Dr Yaji Sripada | The 51cg

Dr Yaji Sripada

Senior Lecturer

Email Address: yaji.sripada@abdn.ac.uk
Telephone Number: +44 (0)1224 272597
Office Address: 327 Meston Building
Old Aberdeen Campus
Meston Walk
AB24 3UE
View on Map
School/Department: School of Natural and Computing Sciences

Biography

I am a Senior Lecturer in the Department of Computing Science. I joined the department as a PDRA (Post-Doctoral Research Associate) in 2000. I was promoted to Lecturer in 2003. Before joining the university, I worked as a Research Scientist for Tata Consultancy Services, India, after completing my PhD in Computer Science and Engineering from the Indian Institute of Technology, Madras, India, in 1998.

Qualifications

PhD Computer Science and Engineering
1998 - Indian Institute of Technology, Madras, India
MTech Computer Science
1991 - Indian Institute of Technology, Roorkee
BSc Electrical Engineering
1989 - National Institute of Technology, Kurukshetra, India

Memberships and Affiliations

Internal Memberships: Current:

Enterprise and Innovation Champion for the School of Natural and Computing Sciences

Industrial Placements Coordinator for Computing Science

Previous:

Interim Head of Computing Science

Director of Undergraduate Pathways in Computing Science

Outreach Director for Computing Science
External Memberships: Member of the Engineering and Physical Sciences Research Council (EPSRC) Peer Review College since 2016.

Reviewer for the European Research Council (ERC) since 2021.

Research

Research Overview

Sitting at the intersection of human-centred AI and automated data science, my research seeks to facilitate two-way communication between users and machines across the ML/data science life cycle. I develop frameworks that incorporate human expertise into automated pipelines, keeping users informed about a model's fairness, ethics, accountability, and transparency (FEAT). This work integrates ML/data science, knowledge-based programming, natural language processing (NLP), and information visualisation (InfoVis). I am an inventor on several US patents related to natural language-based AI technology. I am one of the founders of Arria (), a company specialising in data-to-text (D2T) natural language generation (NLG).

Research Areas

Artificial Intelligence

Supervising

View Research Area

Teaching

Programmes

BSc Computing Science
Undergraduate, 4 year, September start
BSc Computing Science and Mathematics
Undergraduate, 4 year, September start
BSc Computing Science and Physics
Undergraduate, 4 year, September start
MA Computing
Undergraduate, 4 year, September start
MA Computing and Music
Undergraduate, 4 year, September start
MSci Computing Science with Industrial Placement
Undergraduate, 5 year, September start
MSc Artificial Intelligence
Postgraduate, 3 semester, September start
MSc Artificial Intelligence
Postgraduate, 3 stage, January start
MSc Information Technology
Postgraduate, 3 stage, September start

Courses

Publications

Update

51cg

Biography

Qualifications

Memberships and Affiliations

Research Overview

Research Areas

Artificial Intelligence

Programmes

Courses

Authoring and Management of Transparent Research Integrity Assessments of Randomised Clinical Trial Publications Using LLM-assisted Tools and Provenance Knowledge Graphs

Integrating Sensemaking in a Question-Driven Development Framework for Textual Narrative Reporting Applications

AEMC: Aggregator-efficient model compression for streamlining LLMs

Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Play

Stereotypical Bias Amplification, and Reversal, in an Experimental Model of Human Interaction with Generative AI

Response to UKIPO Consultation on Copyright and Artificial Intelligence

Towards LLM-driven Automated Verification of Best Practices in Digital Public Infrastructures

Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo

Systems, computer-implemented methods, and computer program products for data sequence validity processing

Consultation Response to the UK Government’s Policy Proposals on AI Regulation: A Pro-Innovation Approach

Method and apparatus for expressing time in an output text

Error Analysis of ToTTo Table-to-Text Neural NLG Models

An approach to improve asset maintenance and management priorities using machine learning techniques

Auto-generating textual data stories using data science pipelines

Are contrastive explanations useful?

