@inproceedings{boenninghoff-etal-2024-wrote,
title = "Who Wrote When? Author Diarization in Social Media Discussions",
author = "Boenninghoff, Benedikt and
Hosseini, Henry and
Nickel, Robert M. and
Kolossa, Dorothea",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.922/",
doi = "10.18653/v1/2024.findings-emnlp.922",
pages = "15721--15734",
abstract = "We are proposing a novel framework for author diarization, i.e. attributing comments in online discussions to individual authors. We consider an innovative approach that merges pre-trained neural representations of writing style with author-conditional encoder-decoder diarization, enhanced by a Conditional Random Field with Viterbi decoding for alignment refinement. Additionally, we introduce two new large-scale German language datasets, one for authorship verification and the other for author diarization. We evaluate the performance of our diarization framework on these datasets, offering insights into the strengths and limitations of this approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boenninghoff-etal-2024-wrote">
<titleInfo>
<title>Who Wrote When? Author Diarization in Social Media Discussions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benedikt</namePart>
<namePart type="family">Boenninghoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Hosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Nickel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothea</namePart>
<namePart type="family">Kolossa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We are proposing a novel framework for author diarization, i.e. attributing comments in online discussions to individual authors. We consider an innovative approach that merges pre-trained neural representations of writing style with author-conditional encoder-decoder diarization, enhanced by a Conditional Random Field with Viterbi decoding for alignment refinement. Additionally, we introduce two new large-scale German language datasets, one for authorship verification and the other for author diarization. We evaluate the performance of our diarization framework on these datasets, offering insights into the strengths and limitations of this approach.</abstract>
<identifier type="citekey">boenninghoff-etal-2024-wrote</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.922</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.922/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15721</start>
<end>15734</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Who Wrote When? Author Diarization in Social Media Discussions
%A Boenninghoff, Benedikt
%A Hosseini, Henry
%A Nickel, Robert M.
%A Kolossa, Dorothea
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F boenninghoff-etal-2024-wrote
%X We are proposing a novel framework for author diarization, i.e. attributing comments in online discussions to individual authors. We consider an innovative approach that merges pre-trained neural representations of writing style with author-conditional encoder-decoder diarization, enhanced by a Conditional Random Field with Viterbi decoding for alignment refinement. Additionally, we introduce two new large-scale German language datasets, one for authorship verification and the other for author diarization. We evaluate the performance of our diarization framework on these datasets, offering insights into the strengths and limitations of this approach.
%R 10.18653/v1/2024.findings-emnlp.922
%U https://aclanthology.org/2024.findings-emnlp.922/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.922
%P 15721-15734
Markdown (Informal)
[Who Wrote When? Author Diarization in Social Media Discussions](https://aclanthology.org/2024.findings-emnlp.922/) (Boenninghoff et al., Findings 2024)
ACL