@inproceedings{liang-etal-2026-create,
title = "You Can Create Words Rather Than Just Detect Them: Towards A New Paradigm of {C}hinese Neologisms",
author = "Liang, Qiliang and
Wang, Hansi and
Wang, Yue and
Liu, Yang",
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.164/",
pages = "3625--3649",
ISBN = "979-8-89176-439-2",
abstract = "Lexical evolution is universal across languages, yet the mechanisms driving neologism formation vary substantially from one language to another. In Chinese, this variation is particularly reflected in the productivity of compounding, where morphemes are combined through word-formation relations to create interpretable lexical forms. This morphological productivity implies that the Chinese lexicon can be viewed not only as a set of attested words, but also as a dynamically latent space with potential neologisms to be realized. However, this perspective still remains underexplored in computation, as current approaches are largely reactive, focusing on detecting attested words from corpora. This raises a question about word-formation itself: which morpheme combinations do the rules license beyond those that corpora already attest? Motivated by this, we propose a proactive creation paradigm for Chinese neologism research. We introduce a three-stage pipeline: KG-Based Candidate Generation, Morphological Discarding, and LLM-Based Filtering. We then probe the candidates with three complementary signals: expert judgment, model perplexity, and corpus attestation. The three signals agree: accepted candidates sit close to real words and clearly apart from rejected combinations. The pipeline yields 18,662 candidates with definitions, examples, and formation metadata, released as material for follow-up work, such as lexical gaps and lexical change. Overall, this study substantiates a proactive creation paradigm for Chinese neologism research, and uses it to characterize what Chinese word-formation rules license beyond what dictionaries have already recorded."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2026-create">
<titleInfo>
<title>You Can Create Words Rather Than Just Detect Them: Towards A New Paradigm of Chinese Neologisms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiliang</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Lexical evolution is universal across languages, yet the mechanisms driving neologism formation vary substantially from one language to another. In Chinese, this variation is particularly reflected in the productivity of compounding, where morphemes are combined through word-formation relations to create interpretable lexical forms. This morphological productivity implies that the Chinese lexicon can be viewed not only as a set of attested words, but also as a dynamically latent space with potential neologisms to be realized. However, this perspective still remains underexplored in computation, as current approaches are largely reactive, focusing on detecting attested words from corpora. This raises a question about word-formation itself: which morpheme combinations do the rules license beyond those that corpora already attest? Motivated by this, we propose a proactive creation paradigm for Chinese neologism research. We introduce a three-stage pipeline: KG-Based Candidate Generation, Morphological Discarding, and LLM-Based Filtering. We then probe the candidates with three complementary signals: expert judgment, model perplexity, and corpus attestation. The three signals agree: accepted candidates sit close to real words and clearly apart from rejected combinations. The pipeline yields 18,662 candidates with definitions, examples, and formation metadata, released as material for follow-up work, such as lexical gaps and lexical change. Overall, this study substantiates a proactive creation paradigm for Chinese neologism research, and uses it to characterize what Chinese word-formation rules license beyond what dictionaries have already recorded.</abstract>
<identifier type="citekey">liang-etal-2026-create</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.164/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>3625</start>
<end>3649</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T You Can Create Words Rather Than Just Detect Them: Towards A New Paradigm of Chinese Neologisms
%A Liang, Qiliang
%A Wang, Hansi
%A Wang, Yue
%A Liu, Yang
%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 liang-etal-2026-create
%X Lexical evolution is universal across languages, yet the mechanisms driving neologism formation vary substantially from one language to another. In Chinese, this variation is particularly reflected in the productivity of compounding, where morphemes are combined through word-formation relations to create interpretable lexical forms. This morphological productivity implies that the Chinese lexicon can be viewed not only as a set of attested words, but also as a dynamically latent space with potential neologisms to be realized. However, this perspective still remains underexplored in computation, as current approaches are largely reactive, focusing on detecting attested words from corpora. This raises a question about word-formation itself: which morpheme combinations do the rules license beyond those that corpora already attest? Motivated by this, we propose a proactive creation paradigm for Chinese neologism research. We introduce a three-stage pipeline: KG-Based Candidate Generation, Morphological Discarding, and LLM-Based Filtering. We then probe the candidates with three complementary signals: expert judgment, model perplexity, and corpus attestation. The three signals agree: accepted candidates sit close to real words and clearly apart from rejected combinations. The pipeline yields 18,662 candidates with definitions, examples, and formation metadata, released as material for follow-up work, such as lexical gaps and lexical change. Overall, this study substantiates a proactive creation paradigm for Chinese neologism research, and uses it to characterize what Chinese word-formation rules license beyond what dictionaries have already recorded.
%U https://aclanthology.org/2026.aacl-long.164/
%P 3625-3649
Markdown (Informal)
[You Can Create Words Rather Than Just Detect Them: Towards A New Paradigm of Chinese Neologisms](https://aclanthology.org/2026.aacl-long.164/) (Liang et al., AACL-IJCNLP 2026)
ACL