mlsanityData to 7 Oct 2026

Morpheme Induction for Emergent Language

arXiv 2510.03439 ↗First posted 3 Oct 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce CSAR, an algorithm for inducing morphemes from emergent language corpora of parallel utterances and meanings. It is a greedy algorithm that (1) weights morphemes based on mutual information between forms and meanings, (2) selects the highest-weighted pair, (3) removes it from the corpus, and (4) repeats the process to induce further morphemes (i.e., Count, Select, Ablate, Repeat). The effectiveness of CSAR is first validated on procedurally generated datasets and compared against baselines for related tasks. Second, we validate CSAR's performance on human language data to show that the algorithm makes reasonable predictions in adjacent domains. Finally, we analyze a handful of emergent languages, quantifying linguistic characteristics like degree of synonymy and polysemy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 50 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

15 of 50 references.

References · 15

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
  4. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  5. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
  6. 2019Anti-efficient encoding in emergent communicationcited by 59
  7. 2019EGG: a toolkit for research on Emergence of lanGuage in Gamescited by 42
  8. 2021Emergent Communication of Generalizationscited by 41
  9. 2017ShapeWorld - A new test methodology for multimodal language understandingcited by 37
  10. 2022The SIGMORPHON 2022 Shared Task on Morpheme Segmentationcited by 25
  11. 2020Emergent Language Generalization and Acquisition Speed are not tied to Compositionalitycited by 17
  12. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
3 more
  1. 2020Measuring non-trivial compositionality in emergent communicationcited by 10
  2. 2020The Grammar of Emergent Languagescited by 9
  3. 2024Speaking Your Language: Spatial Relationships in Interpretable Emergent Communicationcited by 3

Built on by

Not cited yet.