Search Results for author: Debasis Ganguly

Found 30 papers, 5 papers with code

Top-Down Partitioning for Efficient List-Wise Ranking

no code implementations23 May 2024 Andrew Parry, Sean MacAvaney, Debasis Ganguly

Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval.

Information Retrieval Re-Ranking

"In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"

no code implementations2 May 2024 Andrew Parry, Debasis Ganguly, Manish Chandra

With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tuning the parameters of an LLM specific to a downstream task with labeled examples, a small number of such examples is appended to a prompt instruction for controlling the decoder's generation process.

In-Context Learning Information Retrieval +1

Exploiting Positional Bias for Query-Agnostic Generative Content in Search

1 code implementation1 May 2024 Andrew Parry, Sean MacAvaney, Debasis Ganguly

We demonstrate such defects by showing that non-relevant text--such as promotional content--can be easily injected into a document without adversely affecting its position in search results.

Position Text Retrieval

'One size doesn't fit all': Learning how many Examples to use for In-Context Learning for Improved Text Classification

no code implementations11 Mar 2024 Manish Chandra, Debasis Ganguly, Yiwen Li, Iadh Ounis

While existing work uses a static number of examples during inference for each data instance, in this paper we propose a novel methodology of dynamically adapting the number of examples as per the data.

In-Context Learning text-classification +1

Evaluating the Explainability of Neural Rankers

no code implementations4 Mar 2024 Saran Pandian, Debasis Ganguly, Sean MacAvaney

While the increasing complexity of the search models have been able to demonstrate improvements in effectiveness (measured in terms of relevance of top-retrieved results), a question worthy of a thorough inspection is - "how explainable are these models?

Information Retrieval Sentence

A Deep Learning Approach for Selective Relevance Feedback

no code implementations20 Jan 2024 Suchana Datta, Debasis Ganguly, Sean MacAvaney, Derek Greene

Additionally, to further improve retrieval effectiveness with this selective PRF approach, we make use of the model's confidence estimates to combine the information from the original and expanded queries.


Fighting Fire with Fire: Adversarial Prompting to Generate a Misinformation Detection Dataset

no code implementations9 Jan 2024 Shrey Satapara, Parth Mehta, Debasis Ganguly, Sandip Modha

The recent success in language generation capabilities of large language models (LLMs), such as GPT, Bard, Llama etc., can potentially lead to concerns about their possible misuse in inducing mass agitation and communal hatred via generating fake news and spreading misinformation.

Misinformation Text Generation

Enhancing AI Research Paper Analysis: Methodology Component Extraction using Factored Transformer-based Sequence Modeling Approach

no code implementations5 Nov 2023 Madhusudan Ghosh, Debasis Ganguly, Partha Basuchowdhuri, Sudip Kumar Naskar

Research in scientific disciplines evolves, often rapidly, over time with the emergence of novel methodologies and their associated terminologies.

Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation

1 code implementation25 Apr 2023 Michael Llordes, Debasis Ganguly, Sumit Bhatia, Chirag Agarwal

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations.


Query-specific Variable Depth Pooling via Query Performance Prediction towards Reducing Relevance Assessment Effort

no code implementations23 Apr 2023 Debasis Ganguly, Emine Yilmaz

However, in this paper we argue that the annotation effort can be substantially reduced if the depth of the pool is made a variable quantity for each query, the rationale being that the number of documents relevant to the information need can widely vary across queries.


On the Feasibility and Robustness of Pointwise Evaluation of Query Performance Prediction

no code implementations1 Apr 2023 Suchana Datta, Debasis Ganguly, Derek Greene, Mandar Mitra

Despite the retrieval effectiveness of queries being mutually independent of one another, the evaluation of query performance prediction (QPP) systems has been carried out by measuring rank correlation over an entire set of queries.


Deep-QPP: A Pairwise Interaction-based Deep Learning Model for Supervised Query Performance Prediction

no code implementations15 Feb 2022 Suchana Datta, Debasis Ganguly, Derek Greene, Mandar Mitra

In contrast to unsupervised approaches that rely on various statistics of document score distributions, our approach is entirely data-driven.

