Looks can be Deceptive: Distinguishing Repetition Disfluency from Reduplication
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910522974142464 |
|---|---|
| author | Ahmad, Arif Khyathi, Mothika Gayathri Bhattacharyya, Pushpak |
| author_facet | Ahmad, Arif Khyathi, Mothika Gayathri Bhattacharyya, Pushpak |
| contents | Reduplication and repetition, though similar in form, serve distinct linguistic purposes. Reduplication is a deliberate morphological process used to express grammatical, semantic, or pragmatic nuances, while repetition is often unintentional and indicative of disfluency. This paper presents the first large-scale study of reduplication and repetition in speech using computational linguistics. We introduce IndicRedRep, a new publicly available dataset containing Hindi, Telugu, and Marathi text annotated with reduplication and repetition at the word level. We evaluate transformer-based models for multi-class reduplication and repetition token classification, utilizing the Reparandum-Interregnum-Repair structure to distinguish between the two phenomena. Our models achieve macro F1 scores of up to 85.62% in Hindi, 83.95% in Telugu, and 84.82% in Marathi for reduplication-repetition classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08147 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Looks can be Deceptive: Distinguishing Repetition Disfluency from Reduplication Ahmad, Arif Khyathi, Mothika Gayathri Bhattacharyya, Pushpak Computation and Language Artificial Intelligence Reduplication and repetition, though similar in form, serve distinct linguistic purposes. Reduplication is a deliberate morphological process used to express grammatical, semantic, or pragmatic nuances, while repetition is often unintentional and indicative of disfluency. This paper presents the first large-scale study of reduplication and repetition in speech using computational linguistics. We introduce IndicRedRep, a new publicly available dataset containing Hindi, Telugu, and Marathi text annotated with reduplication and repetition at the word level. We evaluate transformer-based models for multi-class reduplication and repetition token classification, utilizing the Reparandum-Interregnum-Repair structure to distinguish between the two phenomena. Our models achieve macro F1 scores of up to 85.62% in Hindi, 83.95% in Telugu, and 84.82% in Marathi for reduplication-repetition classification. |
| title | Looks can be Deceptive: Distinguishing Repetition Disfluency from Reduplication |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.08147 |