Debasis Ganguly

Madhusudan Ghosh, Shrimon Mukherjee, Asmit Ganguly et al.

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at \url{https://github.com/shrimonmuke0202/AlpaPICO.git}.

Michael Llordes, Debasis Ganguly, Sumit Bhatia et al.

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations. These models, however, suffer from poor interpretability as they do not rely on explicit term matching. As a form of local per-query explanations, we introduce the notion of equivalent queries that are generated by maximizing the similarity between the NRM's results and the result set of a sparse retrieval system with the equivalent query. We then compare this approach with existing methods such as RM3-based query expansion and contrast differences in retrieval effectiveness and in the terms generated by each approach.

Madhusudan Ghosh, Debasis Ganguly, Partha Basuchowdhuri et al.

Research in scientific disciplines evolves, often rapidly, over time with the emergence of novel methodologies and their associated terminologies. While methodologies themselves being conceptual in nature and rather difficult to automatically extract and characterise, in this paper, we seek to develop supervised models for automatic extraction of the names of the various constituents of a methodology, e.g., `R-CNN', `ELMo' etc. The main research challenge for this task is effectively modeling the contexts around these methodology component names in a few-shot or even a zero-shot setting. The main contributions of this paper towards effectively identifying new evolving scientific methodology names are as follows: i) we propose a factored approach to sequence modeling, which leverages a broad-level category information of methodology domains, e.g., `NLP', `RL' etc.; ii) to demonstrate the feasibility of our proposed approach of identifying methodology component names under a practical setting of fast evolving AI literature, we conduct experiments following a simulated chronological setup (newer methodologies not seen during the training process); iii) our experiments demonstrate that the factored approach outperforms state-of-the-art baselines by margins of up to 9.257\% for the methodology extraction task with the few-shot setup.

Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly et al.

A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline.

Fangzheng Tian, Debasis Ganguly, Craig Macdonald

Query Performance Prediction (QPP) estimates the retrieval quality of ranking models without the use of any human-assessed relevance judgements, and finds applications in query-specific selective decision making to improve overall retrieval effectiveness. Although unsupervised QPP approaches are effective for lexical retrieval models, they usually perform weaker for neural rankers. Recent work shows that leveraging query variants (QVs), i.e., queries with potentially similar information needs to a given query, can enhance unsupervised QPP accuracy. However, existing QV-based prediction methods rely on query variants generated by term expansion of the input query, which is likely to yield incoherent, hallucinatory and off-topic QVs. In this paper, we propose to make use of queries retrieved from a log of past queries as QVs to be subsequently used for QPP. In addition to directly applying retrieved QVs in QPP, we further propose to leverage large language models (LLMs) to generate QVs conditioned on the retrieved QVs, thus mitigating the limitation of relying only on existing queries in a log. Experiments on TREC DL'19 and DL'20 show that QPP enhanced with RAQG outperform the best-performing existing QV-based prediction approach by as much as 30% on neural ranking models such as MonoT5.

Shrey Satapara, Parth Mehta, Debasis Ganguly et al.

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. Traditional means of developing a misinformation ground-truth dataset does not scale well because of the extensive manual effort required to annotate the data. In this paper, we propose an LLM-based approach of creating silver-standard ground-truth datasets for identifying misinformation. Specifically speaking, given a trusted news article, our proposed approach involves prompting LLMs to automatically generate a summarised version of the original article. The prompts in our proposed approach act as a controlling mechanism to generate specific types of factual incorrectness in the generated summaries, e.g., incorrect quantities, false attributions etc. To investigate the usefulness of this dataset, we conduct a set of experiments where we train a range of supervised models for the task of misinformation detection.

Manish Chandra, Debasis Ganguly, Iadh Ounis

In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the downstream task performance. Existing ICL approaches use an identical number of examples (a pre-configured hyper-parameter) for each data instance. Our work alleviates the limitations of this 'one fits all' approach by dynamically predicting the number of examples for each data instance to be used in few-shot inference with LLMs. In particular, we employ a multi-label classifier, the parameters of which are fitted using a training set, where the label for each instance in this training set indicates if using a specific value of k (number of most similar examples from 0 up to a maximum value) leads to correct k-shot downstream predictions. Our experiments on a number of text classification benchmarks show that AICL substantially outperforms standard ICL by up to 17%.

Nilanjan Sinhababu, Soumedhik Bharati, Debasis Ganguly et al.

