@inproceedings{reza-etal-2026-beyond,
title = "Beyond Chunking: Node Integrity and Field Structure in {B}engali Retrieval-Augmented Agent Memory",
author = "Reza, Khan Raiyan Ibne and
Maria, Sanjana Aktar and
Nimi, Sumaiya Tabassum",
editor = "Er-Rahmadi, Btissam and
Montella, S{\'e}bastien and
Graux, Damien and
Melo, Andr{\'e} and
Jabeen, Hajira",
booktitle = "Proceedings of the 3rd Workshop on {KNO}wledge {GR}aphs Agentic Systems Interplay ({NORA} 2026)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nora-1.8/",
pages = "84--97",
ISBN = "979-8-89176-457-6",
abstract = "Lexical retrieval in low-resource languages can fail when queries use symptoms, colloquial names, or procedural descriptions rather than formal terminology. Chunking can compound this problem by separating query-matching content from the field that identifies a record. We introduce a three-level representation ladder (chunked text, intact full-node text, and field-aware lexical indexing) that separates recovery associated with record integrity from the additional effect of field-aware representation. In the OCR-heavy education corpus, intact records raise Recall@10 from 37.19{\%} to 89.65{\%}. Field-aware indexing adds gains with fixed weights in agriculture and uniform weights in education, but uniform weighting underperforms intact text in law. Ablations indicate that useful fields depend on query formulation; full field-value shuffling reduces Recall@10 to 0.75-5.09{\%}. In agent memory, Recall@5 rises from 27.6{\%} to 61.9{\%} with intact records on 583 agriculture and education queries. Across 872 queries in all three domains, uniform fielded memory has a citation rate about 12 points higher than intact memory, without higher aggregate Recall@5. These results indicate that record integrity and query-aligned content warrant separate evaluation in retrieval and agent memory."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reza-etal-2026-beyond">
<titleInfo>
<title>Beyond Chunking: Node Integrity and Field Structure in Bengali Retrieval-Augmented Agent Memory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khan</namePart>
<namePart type="given">Raiyan</namePart>
<namePart type="given">Ibne</namePart>
<namePart type="family">Reza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjana</namePart>
<namePart type="given">Aktar</namePart>
<namePart type="family">Maria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumaiya</namePart>
<namePart type="given">Tabassum</namePart>
<namePart type="family">Nimi</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>Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Btissam</namePart>
<namePart type="family">Er-Rahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Graux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajira</namePart>
<namePart type="family">Jabeen</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">979-8-89176-457-6</identifier>
</relatedItem>
<abstract>Lexical retrieval in low-resource languages can fail when queries use symptoms, colloquial names, or procedural descriptions rather than formal terminology. Chunking can compound this problem by separating query-matching content from the field that identifies a record. We introduce a three-level representation ladder (chunked text, intact full-node text, and field-aware lexical indexing) that separates recovery associated with record integrity from the additional effect of field-aware representation. In the OCR-heavy education corpus, intact records raise Recall@10 from 37.19% to 89.65%. Field-aware indexing adds gains with fixed weights in agriculture and uniform weights in education, but uniform weighting underperforms intact text in law. Ablations indicate that useful fields depend on query formulation; full field-value shuffling reduces Recall@10 to 0.75-5.09%. In agent memory, Recall@5 rises from 27.6% to 61.9% with intact records on 583 agriculture and education queries. Across 872 queries in all three domains, uniform fielded memory has a citation rate about 12 points higher than intact memory, without higher aggregate Recall@5. These results indicate that record integrity and query-aligned content warrant separate evaluation in retrieval and agent memory.</abstract>
<identifier type="citekey">reza-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.nora-1.8/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>84</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Chunking: Node Integrity and Field Structure in Bengali Retrieval-Augmented Agent Memory
%A Reza, Khan Raiyan Ibne
%A Maria, Sanjana Aktar
%A Nimi, Sumaiya Tabassum
%Y Er-Rahmadi, Btissam
%Y Montella, Sébastien
%Y Graux, Damien
%Y Melo, André
%Y Jabeen, Hajira
%S Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-457-6
%F reza-etal-2026-beyond
%X Lexical retrieval in low-resource languages can fail when queries use symptoms, colloquial names, or procedural descriptions rather than formal terminology. Chunking can compound this problem by separating query-matching content from the field that identifies a record. We introduce a three-level representation ladder (chunked text, intact full-node text, and field-aware lexical indexing) that separates recovery associated with record integrity from the additional effect of field-aware representation. In the OCR-heavy education corpus, intact records raise Recall@10 from 37.19% to 89.65%. Field-aware indexing adds gains with fixed weights in agriculture and uniform weights in education, but uniform weighting underperforms intact text in law. Ablations indicate that useful fields depend on query formulation; full field-value shuffling reduces Recall@10 to 0.75-5.09%. In agent memory, Recall@5 rises from 27.6% to 61.9% with intact records on 583 agriculture and education queries. Across 872 queries in all three domains, uniform fielded memory has a citation rate about 12 points higher than intact memory, without higher aggregate Recall@5. These results indicate that record integrity and query-aligned content warrant separate evaluation in retrieval and agent memory.
%U https://aclanthology.org/2026.nora-1.8/
%P 84-97
Markdown (Informal)
[Beyond Chunking: Node Integrity and Field Structure in Bengali Retrieval-Augmented Agent Memory](https://aclanthology.org/2026.nora-1.8/) (Reza et al., NORA 2026)
ACL