@inproceedings{bharadwaj-srinivasa-2026-hybrid,
title = "Hybrid {PIR}: Balancing Token Compression and Structural Invariance via {P}{\={a}}ṇinian Role Assignment",
author = "Bharadwaj, Kriti and
Srinivasa, Gowri",
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.1647/",
pages = "35057--35070",
ISBN = "979-8-89176-462-0",
abstract = "Neural text representations often lack structural guarantees for syntactic variations, relying instead on statistical interpolation to recognize paraphrases. We introduce the P{\={a}}ṇinian Intermediate Representation (PIR), a deterministic compiler that maps English sentences to role-tagged canonical sequences using Universal Dependency parses. Unlike heuristic methods such as stopword removal, the PIR compiler is deterministic: given a correct dependency parse, syntactically equivalent paraphrases compile to identical strings. On a 200-pair diagnostic suite of templated syntactic alternations spanning active/passive voice, dative shift, and topicalization, the compiler produces identical strings for 196 pairs; all four failures are structurally typed and traced to known parser limitations. Stopword removal produces identical strings for 0 of 200 pairs. To bridge the performance gap in downstream tasks, we propose Hybrid PIR, which selectively restores lexical content through a deduplication mechanism. Hybrid PIR achieves similarity performance comparable to stopword removal (0.8130 vs. 0.8154 average {\ensuremath{\rho}}; bootstrap 95{\%} CI on the difference includes zero) at 43.8{\%} token compression, while providing structural guarantees that surface-level methods cannot. On retrieval benchmarks, Hybrid PIR reaches 80{\%} of the English baseline nDCG@10 on BEIR SciFact and 86{\%} of MRR@10 on MS MARCO QA at 39.0{\%} compression. A three-variant representation ablation validates our deduplication design: removing this mechanism degrades retrieval performance by 3.5 points and turns the compression benefit negative (-3.0{\%}). In a QQP-validation duplicate-detection use case (40,430 pairs), Hybrid PIR reaches precision 0.861 with no tuning, matching a tuned embedding threshold and validating the intended deployment as an offline canonicalization tool for deduplication and index construction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bharadwaj-srinivasa-2026-hybrid">
<titleInfo>
<title>Hybrid PIR: Balancing Token Compression and Structural Invariance via Pāṇinian Role Assignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kriti</namePart>
<namePart type="family">Bharadwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gowri</namePart>
<namePart type="family">Srinivasa</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>Neural text representations often lack structural guarantees for syntactic variations, relying instead on statistical interpolation to recognize paraphrases. We introduce the Pāṇinian Intermediate Representation (PIR), a deterministic compiler that maps English sentences to role-tagged canonical sequences using Universal Dependency parses. Unlike heuristic methods such as stopword removal, the PIR compiler is deterministic: given a correct dependency parse, syntactically equivalent paraphrases compile to identical strings. On a 200-pair diagnostic suite of templated syntactic alternations spanning active/passive voice, dative shift, and topicalization, the compiler produces identical strings for 196 pairs; all four failures are structurally typed and traced to known parser limitations. Stopword removal produces identical strings for 0 of 200 pairs. To bridge the performance gap in downstream tasks, we propose Hybrid PIR, which selectively restores lexical content through a deduplication mechanism. Hybrid PIR achieves similarity performance comparable to stopword removal (0.8130 vs. 0.8154 average \ensuremathρ; bootstrap 95% CI on the difference includes zero) at 43.8% token compression, while providing structural guarantees that surface-level methods cannot. On retrieval benchmarks, Hybrid PIR reaches 80% of the English baseline nDCG@10 on BEIR SciFact and 86% of MRR@10 on MS MARCO QA at 39.0% compression. A three-variant representation ablation validates our deduplication design: removing this mechanism degrades retrieval performance by 3.5 points and turns the compression benefit negative (-3.0%). In a QQP-validation duplicate-detection use case (40,430 pairs), Hybrid PIR reaches precision 0.861 with no tuning, matching a tuned embedding threshold and validating the intended deployment as an offline canonicalization tool for deduplication and index construction.</abstract>
<identifier type="citekey">bharadwaj-srinivasa-2026-hybrid</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1647/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>35057</start>
<end>35070</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hybrid PIR: Balancing Token Compression and Structural Invariance via Pāṇinian Role Assignment
%A Bharadwaj, Kriti
%A Srinivasa, Gowri
%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 bharadwaj-srinivasa-2026-hybrid
%X Neural text representations often lack structural guarantees for syntactic variations, relying instead on statistical interpolation to recognize paraphrases. We introduce the Pāṇinian Intermediate Representation (PIR), a deterministic compiler that maps English sentences to role-tagged canonical sequences using Universal Dependency parses. Unlike heuristic methods such as stopword removal, the PIR compiler is deterministic: given a correct dependency parse, syntactically equivalent paraphrases compile to identical strings. On a 200-pair diagnostic suite of templated syntactic alternations spanning active/passive voice, dative shift, and topicalization, the compiler produces identical strings for 196 pairs; all four failures are structurally typed and traced to known parser limitations. Stopword removal produces identical strings for 0 of 200 pairs. To bridge the performance gap in downstream tasks, we propose Hybrid PIR, which selectively restores lexical content through a deduplication mechanism. Hybrid PIR achieves similarity performance comparable to stopword removal (0.8130 vs. 0.8154 average \ensuremathρ; bootstrap 95% CI on the difference includes zero) at 43.8% token compression, while providing structural guarantees that surface-level methods cannot. On retrieval benchmarks, Hybrid PIR reaches 80% of the English baseline nDCG@10 on BEIR SciFact and 86% of MRR@10 on MS MARCO QA at 39.0% compression. A three-variant representation ablation validates our deduplication design: removing this mechanism degrades retrieval performance by 3.5 points and turns the compression benefit negative (-3.0%). In a QQP-validation duplicate-detection use case (40,430 pairs), Hybrid PIR reaches precision 0.861 with no tuning, matching a tuned embedding threshold and validating the intended deployment as an offline canonicalization tool for deduplication and index construction.
%U https://aclanthology.org/2026.findings-emnlp.1647/
%P 35057-35070
Markdown (Informal)
[Hybrid PIR: Balancing Token Compression and Structural Invariance via Pāṇinian Role Assignment](https://aclanthology.org/2026.findings-emnlp.1647/) (Bharadwaj & Srinivasa, Findings 2026)
ACL