Dwaipayan Roy

Sourav Saha, Dwaipayan Roy, Mandar Mitra

Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems. However, addressing complex questions, the answers to which are spread across multiple documents, remains a challenging problem. Recent QA systems that are designed to handle complex questions work either on the basis of knowledge graphs, or utilise contem- porary neural models that are expensive to train, in terms of both computational resources and the volume of training data required. In this paper, we present LiCQA, an unsupervised question answer- ing model that works primarily on the basis of corpus evidence. We empirically compare the effectiveness and efficiency of LiCQA with two recently presented QA systems, which are based on different underlying principles. The results of our experiments show that LiCQA significantly outperforms these two state-of-the-art systems on benchmark data with noteworthy reduction in latency.

Mehmet Deniz Türkmen, Suchana Datta, Dwaipayan Roy et al.

Users increasingly expect modern search systems to offer a unified interface that seamlessly retrieves information from diverse data sources and formats. However, current information retrieval (IR) evaluation benchmarks have not kept pace with this development, primarily due to the lack of test collections that represent the diversity of contemporary search domains. We address this critical gap with MIRA, a novel benchmark based on a large-scale social science search platform. MIRA is designed for category-aware ranking across heterogeneous categories - Publications, Research Data, Variables, and Instruments & Tools - within a single, unified evaluation framework. The proposed collection is distinctive in several ways: (1) it is built upon real user queries, providing a more realistic basis for evaluation; (2) it covers scholarly items from four distinct categories, enabling multi-faceted evaluation; and (3) it leverages a Large Language Model to generate topic descriptions and narratives, as well as for relevance assessment with respect to these topics, substantially reducing the labor and cost of test collection generation. We release this resource to benefit the community by providing a foundational testbed for the research on multi-faceted, category-aware, integrated, or cross-category information retrieval.

Soumyadeep Sar, Dwaipayan Roy

This study investigates the several nuanced rationales for countering the rise of political bias. We evaluate the performance of the Llama-3 (70B) language model on the Media Bias Identification Benchmark (MBIB), based on a novel prompting technique that incorporates subtle reasons for identifying political leaning. Our findings underscore the challenges of detecting political bias and highlight the potential of transfer learning methods to enhance future models. Through our framework, we achieve a comparable performance with the supervised and fully fine-tuned ConvBERT model, which is the state-of-the-art model, performing best among other baseline models for the political bias task on MBIB. By demonstrating the effectiveness of our approach, we contribute to the development of more robust tools for mitigating the spread of misinformation and polarization. Our codes and dataset are made publicly available in github.

Shuvam Banerji Seal, Aheli Poddar, Alok Mishra et al.

This paper introduces AgriIR, a configurable retrieval augmented generation (RAG) framework designed to deliver grounded, domain-specific answers while maintaining flexibility and low computational cost. Instead of relying on large, monolithic models, AgriIR decomposes the information access process into declarative modular stages -- query refinement, sub-query planning, retrieval, synthesis, and evaluation. This design allows practitioners to adapt the framework to new knowledge verticals without modifying the architecture. Our reference implementation targets Indian agricultural information access, integrating 1B-parameter language models with adaptive retrievers and domain-aware agent catalogues. The system enforces deterministic citation, integrates telemetry for transparency, and includes automated deployment assets to ensure auditable, reproducible operation. By emphasizing architectural design and modular control, AgriIR demonstrates that well-engineered pipelines can achieve domain-accurate, trustworthy retrieval even under constrained resources. We argue that this approach exemplifies ``AI for Agriculture'' by promoting accessibility, sustainability, and accountability in retrieval-augmented generation systems.

Thomas Krämer, Zeljko Carevic, Dwaipayan Roy et al.

In this demo paper, we present ConSTR, a novel Contextual Search Term Recommender that utilises the user's interaction context for search term recommendation and literature retrieval. ConSTR integrates a two-layered recommendation interface: the first layer suggests terms with respect to a user's current search term, and the second layer suggests terms based on the users' previous search activities (interaction context). For the demonstration, ConSTR is built on the arXiv, an academic repository consisting of 1.8 million documents.

