@inproceedings{a-etal-2026-jerinwarriors,
    title = "{J}erin{W}arriors@{D}ravidian{L}ang{T}ech 2026: A Two-Stream Cross-Attention Approach for Prompt Recovery in {T}elugu",
    author = "A, Savith  and
      Robert, Wordson  and
      C, Jerin Mahibha  and
      Patnaik, Shrey",
    editor = "Chakravarthi, Bharathi Raja  and
      Priyadharshini, Ruba  and
      Madasamy, Anand Kumar  and
      Thavareesan, Sajeetha  and
      Rajiakodi, Saranya  and
      Navaneethakrishnan, Subalalitha  and
      Chinnappa, Dhivya  and
      Palani, Balasubramanian  and
      Subramanian, Malliga  and
      Shanmugavadivel, Kogilavani  and
      Rajalakshmi, Ratnavel",
    booktitle = "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for {D}ravidian Languages",
    month = jul,
    year = "2026",
    address = "Underline (Virtual)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.dravidianlangtech-1.42/",
    pages = "279--283",
    ISBN = "979-8-89176-401-9",
    abstract = "Identifying the structure of detailed sentences which show glimpses of various annotation cues, in a low resource language that is morphological rich like Telugu is a challenge. Standard baseline architectures like Multi Layer Perceptrons (MLP) struggle with low resource languages. This paper details our proposed solution for the Telugu Prompt-Style Recovery Shared Task at DravidianLangTech @ ACL 2026. We propose a Two-Stream Cross-Attention architecture that uses a shared MuRIL encoder to calculate the relationship between an original transcript and its style-shifted counterpart, helping the MLP to distinguish the styles better and catch the differences better. Through experimentation we have found out that this proposed model handles the signal dilution of the individual labels better than the rest. Our best-performing system achieved a Macro F1-score of 0.2588 on the test set, securing 2nd place out of 13 teams. We have concluded that the local transformation is the main driver for the style recovery in this task. For reproducibility, we release our implementation and experimental setup on GitHub."
}