@inproceedings{zhu-etal-2026-learned,
title = "Learned Sparse Lexical Representations for Large-scale Authorship Attribution",
author = "Zhu, Jian and
Yuan, Su and
Yang, Changbing",
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.400/",
pages = "8455--8482",
ISBN = "979-8-89176-462-0",
abstract = "Authorship attribution aims to determine whether a query text and a candidate document are written by the same author. {\%}While dense embeddings are effective, recent work suggests that low-dimensional representations limit encoding capacity. We investigate high-dimensional learned sparse representations (LSR) and multi-vector retrieval for authorship attribution. We further propose Sparse ColBERT (SparCol), a late-interaction sparse lexical reranking model. To address the memory cost of vocabulary-size embeddings, we develop fused \texttt{Triton} kernels that can reduce peak memory usage by 5{~}11 times over the baseline torch implementation. Extensive experiments show that LSR can outperform dense embeddings in both single-genre and cross-genre settings, whereas improves reranking performance over single-vector models only in single-genre settings due to lexical matching bias. In addition to token-based embeddings, we also explore Lexicon-based embeddings that score clusters of tokens, which is competitive with the vocabulary-based LSR with reduced dimensions. We conduct interpretability analysis of LSRs, showing that they allow for a more transparent scoring process."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2026-learned">
<titleInfo>
<title>Learned Sparse Lexical Representations for Large-scale Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changbing</namePart>
<namePart type="family">Yang</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>Authorship attribution aims to determine whether a query text and a candidate document are written by the same author. %While dense embeddings are effective, recent work suggests that low-dimensional representations limit encoding capacity. We investigate high-dimensional learned sparse representations (LSR) and multi-vector retrieval for authorship attribution. We further propose Sparse ColBERT (SparCol), a late-interaction sparse lexical reranking model. To address the memory cost of vocabulary-size embeddings, we develop fused Triton kernels that can reduce peak memory usage by 5 11 times over the baseline torch implementation. Extensive experiments show that LSR can outperform dense embeddings in both single-genre and cross-genre settings, whereas improves reranking performance over single-vector models only in single-genre settings due to lexical matching bias. In addition to token-based embeddings, we also explore Lexicon-based embeddings that score clusters of tokens, which is competitive with the vocabulary-based LSR with reduced dimensions. We conduct interpretability analysis of LSRs, showing that they allow for a more transparent scoring process.</abstract>
<identifier type="citekey">zhu-etal-2026-learned</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.400/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8455</start>
<end>8482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learned Sparse Lexical Representations for Large-scale Authorship Attribution
%A Zhu, Jian
%A Yuan, Su
%A Yang, Changbing
%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 zhu-etal-2026-learned
%X Authorship attribution aims to determine whether a query text and a candidate document are written by the same author. %While dense embeddings are effective, recent work suggests that low-dimensional representations limit encoding capacity. We investigate high-dimensional learned sparse representations (LSR) and multi-vector retrieval for authorship attribution. We further propose Sparse ColBERT (SparCol), a late-interaction sparse lexical reranking model. To address the memory cost of vocabulary-size embeddings, we develop fused Triton kernels that can reduce peak memory usage by 5 11 times over the baseline torch implementation. Extensive experiments show that LSR can outperform dense embeddings in both single-genre and cross-genre settings, whereas improves reranking performance over single-vector models only in single-genre settings due to lexical matching bias. In addition to token-based embeddings, we also explore Lexicon-based embeddings that score clusters of tokens, which is competitive with the vocabulary-based LSR with reduced dimensions. We conduct interpretability analysis of LSRs, showing that they allow for a more transparent scoring process.
%U https://aclanthology.org/2026.findings-emnlp.400/
%P 8455-8482
Markdown (Informal)
[Learned Sparse Lexical Representations for Large-scale Authorship Attribution](https://aclanthology.org/2026.findings-emnlp.400/) (Zhu et al., Findings 2026)
ACL