Large Language Models (LLM) have been widely used in reranking. Computational overhead and large context lengths remain a challenging issue for LLM rerankers. Efficient reranking usually involves selecting a subset of the ranked list from the first stage, known as ranked list truncation (RLT). The truncated list is processed further by a reranker. For LLM rerankers, the ranked list is often partitioned and processed sequentially in batches to reduce the context length. Both these steps involve hyperparameters and topic-agnostic heuristics. Recently, LLMs have been shown to be effective for relevance judgment. Equivalently, we propose that LLMs can be used to generate reference documents that can act as a pivot between relevant and non-relevant documents in a ranked list. We propose methods to use these generated reference documents for RLT as well as for efficient listwise reranking. While reranking, we process the ranked list in either parallel batches of non-overlapping windows or overlapping windows with adaptive strides, improving the existing fixed stride setup. The generated reference documents are also shown to improve existing efficient listwise reranking frameworks. Experiments on TREC Deep Learning benchmarks show that our approach outperforms existing RLT-based approaches. In-domain and out-of-domain benchmarks demonstrate that our proposed methods accelerate LLM-based listwise reranking by up to 66\% compared to existing approaches. This work not only establishes a practical paradigm for efficient LLM-based reranking but also provides insight into the capability of LLMs to generate semantically controlled documents using relevance signals.

Payel Santra, Madhusudan Ghosh, Debasis Ganguly et al.

Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization.

Suchana Datta, Debasis Ganguly, Derek Greene et al.

Motivated by the recent success of end-to-end deep neural models for ranking tasks, we present here a supervised end-to-end neural approach for query performance prediction (QPP). In contrast to unsupervised approaches that rely on various statistics of document score distributions, our approach is entirely data-driven. Further, in contrast to weakly supervised approaches, our method also does not rely on the outputs from different QPP estimators. In particular, our model leverages information from the semantic interactions between the terms of a query and those in the top-documents retrieved with it. The architecture of the model comprises multiple layers of 2D convolution filters followed by a feed-forward layer of parameters. Experiments on standard test collections demonstrate that our proposed supervised approach outperforms other state-of-the-art supervised and unsupervised approaches.

Debasis Ganguly, Suchana Datta, Mandar Mitra et al.

A query performance predictor estimates the retrieval effectiveness of an IR system for a given query. 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. Motivated by this argument, the objective of this paper is to investigate how such variances in the ground truth for QPP evaluation can affect the outcomes of QPP experiments. We consider this not only in terms of the absolute values of the evaluation metrics being reported (e.g. Pearson's $r$, Kendall's $τ$), but also with respect to the changes in the ranks of different QPP systems when ordered by the QPP metric scores. Our experiments reveal that the observed QPP outcomes can vary considerably, both in terms of the absolute evaluation metric values and also in terms of the relative system ranks. Through our analysis, we report the optimal combinations of QPP evaluation metric and experimental settings that are likely to lead to smaller variations in the observed results.

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.). Our proposed method involves learning a multi-objective function that in addition to learning the primary objective of predicting the primary class labels from the data, also employs a clustering-based heuristic to minimize the disparities of the class label distribution with respect to the cluster memberships, with the assumption that each cluster should ideally map to a distinct combination of attribute values. Experiments demonstrate effective mitigation of cognitive biases on a benchmark dataset without the use of annotations of secondary attribute values (the zero-shot case) or with the use of a small number of attribute value annotations (the few-shot case).

Yufang Hou, Charles Jochim, Martin Gleize et al.

Tasks, Datasets and Evaluation Metrics are important concepts for understanding experimental scientific papers. However, most previous work on information extraction for scientific literature mainly focuses on the abstracts only, and does not treat datasets as a separate type of entity (Zadeh and Schumann, 2016; Luan et al., 2018). In this paper, we present a new corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities on 2,000 sentences extracted from NLP papers. We report experiment results on TDM extraction using a simple data augmentation strategy and apply our tagger to around 30,000 NLP papers from the ACL Anthology. The corpus is made publicly available to the community for fostering research on scientific publication summarization (Erera et al., 2019) and knowledge discovery.

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. While standard AL heuristics, such as selecting those points for annotation for which a classification model yields least confident predictions, there has been no empirical investigation to see if these heuristics lead to models that are more interpretable to humans. In the era of data-driven learning, this is an important research direction to pursue. This paper describes our work-in-progress towards developing an AL selection function that in addition to model effectiveness also seeks to improve on the interpretability of a model during the bootstrapping steps. Concretely speaking, our proposed selection function trains an `explainer' model in addition to the classifier model, and favours those instances where a different part of the data is used, on an average, to explain the predicted class. Initial experiments exhibited encouraging trends in showing that such a heuristic can lead to developing more effective and more explainable end-to-end data-driven classifiers.

