A Character-Level Neural Approach to Sinhala Sandhi Splitting A bidirectional LSTM encoder with a unidirectional LSTM decoder achieved 68.40% exact-match accuracy and 82.08% character-level accuracy on the hard subset of Sinhala Sandhi splitting, and 94.00% exact-match accuracy on the full affixational subset, according to a study by Yasas Ekanayaka and Deshan Sumanathilaka published in Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026 (pages 257–266). The character-level sequence-to-sequence work, built on the SandhiLex dataset with native Sinhala Unicode input, establishes what the authors describe as the first empirical neural baseline for the task, which prior published work had not benchmarked. Ablations showed bidirectional encoding contributed most to performance and native Sinhala script improved exact match over romanized input, with the authors naming data scale, Sandhi type conditioning and attention-based decoding as future directions. Abstract Sinhala Sandhi splitting recovers the constituent words or morphemes hidden inside a phonologically merged surface form. The task is important for Sinhala NLP because Sandhi obscures lexical boundaries, but no prior published work has established a neural benchmark for Sinhala Sandhi splitting. We present a character-level sequence-to-sequence study based on SandhiLex, using native Sinhala Unicode input and evaluating recurrent encoder-decoder models for affixational and more complex lexicalized, derivational, and etymological Sandhi. A bidirectional LSTM encoder with a unidirectional LSTM decoder yields the best results on the hard subset, achieving 68.40% exact-match accuracy and 82.08% character-level accuracy. On the full affixational subset, the same model achieves 94.00% exact-match accuracy. Ablations show that bidirectional encoding is the largest contributor to performance, while native Sinhala script improves exact match accuracy over romanized input. Qualitative analysis indicates that many errors are near misses involving boundary adjacent characters or plausible but incorrect phonological substitutions. These results establish an empirical baseline for Sinhala Sandhi splitting and identify data scale, Sandhi type conditioning, and attention-based decoding as the main directions for future work. - Anthology ID: - 2026.findings-aacl.14 - Volume: - Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026 https://aclanthology.org/volumes/2026.findings-aacl/ - Month: - November - Year: - 2026 - Address: - Hengqin, China - Editors: - Yue Zhang https://aclanthology.org/people/yue-zhang/unverified/ , Ruifeng Xu https://aclanthology.org/people/ruifeng-xu/ , Ayu Purwarianti https://aclanthology.org/people/ayu-purwarianti/ , Tong Rong https://aclanthology.org/people/tong-rong/unverified/ , Jun Suzuki https://aclanthology.org/people/jun-suzuki/ - Venue: - Findings https://aclanthology.org/venues/findings/ - SIG: - Publisher: - Association for Computational Linguistics - Note: - Pages: - 257–266 - Language: - URL: - https://aclanthology.org/2026.findings-aacl.14/ https://aclanthology.org/2026.findings-aacl.14/ - DOI: - Cite ACL : - Yasas Ekanayaka and Deshan Sumanathilaka. 2026. A Character-Level Neural Approach to Sinhala Sandhi Splitting https://aclanthology.org/2026.findings-aacl.14/ . In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026 , pages 257–266, Hengqin, China. Association for Computational Linguistics. - Cite Informal : - A Character-Level Neural Approach to Sinhala Sandhi Splitting https://aclanthology.org/2026.findings-aacl.14/ Ekanayaka & Sumanathilaka, Findings 2026 - PDF: - https://aclanthology.org/2026.findings-aacl.14.pdf https://aclanthology.org/2026.findings-aacl.14.pdf