4 citations · 5 across the 9 of their papers we have counts for
9 papers
A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents
Sumit Soman, H. G. Ranjani, Sujoy Roychowdhury +4
Question-Answering (QA) from technical documents often involves questions whose answers are present in figures, such as flowcharts or flow diagrams. Text-based Retrieval Augmented…
Intelligibility of Text-to-Speech Systems for Mathematical Expressions
Sujoy Roychowdhury, H. G. Ranjani, Sumit Soman +3
There has been limited evaluation of advanced Text-to-Speech (TTS) models with Mathematical eXpressions (MX) as inputs. In this work, we design experiments to evaluate quality and…
Test code generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs
Sai Krishna, Balvinder Singh, Sujoy Roychowdhury +7
We describe test code generation using Large Language Models (LLMs) in Ericsson. Our input is a test step in natural language (English) and our output is code (Java) which accompli…
Knowledge Distillation of Domain-adapted LLMs for Question-Answering in Telecom
Rishika Sen, Sujoy Roychowdhury, Sumit Soman +2
Knowledge Distillation (KD) is one of the approaches to reduce the size of Large Language Models (LLMs). A LLM with smaller number of model parameters (student) is trained to mimic…
Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications
Sujoy Roychowdhury, Sumit Soman, HG Ranjani +3
With the ubiquitous use of document corpora for question answering, one important aspect which is especially relevant for technical documents is the ability to extract information…
Icing on the Cake: Automatic Code Summarization at Ericsson
Giriprasad Sridhara, Sujoy Roychowdhury, Sumit Soman +2
This paper presents our findings on the automatic summarization of Java methods within Ericsson, a global telecommunications company. We evaluate the performance of an approach cal…
Evaluation of RAG Metrics for Question Answering in the Telecom Domain
Sujoy Roychowdhury, Sumit Soman, H G Ranjani +3
Retrieval Augmented Generation (RAG) is widely used to enable Large Language Models (LLMs) perform Question Answering (QA) tasks in various domains. However, RAG based on open-sour…
Investigating Distributions of Telecom Adapted Sentence Embeddings for Document Retrieval
Sujoy Roychowdhury, Sumit Soman, Ranjani Hosakere Gireesha +4
A plethora of sentence embedding models makes it challenging to choose one, especially for technical domains rich with specialized vocabulary. In this work, we domain adapt embeddi…
Observations on Building RAG Systems for Technical Documents
Sumit Soman, Sujoy Roychowdhury
Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors aff…