Studying the Impact of Filling Information Gaps on the Output Quality of Neural Data-to-Text

Method and apparatus for motion detection

On the merits and pitfalls of introducing a digital platform to aid conservation management: Volunteer data submission and the mediating role of volunteer coordinators

TravelBot: Utilising social media dialogue to provide journey disruption alerts

Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment

Towards making NLG a voice for interpretable Machine Learning

Method and apparatus for motion description

Build an app and they will come? Lessons learnt from trialling the GetThereBus app in rural communities

Data quality in reasoning

Comprehension Driven Document Planning in Natural Language Generation Systems

Textually Summarising Incomplete Data

Persuasive Strategies for Encouraging Social Interaction for Older Adults

Exploring the rural passenger experience, information needs and decision making during public transport disruption

Environmental communication in the Information Age: Institutional barriers and opportunities in the provision of river data to the general public

Absolute and Relative Properties in Geographic Referring Expressions

The effects of mobile real-time information on rural passengers

Supply of Online Environmental Information to Unknown Demand: The Importance of Interpretation and Liability Related to a National Network of River Level Data

Lessons learned from the development of a rural real time passenger information system

A simple surface realization engine for Telugu

Designing an Algorithm for Generating Named Spatial References

TravelBot: Journey Disruption Alerts Utilising Social Media and Linked Data

Adapting SimpleNLG for Brazilian Portuguese realisation

Determining Content for Unknown Users: Lessons from the MinkApp Case Study

Evaluating Perceived Effectiveness of Persuasive Strategies for Encouraging Social Interaction

Latent user models for online river information tailoring

People, Plans and Place: Understanding and Supporting Responses to Rural Public Transport Disruption

Development of a Map-matching Algorithm for Rural Passenger Information Systems Through Mobile Phones and Crowd-Sourcing

Development of a Map-Matching Algorithm for Rural Passenger Information Systems through Mobile Phones and Crowd Sourcing

A Dynamic Persuasive Dialogue Model for Encouraging Social Interaction for Older Adults

Persuasive Dialogue for Older Adults: Promoting and Encouraging Social Interaction

Supporting rural public transport users during disruption: The role of real time information.

Developing a real time passenger information system for rural areas

Examining the effects of disruption on travel behaviour in rural areas

Integrating natural language generation and model-based reasoning for explanation generation

Communicating river level data and information to stakeholders with different interests: The participative development of an interactive online service

Automatic generation of natural language nursing shift summaries in neonatal intensive care: BT-Nurse

A Rural Passenger Information System Utilising Linked Data The Crowd

A rural real-time passenger information ecosystem

Atlas.txt: Exploring Lingusitic Grounding Techniques for Communicating Spatial Information to Blind Users

A Hybrid Map-matching Algorithm for Real Time Passenger Information Systems via Mobile Phones and Crowd-Sourcing

Development of a Map-matching Algorithm for Rural Passenger Information Systems via Mobile Phones and Crowd-Sourcing

MinkApp: Generating spatio-temporal summaries for nature conservation volunteers

Building an Information Ecosystem for Public Transport in Rural Areas

Exploiting Digital Technologies to Promote Sustainable Travel Behaviour in Rural Areas

Generating approximate geographic descriptions

Moving from data to text using causal statements in explanatory narratives

Case retrieval reuse net (CR2N): An architecture for reuse of textual solutions

Using temporal constraints to integrate signal analysis and domain knowledge in medical event detection

Le projet BabyTalk: génération de texte à partir de données hétérogènes pour la prise de décision en unité néonatale

Automatic generation of textual summaries from neonatal intensive care data

Generating Approximate Geographic Descriptions

From Data to Text in the Neonatal Intensive Care Unit: Using NLG Technology for Decision Support and Information Management

Enabling access to geo-referenced information: Atlas.txt

Summarising complex ICU data in natural language: demonstration of the BT-45 system.

Using Natural Language Generation Technology to Improve Information Flows in Intensive Care Units

What's in a message? Interpreting Geo-referenced Data for the Visually-Impaired