@inproceedings{kanagarajan-etal-2026-beyond,
title = "Beyond Dense Retrieval: A Structured-Semantic Approach for Conversation Analytics",
author = "Kanagarajan, Abinesh and
Aggarwal, Chetan and
Jain, Anjali",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.207/",
pages = "3466--3489",
ISBN = "979-8-89176-460-6",
abstract = "Large Language Model (LLM) based conversational systems generate vast interaction logs containing critical diagnostic signals such as failure modes and safety violations. However, the cross-turn dependencies, implicit state, and topic drift inherent to these conversations defeat dense retrieval, whose lone embedding cannot concurrently encode discrete structured constraints (e.g., refusal type) and open-ended semantic content. Our central claim is conceptual: conversational retrieval must span two complementary information planes, structured metadata and semantic content, and these are best reconciled by a unified hybrid representation that jointly supports filtering over structured metadata fields and vector similarity search over unbounded open-ended fields. We instantiate this as the Extract-Annotate-Query (EAQ) framework, which derives a metadata taxonomy, applies LLM-driven annotation, and compiles natural-language queries into hybrid graph operations. On the CDR-Benchmark, EAQ lifts NDCG@10 by 30.8{\%} over the strongest dense baseline, with consistent gains across five analytical categories and two external datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanagarajan-etal-2026-beyond">
<titleInfo>
<title>Beyond Dense Retrieval: A Structured-Semantic Approach for Conversation Analytics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abinesh</namePart>
<namePart type="family">Kanagarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chetan</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjali</namePart>
<namePart type="family">Jain</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Large Language Model (LLM) based conversational systems generate vast interaction logs containing critical diagnostic signals such as failure modes and safety violations. However, the cross-turn dependencies, implicit state, and topic drift inherent to these conversations defeat dense retrieval, whose lone embedding cannot concurrently encode discrete structured constraints (e.g., refusal type) and open-ended semantic content. Our central claim is conceptual: conversational retrieval must span two complementary information planes, structured metadata and semantic content, and these are best reconciled by a unified hybrid representation that jointly supports filtering over structured metadata fields and vector similarity search over unbounded open-ended fields. We instantiate this as the Extract-Annotate-Query (EAQ) framework, which derives a metadata taxonomy, applies LLM-driven annotation, and compiles natural-language queries into hybrid graph operations. On the CDR-Benchmark, EAQ lifts NDCG@10 by 30.8% over the strongest dense baseline, with consistent gains across five analytical categories and two external datasets.</abstract>
<identifier type="citekey">kanagarajan-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.207/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3466</start>
<end>3489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Dense Retrieval: A Structured-Semantic Approach for Conversation Analytics
%A Kanagarajan, Abinesh
%A Aggarwal, Chetan
%A Jain, Anjali
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F kanagarajan-etal-2026-beyond
%X Large Language Model (LLM) based conversational systems generate vast interaction logs containing critical diagnostic signals such as failure modes and safety violations. However, the cross-turn dependencies, implicit state, and topic drift inherent to these conversations defeat dense retrieval, whose lone embedding cannot concurrently encode discrete structured constraints (e.g., refusal type) and open-ended semantic content. Our central claim is conceptual: conversational retrieval must span two complementary information planes, structured metadata and semantic content, and these are best reconciled by a unified hybrid representation that jointly supports filtering over structured metadata fields and vector similarity search over unbounded open-ended fields. We instantiate this as the Extract-Annotate-Query (EAQ) framework, which derives a metadata taxonomy, applies LLM-driven annotation, and compiles natural-language queries into hybrid graph operations. On the CDR-Benchmark, EAQ lifts NDCG@10 by 30.8% over the strongest dense baseline, with consistent gains across five analytical categories and two external datasets.
%U https://aclanthology.org/2026.emnlp-industry.207/
%P 3466-3489
Markdown (Informal)
[Beyond Dense Retrieval: A Structured-Semantic Approach for Conversation Analytics](https://aclanthology.org/2026.emnlp-industry.207/) (Kanagarajan et al., EMNLP 2026)
ACL