BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Mayank Singh

Mayank Singh appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computation and LanguageDigital LibrariesMachine LearningInformation RetrievalSocial and Information NetworksComputer VisionArtificial IntelligenceCryptography and Securityeess.IV

Catalog footprint

What is connected

18works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

18 published item(s)

preprint2026arXiv

MMT: A Multilingual and Multi-Topic Indian Social Media Dataset

Social media plays a significant role in cross-cultural communication. A vast amount of this occurs in code-mixed and multilingual form, posing a significant challenge to Natural Language Processing (NLP) tools for processing such information, like language identification, topic modeling, and named-entity recognition. To address this, we introduce a large-scale multilingual, and multi-topic dataset (MMT) collected from Twitter (1.7 million Tweets), encompassing 13 coarse-grained and 63 fine-grained topics in the Indian context. We further annotate a subset of 5,346 tweets from the MMT dataset with various Indian languages and their code-mixed counterparts. Also, we demonstrate that the currently existing tools fail to capture the linguistic diversity in MMT on two downstream tasks, i.e., topic modeling and language identification. To facilitate future research, we have make the anonymized and annotated dataset available at https://huggingface.co/datasets/LingoIITGN/MMT.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?

Aligning multilingual assistants with culturally grounded user preferences is essential for serving India's linguistically diverse population of over one billion speakers across multiple scripts. However, existing benchmarks either focus on a single language or conflate retrieval with generation, leaving open the question of whether current embedding models can encode persona-instruction compatibility without relying on response synthesis. We present a unified benchmark spanning 12 Indian languages and four evaluation tasks: monolingual and cross-lingual persona-to-instruction retrieval, reverse retrieval from instruction to persona, and binary compatibility classification. Eight multilingual embedding models are evaluated in a frozen-encoder setting with a thin logistic regression head for classification. E5-Large-Instruct achieves the highest Recall@1 of 27.4\% on monolingual retrieval and 20.7\% on cross-lingual transfer, while BGE-M3 leads reverse retrieval at 32.1\% Recall@1. For classification, LaBSE attains 75.3\% AUROC with strong calibration. These findings offer practical guidance for model selection in Indic multilingual retrieval and establish reproducible baselines for future work\footnote{Code, datasets, and models are publicly available at https://github.com/aryashah2k/PI-Indic-Align.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models

Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-answer accuracy alone does not show whether they faithfully execute the procedure specified in a prompt. We study this question through a controlled diagnostic benchmark for procedural execution, where models are given a step-wise arithmetic algorithm and two numeric inputs, and must return the final computed value. The benchmark uses simple arithmetic operations but increases complexity through algorithm length and look-back dependencies over intermediate variables. Across 14 models and 55 datasets, average first-answer accuracy drops from 61% on 5-step procedures to 20% on 95-step procedures. Generation-level analysis shows that failures often involve missing answers, premature answers, self-correction after an initial error, under-executed traces, and hallucinated extra steps. These findings suggest that apparent reasoning ability can mask substantial weaknesses in faithful instruction execution.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Inefficiency of Language Models in Scholarly Retrieval: An Experimental Walk-through

Language models are increasingly becoming popular in AI-powered scientific IR systems. This paper evaluates popular scientific language models in handling (i) short-query texts and (ii) textual neighbors. Our experiments showcase the inability to retrieve relevant documents for a short-query text even under the most relaxed conditions. Additionally, we leverage textual neighbors, generated by small perturbations to the original text, to demonstrate that not all perturbations lead to close neighbors in the embedding space. Further, an exhaustive categorization yields several classes of orthographically and semantically related, partially related, and completely unrelated neighbors. Retrieval performance turns out to be more influenced by the surface form rather than the semantics of the text.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Attributional Robustness Training using Input-Gradient Spatial Alignment

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the explanations could be manipulated easily by adding visually imperceptible perturbations to the input while keeping the model's prediction intact. In this work, we study the problem of attributional robustness (i.e. models having robust explanations) by showing an upper bound for attributional vulnerability in terms of spatial correlation between the input image and its explanation map. We propose a training methodology that learns robust features by minimizing this upper bound using soft-margin triplet loss. Our methodology of robust attribution training (\textit{ART}) achieves the new state-of-the-art attributional robustness measure by a margin of $\approx$ 6-18 $\%$ on several standard datasets, ie. SVHN, CIFAR-10 and GTSRB. We further show the utility of the proposed robust training technique (\textit{ART}) in the downstream task of weakly supervised object localization by achieving the new state-of-the-art performance on CUB-200 dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Bollyrics: Automatic Lyrics Generator for Romanised Hindi

