EMNLP Findings2025
NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use
Yuqing Zhang, Ecesu Ürker, Tessa Verhoef, Gemma Boleda, Arianna Bisazza
Abstract
Lexical semantic change has primarily been investigated with observational and experimental methods; however, observational methods (corpus analysis, distributional semantic modeling) cannot get at causal mechanisms, and experimental paradigms with humans are hard to apply to semantic change due to the extended diachronic processes involved. This work introduces NeLLCom-Lex, a neural-agent framework designed to simulate semantic change by first grounding agents in a real lexical system (e.g. English) and then systematically manipulating their communicative needs. Using a well-established color naming task, we simulate the evolution of a lexical system within a single generation, and study which factors lead agents to: (i) develop human-like naming behavior and lexicons, and (ii) change their behavior and lexicons according to their communicative needs. Our experiments with different supervised and reinforcement learning pipelines show that neural agents trained to 'speak' an existing language can reproduce human-like patterns in color naming to a remarkable extent, supporting the further use of NeLLCom-Lex to elucidate the mechanisms of semantic change.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Why do objects have many names? A study on word informativeness in language use and lexical systems cites Bridging semantics and pragmatics in information-theoretic emergent communication
- Entropy Minimization In Emergent Languages cites Compositionality and Generalization In Emergent Languages
Builds on6
- Compositionality and Generalization In Emergent LanguagesRahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux et al.ACL 2020 · 40 citations
- Entropy Minimization In Emergent LanguagesEugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco BaroniICML 2020 · 39 citations
- Bridging semantics and pragmatics in information-theoretic emergent communicationEleonora Gualdoni, Mycal Tucker, Roger Levy, Noga ZaslavskyNeurIPS 2024 · 7 citations
- Why do objects have many names? A study on word informativeness in language use and lexical systemsEleonora Gualdoni, Gemma BoledaEMNLP 2024 · 2 citations
- Revisiting Populations in multi-agent CommunicationPaul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman et al.ICLR 2023
Related papers
- Grammar-Based Grounded Lexicon LearningJiayuan Mao, Freda Shi, Jiajun Wu, Roger Levy et al.NeurIPS 2021 · 19 citations
- Analyzing Semantic Change through Lexical ReplacementsFrancesco Periti, Pierluigi Cassotti, Haim Dubossarsky, Nina TahmasebiACL 2024
- On the Correspondence between Compositionality and Imitation in Emergent Neural CommunicationEmily Cheng, Mathieu Rita, Thierry PoibeauACL Findings 2023
- Evolution and compression in LLMs: on the emergence of human-aligned categorizationNathaniel Imel, Noga ZaslavskyICLR 2026 · 2 citations
- Trading off Utility, Informativeness, and Complexity in Emergent CommunicationMycal Tucker, Roger Levy, Julie A. Shah, Noga ZaslavskyNeurIPS 2022 · 34 citations