Zeljko Carevic, Dwaipayan Roy, Philipp Mayr

Secondary analysis or the reuse of existing survey data is a common practice among social scientists. Searching for relevant datasets in Digital Libraries is a somehow unfamiliar behaviour for this community. Dataset retrieval, especially in the social sciences, incorporates additional material such as codebooks, questionnaires, raw data files and more. Our assumption is that due to the diverse nature of datasets, document retrieval models often do not work as efficiently for retrieving datasets. One way of enhancing these types of searches is to incorporate the users' interaction context in order to personalise dataset retrieval sessions. As a first step towards this long term goal, we study characteristics of dataset retrieval sessions from a real-life Digital Library for the social sciences that incorporates both: research data and publications. Previous studies reported a way of discerning queries between document search and dataset search by query length. In this paper, we argue the claim and report our findings of an indistinguishability of queries, whether aiming for a dataset or a document. Amongst others, we report our findings of dataset retrieval sessions with respect to query characteristics, interaction sequences and topical drift within 65,000 unique sessions.

Suraj Agrawal, Dwaipayan Roy, Mandar Mitra

Personalized Point of Interest recommendation is very helpful for satisfying users' needs at new places. In this article, we propose a tag embedding based method for Personalized Recommendation of Point Of Interest. We model the relationship between tags corresponding to Point Of Interest. The model provides representative embedding corresponds to a tag in a way that related tags will be closer. We model Point of Interest-based on tag embedding and also model the users (user profile) based on the Point Of Interest rated by them. finally, we rank the user's candidate Point Of Interest based on cosine similarity between user's embedding and Point of Interest's embedding. Further, we find the parameters required to model user by discrete optimizing over different measures (like ndcg@5, MRR, ...). We also analyze the result while considering the same parameters for all users and individual parameters for each user. Along with it we also analyze the effect on the result while changing the dataset to model the relationship between tags. Our method also minimizes the privacy leak issue. We used TREC Contextual Suggestion 2016 Phase 2 dataset and have significant improvement over all the measures on the state of the art method. It improves ndcg@5 by 12.8%, p@5 by 4.3%, and MRR by 7.8%, which shows the effectiveness of the method.

Dwaipayan Roy, Debasis Ganguly, Mandar Mitra et al.

A major difficulty in applying word vector embeddings in IR is in devising an effective and efficient strategy for obtaining representations of compound units of text, such as whole documents, (in comparison to the atomic words), for the purpose of indexing and scoring documents. Instead of striving for a suitable method for obtaining a single vector representation of a large document of text, we rather aim for developing a similarity metric that makes use of the similarities between the individual embedded word vectors in a document and a query. More specifically, we represent a document and a query as sets of word vectors, and use a standard notion of similarity measure between these sets, computed as a function of the similarities between each constituent word pair from these sets. We then make use of this similarity measure in combination with standard IR based similarities for document ranking. The results of our initial experimental investigations shows that our proposed method improves MAP by up to $5.77\%$, in comparison to standard text-based language model similarity, on the TREC ad-hoc dataset.

Dwaipayan Roy, Debjyoti Paul, Mandar Mitra et al.

In this paper a framework for Automatic Query Expansion (AQE) is proposed using distributed neural language model word2vec. Using semantic and contextual relation in a distributed and unsupervised framework, word2vec learns a low dimensional embedding for each vocabulary entry. Using such a framework, we devise a query expansion technique, where related terms to a query are obtained by K-nearest neighbor approach. We explore the performance of the AQE methods, with and without feedback query expansion, and a variant of simple K-nearest neighbor in the proposed framework. Experiments on standard TREC ad-hoc data (Disk 4, 5 with query sets 301-450, 601-700) and web data (WT10G data with query set 451-550) shows significant improvement over standard term-overlapping based retrieval methods. However the proposed method fails to achieve comparable performance with statistical co-occurrence based feedback method such as RM3. We have also found that the word2vec based query expansion methods perform similarly with and without any feedback information.