Suparna De

I'm presenting a paper at the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing in Barcelona. Learn more! invt.io/1txbp9221os

Back from an exciting week of discussions around #NLP #trustworthyAI and efficient LLMs at #EMNLP2025. Honoured to have chaired two of the industry & panel discussion sessions.

🎓Happy to share that our paper on dual-branch LoRA for language-invariant embeddings has been accepted at @emnlpmeeting. This work launches a new research stream on language-agnostic sociological concept equivalence in our @ESRC-funded #MetacurateML project.

Pleased to report that the findings of our work on hierarchical sociological concept equivalence have been accepted as a #CIKM full paper; congratulations to my PhD student Zeqiang Wang & @ESRC-funded #MetacurateML project postdoc Justina Li! Paper and code coming soon.

Justina Li, postdoc on our @ESRC funded MetacurateML project, is presenting our paper "Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?" at #SIGIR2025 🇮🇹this week. Paper link: arxiv.org/abs/2504.20679

Excited to present our paper "Conversation Kernels: A flexible mechanism to learn relevant context for online conversation understanding" at @icwsm 2025. Catch me in Session 20 (June 26). Work with Arjoo, @supdey, @nishanthsastry at @UniOfSurrey. Paper: tinyurl.com/conv-kernels

The collaboration w/ Wei Wang @XJTLU & Maria B-Edo @CanalUGR on #IoT data models and #Context info is finally published: link.springer.com/book/10.1007/9…

Congratulations to my PhD student Zeqiang Wang & @yuqiw_ for their work on #longitudinal semantic shifts getting accepted @emnlpmeeting Findings. Co-supervised w/ WeiWang, @nishanthsastry & @spuddybike @CLOSER_UK. @MetadataUplift

This work led by @yuqiw_ & WeiWang @XJTLU addresses the extreme 0-shot #textclassification problem, integrating descriptive & structural knowledge from #KGs w/ an adversarial example generator for better performance & model robustness.

Our @ElsevierConnect Neurocomputing paper is now online: doi.org/10.1016/j.neuc…

Pleased to be in Manchester for @NCRMUK #MethodsCon where Jon Johnson @spuddybike is presenting our @ESRC-funded #FutureDataServices MetacurateML @MetadataUplift project. @CLOSER_UK @ScotCen

Our research in Scientific Reports presents a probabilistic label tree for structured ICD code prediction. This approach leverages the hierarchical structure of ICD labels, demonstrating competitive performance on the MIMIC-III database. Full details here. go.nature.com/3ZcFKRc

We present an end-to-end context-aware Text-to-Speech (TTS) synthesis system, combining a text classifier with a voice synthesis model, to derive the conveyed emotion from text input & synthesise audio embedding both emotion and speaker features.

Presenting our work with Ionut Bostan & @nishanthsastry on Emotion-aware #TTS @asonamcon in UniCal, Italy.

Are you developing a cool interactive system or running an exciting user study? Why don't we share your latest work with us? The metadata deadline for CHI 2025 Papers track is just a month ahead. Please consider to submit your work to CHI 2025! #CHI2025 buff.ly/45TkkK1

The Call for Papers (CFP) of #CHI2025 has been announced! The deadline for paper submissions is September 12th (AoE). Please remember that abstracts/metadata must be submitted by September 5th (AoE). For more detailed information, please visit:   buff.ly/45TkkK1

We are recruiting! If you have a PhD in NLP/ML & tackling challenges in #longitudinal #NLP sounds like something up your street, consider applying for this PDRA role in the @ESRC funded MetaCurate-ML project @ComputingSurrey jobs.surrey.ac.uk/031124

Job Alert! We are looking for a PDRA in #NLP and #ML, as part of our @ESRC-funded #FutureDataServices grant, at @ComputingSurrey. The successful candidates will collaborate with @CLOSER_UK @ucl, @UKDataService and @ScotCen. Apply by: 22 July 2024 jobs.surrey.ac.uk/031024

Excited to kick-off our #METACURATEML project, with @CLOSER_UK @ucl, @UKDataService & @ScotCen to generate #ML-driven #metadata and #data solutions which are #FAIR ready, using #GrowingupinScotland study as a pilot dataset. Grateful for funding from @ESRC #FutureDataService.

We are looking for a Senior NLP Data Scientist at Nokia Bell Labs Cambridge. Deadline: May 27th, 2024. social-dynamics.net/docs/positions…