Song lyrics convey a meaningful story in a creative manner with complex rhythmic patterns. Researchers have been successful in generating and analyisng lyrics for poetry and songs in English and Chinese. But there are no works which explore the Hindi language datasets. Given the popularity of Hindi songs across the world and the ambiguous nature of romanized Hindi script, we propose Bollyrics, an automatic lyric generator for romanized Hindi songs. We propose simple techniques to capture rhyming patterns before and during the model training process in Hindi language. The dataset and codes are available publicly at https://github.com/lingo-iitgn/Bollyrics.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques. We observe that regularizing the feature manifold, enriched via self-supervised techniques, with Manifold Mixup significantly improves few-shot learning performance. We show that our proposed method S2M2 beats the current state-of-the-art accuracy on standard few-shot learning datasets like CIFAR-FS, CUB, mini-ImageNet and tiered-ImageNet by 3-8 %. Through extensive experimentation, we show that the features learned using our approach generalize to complex few-shot evaluation tasks, cross-domain scenarios and are robust against slight changes to data distribution.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Identification, Tracking and Impact: Understanding the trade secret of catchphrases

Understanding the topical evolution in industrial innovation is a challenging problem. With the advancement in the digital repositories in the form of patent documents, it is becoming increasingly more feasible to understand the innovation secrets -- "catchphrases" of organizations. However, searching and understanding this enormous textual information is a natural bottleneck. In this paper, we propose an unsupervised method for the extraction of catchphrases from the abstracts of patents granted by the U.S. Patent and Trademark Office over the years. Our proposed system achieves substantial improvement, both in terms of precision and recall, against state-of-the-art techniques. As a second objective, we conduct an extensive empirical study to understand the temporal evolution of the catchphrases across various organizations. We also show how the overall innovation evolution in the form of introduction of newer catchphrases in an organization's patents correlates with the future citations received by the patents filed by that organization. Our code and data sets will be placed in the public domain soon.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

IIT Gandhinagar at SemEval-2020 Task 9: Code-Mixed Sentiment Classification Using Candidate Sentence Generation and Selection

Code-mixing is the phenomenon of using multiple languages in the same utterance of a text or speech. It is a frequently used pattern of communication on various platforms such as social media sites, online gaming, product reviews, etc. Sentiment analysis of the monolingual text is a well-studied task. Code-mixing adds to the challenge of analyzing the sentiment of the text due to the non-standard writing style. We present a candidate sentence generation and selection based approach on top of the Bi-LSTM based neural classifier to classify the Hinglish code-mixed text into one of the three sentiment classes positive, negative, or neutral. The proposed approach shows an improvement in the system performance as compared to the Bi-LSTM based neural classifier. The results present an opportunity to understand various other nuances of code-mixing in the textual data, such as humor-detection, intent classification, etc.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Innovation and Revenue: Deep Diving into the Temporal Rank-shifts of Fortune 500 Companies

Research and innovation is important agenda for any company to remain competitive in the market. The relationship between innovation and revenue is a key metric for companies to decide on the amount to be invested for future research. Two important parameters to evaluate innovation are the quantity and quality of scientific papers and patents. Our work studies the relationship between innovation and patenting activities for several Fortune 500 companies over a period of time. We perform a comprehensive study of the patent citation dataset available in the Reed Technology Index collected from the US Patent Office. We observe several interesting relations between parameters like the number of (i) patent applications, (ii) patent grants, (iii) patent citations and Fortune 500 ranks of companies. We also study the trends of these parameters varying over the years and derive causal explanations for these with qualitative and intuitive reasoning. To facilitate reproducible research, we make all the processed patent dataset publicly available at https://github.com/mayank4490/Innovation-and-revenue.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On the Benefits of Models with Perceptually-Aligned Gradients

Adversarial robust models have been shown to learn more robust and interpretable features than standard trained models. As shown in [\cite{tsipras2018robustness}], such robust models inherit useful interpretable properties where the gradient aligns perceptually well with images, and adding a large targeted adversarial perturbation leads to an image resembling the target class. We perform experiments to show that interpretable and perceptually aligned gradients are present even in models that do not show high robustness to adversarial attacks. Specifically, we perform adversarial training with attack for different max-perturbation bound. Adversarial training with low max-perturbation bound results in models that have interpretable features with only slight drop in performance over clean samples. In this paper, we leverage models with interpretable perceptually-aligned features and show that adversarial training with low max-perturbation bound can improve the performance of models for zero-shot and weakly supervised localization tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translation

Code-mixing is the phenomenon of using more than one language in a sentence. It is a very frequently observed pattern of communication on social media platforms. Flexibility to use multiple languages in one text message might help to communicate efficiently with the target audience. But, it adds to the challenge of processing and understanding natural language to a much larger extent. This paper presents a parallel corpus of the 13,738 code-mixed English-Hindi sentences and their corresponding translation in English. The translations of sentences are done manually by the annotators. We are releasing the parallel corpus to facilitate future research opportunities in code-mixed machine translation. The annotated corpus is available at https://doi.org/10.5281/zenodo.3605597.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SEAL: Scientific Keyphrase Extraction and Classification

Automatic scientific keyphrase extraction is a challenging problem facilitating several downstream scholarly tasks like search, recommendation, and ranking. In this paper, we introduce SEAL, a scholarly tool for automatic keyphrase extraction and classification. The keyphrase extraction module comprises two-stage neural architecture composed of Bidirectional Long Short-Term Memory cells augmented with Conditional Random Fields. The classification module comprises of a Random Forest classifier. We extensively experiment to showcase the robustness of the system. We evaluate multiple state-of-the-art baselines and show a significant improvement. The current system is hosted at http://lingo.iitgn.ac.in:5000/.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Is this conference a top-tier? ConfAssist: An assistive conflict resolution framework for conference categorization

