Atul Gupta

Nilesh, Atul Gupta, Avinash C Panday

In document-level relation extraction, entities may appear multiple times in a document, and their relationships can shift from one context to another. Accurate prediction of the relationship between two entities across an entire document requires building a global context spanning all relevant sentences. Previous approaches have focused only on the sentences where entities are mentioned, which fails to capture the complete document context necessary for accurate relation extraction. Therefore, this paper introduces a novel input embedding approach to capture the positions of mentioned entities throughout the document rather than focusing solely on the span where they appear. The proposed input encoding approach leverages global relationships and multi-sentence reasoning by representing entities as standalone segments, independent of their positions within the document. The performance of the proposed method has been tested on three benchmark relation extraction datasets, namely DocRED, Re-DocRED, and REBEL. The experimental results demonstrated that the proposed method accurately predicts relationships between entities in a document-level setting. The proposed research also has theoretical and practical implications. Theoretically, it advances global context modeling and multi-sentence reasoning in document-level relation extraction. Practically, it enhances relationship detection, enabling improved performance in real-world NLP applications requiring comprehensive entity-level insights and interpretability.

Rashmi Gupta, Aditya K Gupta, Aarav Jain et al.

Like any other discipline, Large Language Models (LLMs) have significantly impacted software engineering by helping developers generate the required artifacts across various phases of software development. This paper presents a case study comparing the performance of popular LLMs GPT, Claude, Gemini, and DeepSeek in generating functional specifications that include use cases, business rules, and collaborative workflows for a web application, the Mess Management System. The study evaluated the quality of LLM generated use cases, business rules, and collaborative workflows in terms of their syntactic and semantic correctness, consistency, non ambiguity, and completeness compared to the reference specifications against the zero-shot prompted problem statement. Our results suggested that all four LLMs can specify syntactically and semantically correct, mostly non-ambiguous artifacts. Still, they may be inconsistent at times and may differ significantly in the completeness of the generated specification. Claude and Gemini generated all the reference use cases, with Claude achieving the most complete but somewhat redundant use case specifications. Similar results were obtained for specifying workflows. However, all four LLMs struggled to generate relevant Business Rules, with DeepSeek generating the most reference rules but with less completeness. Overall, Claude generated more complete specification artifacts, while Gemini was more precise in the specifications it generated.

Sawan Rai, Atul Gupta

Pseudo code is one of the valuable artifacts to comprehending the complex program codes. Most of the source code still has no equivalent pseudo code, due to the time-consuming process of writing pseudo codes. In this work, we have developed an approach to generate pseudo code from the python source code. In the first step, we convert python code into XML code for better code information extraction. Next, Important information extracted from the XML code, which later on used to generate actual pseudo code with the help of pseudo code templates. Initial performance results have been discussed in this paper.

Jitendra Singh Thakur, Atul Gupta

In object oriented software development, the analysis modeling is concerned with the task of identifying problem level objects along with the relationships between them from software requirements. The software requirements are usually written in some natural language, and the analysis modeling is normally performed by experienced human analysts. The huge gap between the software requirements which are unstructured texts and analysis models which are usually structured UML diagrams, along with human slip-ups inevitably makes the transformation process error prone. The automation of this process can help in reducing the errors in the transformation. In this paper we propose a tool supported approach for automated transformation of use case specifications documented in English language into analysis class diagrams. The approach works in four steps. It first takes the textual specification of a use case as input, and then using a natural language parser generates type dependencies and parts of speech tags for each sentence in the specification. Then, it identifies the sentence structure of each sentence using a set of comprehensive sentence structure rules. Next, it applies a set of transformation rules on the type dependencies and parts of speech tags of the sentences to discover the problem level objects and the relationships between them. Finally, it generates and visualizes the analysis class diagram. We conducted a controlled experiment to compare the correctness, completeness and redundancy of the analysis class diagrams generated by our approach with those generated by the existing automated approaches. The results showed that the analysis class diagrams generated by our approach were more correct, more complete, and less redundant than those generated by the other approaches.