Neuro-Symbolic Approach to Augmented Text Generation via Automated Induction of Morphotactic Rules
Main Article Content
Abstract
The work presents a hybrid neuro-symbolic method that combines a large language model (LLM) and a finite-state transducer (FST) to ensure morphological correctness in text generation for agglutinative languages. The system automatically extracts rules from corpus data: for local examples of word forms, the LLM produces sequences of morphological analyses, which are then aggregated and organized into compact descriptions of morphotactic rules (LEXC) and allomorph selection (regex). During generation, the LLM and FST operate jointly: if a token is not recognized by the automaton, the LLM derives a “lemma+tags” pair from the context, and the FST produces the correct surface form. A literary corpus (~1600 sentences) was used as the dataset. For a list of 50 nouns, 250 word forms were extracted. Using the proposed algorithm, the LLM generated 110 context-sensitive regex rules along with LEXC morphotactics, from which an FST was compiled that recognized 170/250 forms (~70%). In an applied machine translation test on a subcorpus of 300 sentences, integrating this FST into the LLM cycle improved quality from BLEU 16.14 / ChrF 45.13 to BLEU 25.71 / ChrF 50.87 without retraining the translator. The approach scales to other parts of speech (verbs, adjectives, etc.) as well as to other agglutinative and low-resource languages, where it can accelerate the development of lexical and grammatical resources.
Article Details
References
2. Kann K., Cotterell R., Schütze H. Neural models of inflectional morphology // Proceedings of the 15th Conference of the European Chapter of the ACL (EACL 2017). Valencia, 2017. P. 322–334.
3. Mielke S., Eisenstein J., Cotterell R. Dialect-to-dialect translation and cross-dialect morphological robustness of language models // Transactions of the ACL. 2021. Vol. 9. P. 288–302.
4. Koskenniemi K. Two-level morphology: a general computational model for word-form recognition and production. Helsinki: University of Helsinki, Department of General Linguistics, 1983. 38 p.
5. Beesley K.R., Karttunen L. Finite-State Morphology. Stanford (CA): CSLI Publications, 2003. 550 p.
6. Stahlberg F., Hasler E., Waite A. SGNMT: A flexible NMT decoding toolkit for quick prototyping of new models // Proceedings of ACL System Demonstrations. Vancouver, 2017. P. 67–72.
7. Hulden M. FST-based grammar correction for richly inflected languages // Proceedings of ACL Workshop on Finite-State Methods. Montréal, 2012. P. 32–39.
8. Tamchyna A., Bojar O. Target-side context for morphological reinflection // Proceedings of the First Conference on Machine Translation (WMT 2016). Berlin, 2016. P. 586–594.
9. Schwartz L., Liu S., Surrain S. Bootstrapping a neural morphological analyzer from an existing FST // Proceedings of the ACL Workshop on Morphological Resources 2022. Seattle, 2022. P. 12–20.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.