Elamur Research⌕
☰
home / papers / 2025 / ASC analyzer: A Python package for measuring argument structure construction usage in English texts

ASC analyzer: A Python package for measuring argument structure construction usage in English texts

Summary

The authors present ASC analyzer, an open-source Python package. It automatically measures how argument structure constructions (ASCs) are used in English texts. These are clausal patterns in which the main verb combines with a particular set of arguments. Researchers in second language (L2) acquisition have long regarded such constructions as an indicator of linguistic proficiency, but scalable tools for counting them have been lacking. The package uses a RoBERTa-based tagger previously developed by the authors and trained on a manually annotated treebank of L1 and L2 texts. The tagger distinguishes nine ASC types. From the resulting annotation, the package computes 50 indices. They describe the diversity of constructions, the proportion of each type, their frequency, and the strength of association between a construction and the verb lemma. Frequency and association strength are calculated relative to norms derived from large reference corpora. As a demonstration, the authors analyzed 6,482 essays from the ELLIPSE corpus. A model based solely on ASC indices explained more variance in writing scores than a model based on traditional measures of syntactic complexity. Adding ASC indices to lexico-grammatical ones also improved prediction. The tool is useful for automated writing assessment and L2 corpus research.

Key points

  • The RoBERTa tagger (the Gold L1+L2 model) achieves an F1 of 0.915 on written L2 texts and 0.928 on spoken L2 speech. Norms for the reference corpora were obtained with the Gold L1 model.
  • The reference norms come from two corpora: a subset of EnCOW (about 361 million tokens, nearly 40 million ASCs) and SUBTLEX-US (about 77 million tokens of subtitles, approximately 5.7 million ASCs).
  • On ELLIPSE, the strongest positive correlation with writing scores is for ascMATTR (r = 0.26), and the strongest negative correlation is for ascAvFreq (r = −0.22).
  • A regression with 12 ASC predictors yielded an adjusted R² = 0.143. A model based on syntactic complexity measures yielded only 0.077. Adding ASC indices to the lexico-grammatical baseline set increases adjusted R² from 0.363 to 0.390.
  • The package is installed via pip install asc-analyzer, requires spaCy with en_core_web_trf, and has a CLI that saves the indices to CSV. The code is available on GitHub (hksung/ASC-analyzer).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

Cite as Hakyung Sung and Kristopher Kyle. 2025. ASC analyzer: A Python package for measuring argument structure construction usage in English texts. Proceedings of the Second International Workshop on Construction Grammars and NLP.

The paper itself, not this page. BibTeX from the library's record of the work. arXiv 2510.10384

@inproceedings{sung2025asc,
  title = {{ASC analyzer: A Python package for measuring argument structure construction usage in English texts}},
  author = {Hakyung Sung and Kristopher Kyle},
  booktitle = {Proceedings of the Second International Workshop on Construction Grammars and NLP},
  year = {2025},
  eprint = {2510.10384},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.10384}
}