Anirban Chakraborty, Debasis Ganguly, Annalina Caputo et al.

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. To balance this trade-off between exploitation and exploration, we propose an unsupervised, generic framework involving a factored relevance model (FRLM), constituting two distinct components, one pertaining to historical contexts, and the other corresponding to the current context. We further generalize the proposed FRLM by incorporating the semantic relationships between terms in POI descriptors using kernel density estimation (KDE) on embedded word vectors. Additionally, we show that trip-qualifiers, (e.g. 'trip-type', 'accompanied-by') are potentially useful information sources that could be used to improve the recommendation effectiveness. Using such information is not straight forward since users' texts/reviews of visited POIs typically do not explicitly contain such annotations. We undertake a weakly supervised approach to predict the associations between the review-texts in a user profile and the likely trip contexts. Our experiments, conducted on the TREC contextual suggestion 2016 dataset, demonstrate that factorization, KDE-based generalizations, and trip-qualifier enriched contexts of the relevance model improve POI recommendation.

Procheta Sen, Debasis Ganguly

Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice. The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as unethical and seemingly inhuman predictions as outputs of AI systems trained on such data. To alleviate this problem, we propose a bias-aware multi-objective learning framework that given a set of identity attributes (e.g. gender, ethnicity etc.) and a subset of sensitive categories of the possible classes of prediction outputs, learns to reduce the frequency of predicting certain combinations of them, e.g. predicting stereotypes such as `most blacks use abusive language', or `fear is a virtue of women'. Our experiments conducted on an emotion prediction task with balanced class priors shows that a set of baseline bias-agnostic models exhibit cognitive biases with respect to gender, such as women are prone to be afraid whereas men are more prone to be angry. In contrast, our proposed bias-aware multi-objective learning methodology is shown to reduce such biases in the predictied emotions.

Chandan Biswas, Debasis Ganguly, Ujjwal Bhattacharya

Amidst an increasing number of infected cases during the Covid-19 pandemic, it is essential to trace, as early as possible, the susceptible people who might have been infected by the disease due to their close proximity with people who were tested positive for the virus. This early contact tracing is likely to limit the rate of spread of the infection within a locality. 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. To address this problem from an information retrieval (search) perspective, we represent the location of each person at each time instant as a point in a vector space. By using the locations of the given list of infected persons as queries, we investigate the feasibility of applying approximate nearest neighbour (ANN) based indexing and retrieval approaches to obtain a list of top-k suspected users in real-time. Since leveraging information from true user location data can lead to security and privacy concerns, we also investigate what effects does distance-preserving encoding methods have on the effectiveness of the ANN methods. Experiments conducted on real and synthetic datasets demonstrate that the top-k retrieved lists of susceptible users retrieved with existing ANN approaches (KD-tree and HNSW) yield satisfactory precision and recall values, thus indicating that ANN approaches can potentially be applied in practice to facilitate real-time contact tracing even under the presence of imposed privacy constraints.

Yufang Hou, Charles Jochim, Martin Gleize et al.

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. The community could greatly benefit from an automatic system able to summarize scientific results, e.g., in the form of a leaderboard. In this paper we build two datasets and develop a framework (TDMS-IE) aimed at automatically extracting task, dataset, metric and score from NLP papers, towards the automatic construction of leaderboards. Experiments show that our model outperforms several baselines by a large margin. Our model is a first step towards automatic leaderboard construction, e.g., in the NLP domain.

Yufang Hou, Debasis Ganguly, Lea A. Deleris et al.

Population age information is an essential characteristic of clinical trials. In this paper, we focus on extracting minimum and maximum (min/max) age values for the study samples from clinical research articles. Specifically, we investigate the use of a neural network model for question answering to address this information extraction task. The min/max age QA model is trained on the massive structured clinical study records from ClinicalTrials.gov. For each article, based on multiple min and max age values extracted from the QA model, we predict both actual min/max age values for the study samples and filter out non-factual age expressions. Our system improves the results over (i) a passage retrieval based IE system and (ii) a CRF-based system by a large margin when evaluated on an annotated dataset consisting of 50 research papers on smoking cessation.

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.