@inproceedings{czyznikiewicz-etal-2026-query,
title = "Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering",
author = "Czy{\.z}nikiewicz, Mateusz and
Tuora, Ryszard and
Kozakiewicz, Adam and
Zi{\k{e}}tkiewicz, Tomasz and
Gali{\'n}ski, Mateusz and
Godziszewski, Micha{\l} Tomasz and
Karpowicz, Michal P. and
Hospedales, Timothy and
Cornelio, Cristina",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1319/",
pages = "27929--27960",
ISBN = "979-8-89176-462-0",
abstract = "Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches support such operations, but they are often brittle on noisy natural-language corpora. We address this gap with DualGraph, a RAG framework that represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject{--}predicate{--}object triples. Building on these two components, we provide multiple strategies for selecting or combining semantic and symbolic evidence. We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types. Code and data are available at https://github.com/corneliocristina/DualGraphRAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="czyznikiewicz-etal-2026-query">
<titleInfo>
<title>Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Czyżnikiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryszard</namePart>
<namePart type="family">Tuora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Kozakiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Ziętkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Galiński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="given">Tomasz</namePart>
<namePart type="family">Godziszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Karpowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Hospedales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Cornelio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches support such operations, but they are often brittle on noisy natural-language corpora. We address this gap with DualGraph, a RAG framework that represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject–predicate–object triples. Building on these two components, we provide multiple strategies for selecting or combining semantic and symbolic evidence. We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types. Code and data are available at https://github.com/corneliocristina/DualGraphRAG.</abstract>
<identifier type="citekey">czyznikiewicz-etal-2026-query</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1319/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>27929</start>
<end>27960</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering
%A Czyżnikiewicz, Mateusz
%A Tuora, Ryszard
%A Kozakiewicz, Adam
%A Ziętkiewicz, Tomasz
%A Galiński, Mateusz
%A Godziszewski, Michał Tomasz
%A Karpowicz, Michal P.
%A Hospedales, Timothy
%A Cornelio, Cristina
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F czyznikiewicz-etal-2026-query
%X Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches support such operations, but they are often brittle on noisy natural-language corpora. We address this gap with DualGraph, a RAG framework that represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject–predicate–object triples. Building on these two components, we provide multiple strategies for selecting or combining semantic and symbolic evidence. We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types. Code and data are available at https://github.com/corneliocristina/DualGraphRAG.
%U https://aclanthology.org/2026.findings-emnlp.1319/
%P 27929-27960
Markdown (Informal)
[Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering](https://aclanthology.org/2026.findings-emnlp.1319/) (Czyżnikiewicz et al., Findings 2026)
ACL
- Mateusz Czyżnikiewicz, Ryszard Tuora, Adam Kozakiewicz, Tomasz Ziętkiewicz, Mateusz Galiński, Michał Tomasz Godziszewski, Michal P. Karpowicz, Timothy Hospedales, and Cristina Cornelio. 2026. Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 27929–27960, Budapest, Hungary. Association for Computational Linguistics.