References

35 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Nick C Ellis and Fernando Ferreira-Junior. 2009. Construction learning as a function of frequency, frequency distribution, and function. The Modern language journal, 93(3):370–385. ↗
  2. Hirotugu Akaike. 2003. A new look at the statistical model identification. IEEE transactions on automatic control, 19(6):716–723. find
  3. Douglas Biber, Bethany Gray, and Shelley Staples. 2016. Predicting patterns of grammatical complexity across language exam task types and proficiency levels. Applied Linguistics, 37(5):639–668. find
  4. Nick C Ellis and Diane Larsen-Freeman. 2009. Constructing a second language: Analyses and computational simulations of the emergence of linguistic constructions from usage. Language Learning, 59:90– 125. ↗
  5. Marc Brysbaert and Boris New. 2009. Moving beyond kučera and francis: A critical evaluation of current word frequency norms and the introduction of a new and improved word frequency measure for american english. Behavior research methods, 41(4):977–990. find
  6. Charles J Fillmore. 1988. The mechanisms of” construction grammar”. In Annual Meeting of the Berkeley Linguistics Society, pages 35–55. find
  7. Adele E Goldberg. 1995. Constructions: A construction grammar approach to argument structure. University of Chicago Press. find
  8. Marc Brysbaert, Boris New, and Emmanuel Keuleers. 2012. Adding part-of-speech information to the subtlex-us word frequencies. Behavior research methods, 44:991–997. find
  9. Adele E Goldberg. 2013. Argument structure constructions versus lexical rules or derivational verb templates. Mind & Language, 28(4):435–465. find
  10. Bram Bulté and Alex Housen. 2012. Defining and op-erationalising l2 complexity. Dimensions of L2 performance and proficiency: Complexity, accuracy and fluency in SLA, 32:21. find
  11. Stefan Th Gries and Nick C Ellis. 2015. Statistical measures for usage-based linguistics. Language Learning, 65(S1):228–255. ↗
  12. Bram Bulté, Alex Housen, and Gabriele Pallotti. 2025. Complexity and difficulty in second language acquisition: A theoretical and methodological overview. Language Learning, 75(2):533–574. find
  13. Kellogg W Hunt. 1965. Grammatical structures written at three grade levels. 8. National Council of Teachers of English. find
  14. Haerim Hwang and Hyunwoo Kim. 2023. Automatic analysis of constructional diversity as a predictor of efl students’ writing proficiency. Applied Linguistics, 44(1):127–147. ↗
  15. Magali Paquot. 2018. Phraseological competence: A missing component in university entrance language tests? insights from a study of efl learners’ use of statistical collocations. Language Assessment Quarterly, 15(1):29–43. find
  16. Jeeyoung Jeon. 2024. A corpus-based analysis of english argument structure constructions in esl learner writings. Master’s thesis, Seoul National University. Unpublished master’s thesis. find
  17. Ute Römer, Matthew Brook O’Donnell, and Nick C Ellis. 2014. Second language learner knowledge of verb–argument constructions: Effects of language transfer and typology. The Modern Language Journal, 98(4):952–975. find
  18. Hyunwoo Kim and Eunseok Ro. 2023. Assessment of sentence sophistication in l2 spoken production: Expansion of verbs and argument structure constructions. System, 119:103175. find
  19. Roland Schäfer. 2015. Processing and querying large web corpora with the cow14 architecture. In Proceedings of the 3rd Workshop on Challenges in the Management of Large Corpora, pages 28–34. find
  20. Hyunwoo Kim, Gyu-Ho Shin, and Min-Chang Sung. 2023. Constructional complexity as a predictor of korean efl learners’ writing proficiency. Revista Española de Lingüı́stica Aplicada/Spanish Journal of Applied Linguistics, 36(2):436–466. find
  21. Roland Schäfer and Felix Bildhauer. 2012. Building large corpora from the web using a new efficient tool chain. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 486–493, Istanbul, Turkey. European Language Resources Association (ELRA). our card
  22. Kristopher Kyle. 2016. Measuring syntactic development in L2 writing: Fine grained indices of syntactic complexity and usage-based indices of syntactic sophistication. Ph.D. thesis, Georgia State University, Atlanta, GA. find
  23. Anatol Stefanowitsch and Stefan Th Gries. 2003. Col-lostructions: Investigating the interaction of words and constructions. International journal of corpus linguistics, 8(2):209–243. Kristopher. find
  24. Kyle and Scott Crossley. 2017. Assessing syntactic sophistication in l2 writing: A usage-based approach. Language Testing, 34(4):513–535. find
  25. Hakyung Sung and Kristopher Kyle. 2024a. Annotation scheme for English argument structure constructions treebank. In Proceedings of The 18th Linguistic Annotation Workshop (LAW-XVIII), pages 12–18, St. Julians, Malta. Association for Computational Linguistics (ACL). our card
  26. Kristopher Kyle and Masaki Eguchi. 2023. Assessing spoken lexical and lexicogrammatical proficiency using features of word, bigram, and dependency bigram use. The Modern Language Journal, 107(2):531– 564. find
  27. Hakyung Sung and Kristopher Kyle. 2024b. Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7302–7314, Miami, Florida, USA. Association for Computational Linguistics. find
  28. Kristopher Kyle and Hakyung Sung. 2023. An argument structure construction treebank. In Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+ NLP, GURT/SyntaxFest 2023), pages 51–62. our card
  29. Ronald W Langacker. 1987. Nouns and verbs. Language, pages 53–94. ↗
  30. Hakyung Sung and Kristopher Kyle. 2025. Usage-based analysis of l2 oral proficiency: Characteristics of argument structure construction use. Studies in Second Language Acquisition, page 1–27. find
  31. Xiaofei Lu. 2011. A corpus-based evaluation of syntactic complexity measures as indices of college-level esl writers’ language development. TESOL quarterly, 45(1):36–62. find
  32. Y.J̃. Tan, M. and Rahul Biswas. 2012. The reliability of the akaike information criterion method in cosmolog-ical model selection. Monthly Notices of the Royal Astronomical Society, 419(4):3292–3303. find
  33. Anat Ninio. 1999. Pathbreaking verbs in syntactic development and the question of prototypical transitivity. Journal of child language, 26(3):619–653. ↗
  34. Lourdes Ortega. 2003. Syntactic complexity measures and their relationship to l2 proficiency: A research synthesis of college-level l2 writing. Applied linguistics, 24(4):492–518. find
  35. Matthew O’Donnell and Nick Ellis. 2010. Towards an inventory of english verb argument constructions. In Proceedings of the NAACL HLT Workshop on Extracting and Using Constructions in Computational Linguistics, pages 9–16. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sung-2025-asc-analyzer-python-package-measuring/