@inproceedings{farhansyah-etal-2026-pingpong,
title = "{PINGPONG}: A Natural Benchmark for Multi-Turn Code-Switching Dialogues",
author = "Farhansyah, Mohammad Rifqi and
Zhafran, Hanif Muhammad and
Adilazuarda, Farid and
Mukhtar, Maryam Ibrahim and
Muhammad, Shamsuddeen Hassan and
Ousidhoum, Nedjma and
Reddy, Sathwik and
Kumaraguru, Ponnurangam and
Kodali, Prashant and
Sitaram, Sunayana and
Winata, Genta Indra and
Purwarianti, Ayu and
Aji, Alham Fikri",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1854/",
pages = "42146--42174",
ISBN = "979-8-89176-459-0",
abstract = "Code-switching is a widespread practice among the world{'}s multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PINGPONG, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PINGPONG reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farhansyah-etal-2026-pingpong">
<titleInfo>
<title>PINGPONG: A Natural Benchmark for Multi-Turn Code-Switching Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Rifqi</namePart>
<namePart type="family">Farhansyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanif</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Zhafran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farid</namePart>
<namePart type="family">Adilazuarda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Mukhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedjma</namePart>
<namePart type="family">Ousidhoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sathwik</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ponnurangam</namePart>
<namePart type="family">Kumaraguru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prashant</namePart>
<namePart type="family">Kodali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</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</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Code-switching is a widespread practice among the world’s multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PINGPONG, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PINGPONG reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse.</abstract>
<identifier type="citekey">farhansyah-etal-2026-pingpong</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1854/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42146</start>
<end>42174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PINGPONG: A Natural Benchmark for Multi-Turn Code-Switching Dialogues
%A Farhansyah, Mohammad Rifqi
%A Zhafran, Hanif Muhammad
%A Adilazuarda, Farid
%A Mukhtar, Maryam Ibrahim
%A Muhammad, Shamsuddeen Hassan
%A Ousidhoum, Nedjma
%A Reddy, Sathwik
%A Kumaraguru, Ponnurangam
%A Kodali, Prashant
%A Sitaram, Sunayana
%A Winata, Genta Indra
%A Purwarianti, Ayu
%A Aji, Alham Fikri
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F farhansyah-etal-2026-pingpong
%X Code-switching is a widespread practice among the world’s multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PINGPONG, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PINGPONG reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse.
%U https://aclanthology.org/2026.emnlp-main.1854/
%P 42146-42174
Markdown (Informal)
[PINGPONG: A Natural Benchmark for Multi-Turn Code-Switching Dialogues](https://aclanthology.org/2026.emnlp-main.1854/) (Farhansyah et al., EMNLP 2026)
ACL
- Mohammad Rifqi Farhansyah, Hanif Muhammad Zhafran, Farid Adilazuarda, Maryam Ibrahim Mukhtar, Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Sathwik Reddy, Ponnurangam Kumaraguru, Prashant Kodali, Sunayana Sitaram, Genta Indra Winata, Ayu Purwarianti, and Alham Fikri Aji. 2026. PINGPONG: A Natural Benchmark for Multi-Turn Code-Switching Dialogues. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 42146–42174, Budapest, Hungary. Association for Computational Linguistics.