai Roitman and Guy Feigenblat and Mustafa Cannim",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 ; Conference date: 25-07-2020 Through 30-07-2020",

year = "2020",

month = jul,

day = "25",

doi = "10.1145/3397271.3401120",

language = "אנגלית",

series = "SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval",

publisher = "Association for Computing Machinery, Inc",

pages = "1399--1408",

booktitle = "SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

Shraga, R, Roitman, H, Feigenblat, G & Cannim, M 2020, Web Table Retrieval using Multimodal Deep Learning. in SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, pp. 1399-1408, 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, Virtual, Online, China, 25/07/20. https://doi.org/10.1145/3397271.3401120

Web Table Retrieval using Multimodal Deep Learning. / Shraga, Roee; Roitman, Haggai; Feigenblat, Guy et al.
SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2020. p. 1399-1408 (SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Web Table Retrieval using Multimodal Deep Learning

AU - Shraga, Roee

AU - Roitman, Haggai

AU - Feigenblat, Guy

AU - Cannim, Mustafa

PY - 2020/7/25

Y1 - 2020/7/25

N2 - We address the web table retrieval task, aiming to retrieve and rank web tables as whole answers to a given information need. To this end, we formally define web tables as multimodal objects. We then suggest a neural ranking model, termed MTR, which makes a novel use of Gated Multimodal Units (GMUs) to learn a joint-representation of the query and the different table modalities. We further enhance this model with a co-learning approach which utilizes automatically learned query-independent and query-dependent "helper" labels. We evaluate the proposed solution using both ad hoc queries (WikiTables) and natural language questions (GNQtables). Overall, we demonstrate that our approach surpasses the performance of previously studied state-of-the-art baselines.

AB - We address the web table retrieval task, aiming to retrieve and rank web tables as whole answers to a given information need. To this end, we formally define web tables as multimodal objects. We then suggest a neural ranking model, termed MTR, which makes a novel use of Gated Multimodal Units (GMUs) to learn a joint-representation of the query and the different table modalities. We further enhance this model with a co-learning approach which utilizes automatically learned query-independent and query-dependent "helper" labels. We evaluate the proposed solution using both ad hoc queries (WikiTables) and natural language questions (GNQtables). Overall, we demonstrate that our approach surpasses the performance of previously studied state-of-the-art baselines.

KW - experimentation

KW - multimodal deep-learning

KW - table retrieval

UR - http://www.scopus.com/inward/record.url?scp=85090154104&partnerID=8YFLogxK

U2 - 10.1145/3397271.3401120

DO - 10.1145/3397271.3401120

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85090154104

T3 - SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

SP - 1399

EP - 1408

BT - SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery, Inc

T2 - 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020

Y2 - 25 July 2020 through 30 July 2020

ER -

Shraga R, Roitman H, Feigenblat G, Cannim M. Web Table Retrieval using Multimodal Deep Learning. In SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc. 2020. p. 1399-1408. (SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval). doi: 10.1145/3397271.3401120

Web Table Retrieval using Multimodal Deep Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this