@inproceedings{zhang-etal-2026-dpdisc,
title = "{DPD}isc: From Factoid Questions to Data Product Requests for Open-World Data Product Discovery over Tables and Text",
author = "Zhang, Liangliang and
Mihindukulasooriya, Nandana and
D{'}Souza, Niharika S. and
Shirai, Sola and
Dash, Sarthak and
Ma, Yao and
Samulowitz, Horst",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.247/",
pages = "4846--4865",
ISBN = "979-8-89176-444-6",
abstract = "Modern enterprises store vast, heterogeneous data across large data lakes, where the central challenge is shifting from answering an isolated question to discovering and assembling the tables and documents that together serve an analytical goal. We refer to such a coherent collection of related assets as a data product. Existing table-text benchmarks evaluate factoid question answering over individual tables and therefore do not capture this discovery and assembly problem. We introduce DPDisc, the first benchmark for data product discovery: given a high-level Data Product Request (DPR), a system must retrieve the coherent set of tables and passages that satisfy it. DPDisc is constructed by DPForge, an automated pipeline that repurposes table-text QA datasets by clustering related tables and passages into products, generating DPRs with an LLM ensemble, and validating them through multi-phase LLM evaluation. It comprises 13,076 validated instances with full provenance, spanning open-domain and financial sources. Sparse, dense, and hybrid baselines establish that the task is feasible yet reveal large performance gaps across domains, motivating structure-aware retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-dpdisc">
<titleInfo>
<title>DPDisc: From Factoid Questions to Data Product Requests for Open-World Data Product Discovery over Tables and Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liangliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nandana</namePart>
<namePart type="family">Mihindukulasooriya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niharika</namePart>
<namePart type="given">S</namePart>
<namePart type="family">D’Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sola</namePart>
<namePart type="family">Shirai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horst</namePart>
<namePart type="family">Samulowitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Modern enterprises store vast, heterogeneous data across large data lakes, where the central challenge is shifting from answering an isolated question to discovering and assembling the tables and documents that together serve an analytical goal. We refer to such a coherent collection of related assets as a data product. Existing table-text benchmarks evaluate factoid question answering over individual tables and therefore do not capture this discovery and assembly problem. We introduce DPDisc, the first benchmark for data product discovery: given a high-level Data Product Request (DPR), a system must retrieve the coherent set of tables and passages that satisfy it. DPDisc is constructed by DPForge, an automated pipeline that repurposes table-text QA datasets by clustering related tables and passages into products, generating DPRs with an LLM ensemble, and validating them through multi-phase LLM evaluation. It comprises 13,076 validated instances with full provenance, spanning open-domain and financial sources. Sparse, dense, and hybrid baselines establish that the task is feasible yet reveal large performance gaps across domains, motivating structure-aware retrieval.</abstract>
<identifier type="citekey">zhang-etal-2026-dpdisc</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.247/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4846</start>
<end>4865</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DPDisc: From Factoid Questions to Data Product Requests for Open-World Data Product Discovery over Tables and Text
%A Zhang, Liangliang
%A Mihindukulasooriya, Nandana
%A D’Souza, Niharika S.
%A Shirai, Sola
%A Dash, Sarthak
%A Ma, Yao
%A Samulowitz, Horst
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F zhang-etal-2026-dpdisc
%X Modern enterprises store vast, heterogeneous data across large data lakes, where the central challenge is shifting from answering an isolated question to discovering and assembling the tables and documents that together serve an analytical goal. We refer to such a coherent collection of related assets as a data product. Existing table-text benchmarks evaluate factoid question answering over individual tables and therefore do not capture this discovery and assembly problem. We introduce DPDisc, the first benchmark for data product discovery: given a high-level Data Product Request (DPR), a system must retrieve the coherent set of tables and passages that satisfy it. DPDisc is constructed by DPForge, an automated pipeline that repurposes table-text QA datasets by clustering related tables and passages into products, generating DPRs with an LLM ensemble, and validating them through multi-phase LLM evaluation. It comprises 13,076 validated instances with full provenance, spanning open-domain and financial sources. Sparse, dense, and hybrid baselines establish that the task is feasible yet reveal large performance gaps across domains, motivating structure-aware retrieval.
%U https://aclanthology.org/2026.findings-aacl.247/
%P 4846-4865
Markdown (Informal)
[DPDisc: From Factoid Questions to Data Product Requests for Open-World Data Product Discovery over Tables and Text](https://aclanthology.org/2026.findings-aacl.247/) (Zhang et al., Findings 2026)
ACL