An Analysis of Variations in the Effectiveness of Query Performance Prediction

no code implementations13 Feb 2022 Debasis Ganguly, Suchana Datta, Mandar Mitra, Derek Greene

An important characteristic of QPP evaluation is that, since the ground truth retrieval effectiveness for QPP evaluation can be measured with different metrics, the ground truth itself is not absolute, which is in contrast to other retrieval tasks, such as that of ad-hoc retrieval.


Multi-Objective Few-shot Learning for Fair Classification

no code implementations5 Oct 2021 Ishani Mondal, Procheta Sen, Debasis Ganguly

In this paper, we propose a general framework for mitigating the disparities of the predicted classes with respect to secondary attributes within the data (e. g., race, gender etc.).

Attribute Classification +1

Tessellated 2D Convolution Networks: A Robust Defence against Adversarial Attacks

no code implementations29 Sep 2021 Swarnava Das, Pabitra Mitra, Debasis Ganguly

This means that an adversarial crafted image which is sufficiently close (visually indistinguishable) to its representative class can often be misclassified to be a member of a different class.

Image Classification

ALEX: Active Learning based Enhancement of a Model's Explainability

no code implementations2 Sep 2020 Ishani Mondal, Debasis Ganguly

An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner.

Active Learning

Kernel Density Estimation based Factored Relevance Model for Multi-Contextual Point-of-Interest Recommendation

no code implementations28 Jun 2020 Anirban Chakraborty, Debasis Ganguly, Annalina Caputo, Gareth J. F. Jones

An automated contextual suggestion algorithm is likely to recommend contextually appropriate and personalized 'points-of-interest' (POIs) to a user, if it can extract information from the user's preference history (exploitation) and effectively blend it with the user's current contextual information (exploration) to predict a POI's 'appropriateness' in the current context.

Density Estimation

Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning

no code implementations14 May 2020 Procheta Sen, Debasis Ganguly

Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice.

Abusive Language

HBCP Corpus: A New Resource for the Analysis of Behavioural Change Intervention Reports

no code implementations LREC 2020 Francesca Bonin, Martin Gleize, Ailbhe Finnerty, C. Moore, ice, Charles Jochim, Emma Norris, Yufang Hou, Alison J. Wright, Debasis Ganguly, Emily Hayes, Silje Zink, Aless Pascale, ra, Pol Mac Aonghusa, Susan Michie

Due to the fast pace at which research reports in behaviour change are published, researchers, consultants and policymakers would benefit from more automatic ways to process these reports.

Approximate Nearest Neighbour Search on Privacy-aware Encoding of User Locations to Identify Susceptible Infections in Simulated Epidemics

1 code implementation19 Apr 2020 Chandan Biswas, Debasis Ganguly, Ujjwal Bhattacharya

In this paper, we investigate how effectively and efficiently can such a list of susceptible people be found given a list of infected persons and their locations.

Information Retrieval Retrieval

Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction

1 code implementation ACL 2019 Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, Debasis Ganguly

While the fast-paced inception of novel tasks and new datasets helps foster active research in a community towards interesting directions, keeping track of the abundance of research activity in different areas on different datasets is likely to become increasingly difficult.

Scientific Results Extraction

Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences

no code implementations NAACL 2019 Procheta Sen, Debasis Ganguly, Gareth Jones

However, this strong assumption may not capture the semantic association between words that co-occur frequently but non-locally within documents.

Decision Conversations Decoded

no code implementations NAACL 2018 L{\'e}a Deleris, Debasis Ganguly, Killian Levacher, Martin Stephenson, Francesca Bonin

We describe the vision and current version of a Natural Language Processing system aimed at group decision making facilitation.

Decision Making

Developing a Dataset for Evaluating Approaches for Document Expansion with Images

no code implementations LREC 2016 Debasis Ganguly, Iacer Calixto, Gareth Jones

Motivated by the adage that a {``}picture is worth a thousand words{''} it can be reasoned that automatically enriching the textual content of a document with relevant images can increase the readability of a document.

Information Retrieval Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.