@inproceedings{ventirozos-etal-2026-auto,
title = "Auto-{A}dv{ER}: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements",
author = "Ventirozos, Filippos and
Nteka, Ioanna and
Nandy, Tania and
Ba{\v{c}}a, Jozef and
Roadhouse, Charlie and
Appleby, Peter A. and
Shardlow, Matthew",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.28/",
pages = "603--619",
ISBN = "979-8-89176-439-2",
abstract = "This paper presents a case study on the development of Auto-AdvER, a specialised span-labelling schema, along with its corresponding dataset for the textual car advertisement domain. Developed with industry needs in mind, Auto-AdvER is designed to enhance text mining analytics in this domain and contributes a linguistically unique sequence-labelling dataset. We introduce a schema consisting of three labels: `Condition', `Historic', and `Sales Options'. We outline the guiding principles for annotation, describe the methodology for schema development, and present the results of an annotation study demonstrating an inter-annotator agreement of 78{\%}. Furthermore, we compare the performance of various models, including transformer encoder models (BERT, DeBERTaV3) and transformer decoder-based open- and closed-source large language models: Llama, Qwen, GPT, and Gemini, as well as conditional random fields. Our results show that a fine-tuned DeBERTaV3 encoder achieves the highest F1-score, followed closely by conditional random fields, while the large language models reach the highest precision but lower recall. We present this work as a stepping stone towards more fine-grained analysis and discuss Auto-AdvER{'}s potential impact on advertisement analytics, pricing, and customer insights. Potential applications include the analysis of market dynamics and data-driven predictive maintenance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ventirozos-etal-2026-auto">
<titleInfo>
<title>Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filippos</namePart>
<namePart type="family">Ventirozos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioanna</namePart>
<namePart type="family">Nteka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Nandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jozef</namePart>
<namePart type="family">Bača</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlie</namePart>
<namePart type="family">Roadhouse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Appleby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</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 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</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">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>This paper presents a case study on the development of Auto-AdvER, a specialised span-labelling schema, along with its corresponding dataset for the textual car advertisement domain. Developed with industry needs in mind, Auto-AdvER is designed to enhance text mining analytics in this domain and contributes a linguistically unique sequence-labelling dataset. We introduce a schema consisting of three labels: ‘Condition’, ‘Historic’, and ‘Sales Options’. We outline the guiding principles for annotation, describe the methodology for schema development, and present the results of an annotation study demonstrating an inter-annotator agreement of 78%. Furthermore, we compare the performance of various models, including transformer encoder models (BERT, DeBERTaV3) and transformer decoder-based open- and closed-source large language models: Llama, Qwen, GPT, and Gemini, as well as conditional random fields. Our results show that a fine-tuned DeBERTaV3 encoder achieves the highest F1-score, followed closely by conditional random fields, while the large language models reach the highest precision but lower recall. We present this work as a stepping stone towards more fine-grained analysis and discuss Auto-AdvER’s potential impact on advertisement analytics, pricing, and customer insights. Potential applications include the analysis of market dynamics and data-driven predictive maintenance.</abstract>
<identifier type="citekey">ventirozos-etal-2026-auto</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.28/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>603</start>
<end>619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements
%A Ventirozos, Filippos
%A Nteka, Ioanna
%A Nandy, Tania
%A Bača, Jozef
%A Roadhouse, Charlie
%A Appleby, Peter A.
%A Shardlow, Matthew
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F ventirozos-etal-2026-auto
%X This paper presents a case study on the development of Auto-AdvER, a specialised span-labelling schema, along with its corresponding dataset for the textual car advertisement domain. Developed with industry needs in mind, Auto-AdvER is designed to enhance text mining analytics in this domain and contributes a linguistically unique sequence-labelling dataset. We introduce a schema consisting of three labels: ‘Condition’, ‘Historic’, and ‘Sales Options’. We outline the guiding principles for annotation, describe the methodology for schema development, and present the results of an annotation study demonstrating an inter-annotator agreement of 78%. Furthermore, we compare the performance of various models, including transformer encoder models (BERT, DeBERTaV3) and transformer decoder-based open- and closed-source large language models: Llama, Qwen, GPT, and Gemini, as well as conditional random fields. Our results show that a fine-tuned DeBERTaV3 encoder achieves the highest F1-score, followed closely by conditional random fields, while the large language models reach the highest precision but lower recall. We present this work as a stepping stone towards more fine-grained analysis and discuss Auto-AdvER’s potential impact on advertisement analytics, pricing, and customer insights. Potential applications include the analysis of market dynamics and data-driven predictive maintenance.
%U https://aclanthology.org/2026.aacl-long.28/
%P 603-619
Markdown (Informal)
[Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements](https://aclanthology.org/2026.aacl-long.28/) (Ventirozos et al., AACL-IJCNLP 2026)
ACL
- Filippos Ventirozos, Ioanna Nteka, Tania Nandy, Jozef Bača, Charlie Roadhouse, Peter A. Appleby, and Matthew Shardlow. 2026. Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 603–619, Hengqin, China. Association for Computational Linguistics.