@article{10.1145/3712060,
author = {Joshi, Aditya and Dabre, Raj and Kanojia, Diptesh and Li, Zhuang and Zhan, Haolan and Haffari, Gholamreza and Dippold, Doris},
title = {Natural Language Processing for Dialects of a Language: A Survey},
year = {2025},
issue_date = {June 2025},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {57},
number = {6},
issn = {0360-0300},
url = {https://doi.org/10.1145/3712060},
doi = {10.1145/3712060},
abstract = {State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German, among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and extends to several NLU and NLG tasks. For these tasks, we describe classical machine learning using statistical models, along with the recent deep learning-based approaches based on pre-trained language models. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.},
journal = {ACM Comput. Surv.},
month = feb,
articleno = {149},
numpages = {37},
keywords = {NLP, dialects, natural language processing, linguistic diversity, large language models, inclusion}
}

@inproceedings{srirag-etal-2026-triage,
    title = "From Triage to Discharge: A Survey of {NLP} Tasks, Methods, and Open Challenges in the Emergency Department",
    author = "Srirag, Dipankar  and
      Joshi, Aditya  and
      Kanhere, Salil S.  and
      Narasimhan, Padmanesan",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.908/",
    pages = "20918--20942",
    ISBN = "979-8-89176-459-0"
}

@inproceedings{doan-etal-2026-benchmark,
    title = "A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-Related Documents",
    author = "Doan, Bao Gia  and
      Joshi, Aditya  and
      Elinas, Pantelis  and
      Bodhankar, Aarya  and
      Leslie, Oscar  and
      Marchant, Tom  and
      Salim, Flora D.",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.944/",
    pages = "21747--21775",
    ISBN = "979-8-89176-459-0"
}

@inproceedings{liyanarachchi26_interspeech,
  title     = {{Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion}},
  author    = {Rashini Liyanarachchi and Rachael Mackay and Alison Short and Aditya Joshi and Erik Meijering},
  year      = {2026},
  booktitle = {{Interspeech 2026}},
  pages     = {5600--5604},
  doi       = {10.21437/Interspeech.2026-1131},
  issn      = {2958-1796},
}

@misc{shetty2026vinoveritasvulnerabilitiesexamining,
    title={In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement},
    author={Anudeex Shetty and Aditya Joshi and Salil S. Kanhere},
    year={2026},
    eprint={2601.22169},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2601.22169},
}