Classifying publication venues into top-tier or non top-tier is quite subjective and can be debatable at times. In this paper, we propose ConfAssist, a novel assisting framework for conference categorization that aims to address the limitations in the existing systems and portals for venue classification. We start with the hypothesis that top-tier conferences are much more stable than other conferences and the inherent dynamics of these groups differs to a very large extent. We identify various features related to the stability of conferences that might help us separate a top-tier conference from the rest of the lot. While there are many clear cases where expert agreement can be almost immediately achieved as to whether a conference is a top-tier or not, there are equally many cases that can result in a conflict even among the experts. ConfAssist tries to serve as an aid in such cases by increasing the confidence of the experts in their decision. An analysis of 110 conferences from 22 sub-fields of computer science clearly favors our hypothesis as the top-tier conferences are found to exhibit much less fluctuations in the stability related features than the non top-tier ones. We evaluate our hypothesis using systems based on conference categorization. For the evaluation, we conducted human judgment survey with 28 domain experts. The results are impressive with 85.18% classification accuracy. We also compare the dynamics of the newly started conferences with the older conferences to identify the initial signals of popularity. The system is applicable to any conference with atleast 5 years of publication history.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

OCR++: A Robust Framework For Information Extraction from Scholarly Articles

This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text, table and figure headings, URLs and footnotes) and bibliography (citation instances and references). We analyze a diverse set of scientific articles written in English language to understand generic writing patterns and formulate rules to develop this hybrid framework. Extensive evaluations show that the proposed framework outperforms the existing state-of-the-art tools with huge margin in structural information extraction along with improved performance in metadata and bibliography extraction tasks, both in terms of accuracy (around 50% improvement) and processing time (around 52% improvement). A user experience study conducted with the help of 30 researchers reveals that the researchers found this system to be very helpful. As an additional objective, we discuss two novel use cases including automatically extracting links to public datasets from the proceedings, which would further accelerate the advancement in digital libraries. The result of the framework can be exported as a whole into structured TEI-encoded documents. Our framework is accessible online at http://cnergres.iitkgp.ac.in/OCR++/home/.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Which techniques does your application use?: An information extraction framework for scientific articles

Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas. With the exponential growth in research volumes, it has become difficult to keep track of the ever-growing number of application areas as well as the corresponding problem solving techniques. In this paper, we consider the computational linguistics domain and present a novel information extraction system that automatically constructs a pool of all application areas in this domain and appropriately links them with corresponding problem solving techniques. Further, we categorize individual research articles based on their application area and the techniques proposed/used in the article. k-gram based discounting method along with handwritten rules and bootstrapped pattern learning is employed to extract application areas. Subsequently, a language modeling approach is proposed to characterize each article based on its application area. Similarly, regular expressions and high-scoring noun phrases are used for the extraction of the problem solving techniques. We propose a greedy approach to characterize each article based on the techniques. Towards the end, we present a table representing the most frequent techniques adopted for a particular application area. Finally, we propose three use cases presenting an extensive temporal analysis of the usage of techniques and application areas.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Sic Transit Gloria Manuscriptum: Two Views of the Aggregate Fate of Ancient Papers

When PageRank began to be used for ranking in Web search, a concern soon arose that older pages have an inherent --- and potentially unfair --- advantage over emerging pages of high quality, because they have had more time to acquire hyperlink citations. Algorithms were then proposed to compensate for this effect. Curiously, in bibliometry, the opposite concern has often been raised: that a growing body of recent papers crowds out older papers, resulting in a collective amnesia in research communities, which potentially leads to reinventions, redundancies, and missed opportunities to connect ideas. A recent paper by Verstak et al. reported experiments on Google Scholar data, which seemed to refute the amnesia, or aging, hypothesis. They claimed that more recently written papers have a larger fraction of outbound citations targeting papers that are older by a fixed number of years, indicating that ancient papers are alive and well-loved and increasingly easily found, thanks in part to Google Scholar. In this paper we show that the full picture is considerably more nuanced. Specifically, the fate of a fixed sample of papers, as they age, is rather different from what Verstak et al.'s study suggests: there is clear and steady abandonment in favor of citations to newer papers. The two apparently contradictory views are reconciled by the realization that, as time passes, the number of papers older than a fixed number of years grows rapidly.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

CompChall: Addressing Password Guessing Attacks

Even though passwords are the most convenient means of authentication, they bring along themselves the threat of dictionary attacks. Dictionary attacks may be of two kinds: online and offline. While offline dictionary attacks are possible only if the adversary is able to collect data for a successful protocol execution by eavesdropping on the communication channel and can be successfully countered using public key cryptography, online dictionary attacks can be performed by anyone and there is no satisfactory solution to counter them. This paper presents a new authentication protocol which is called CompChall (computational challenge). The proposed protocol uses only one way hash functions as the building blocks and attempts to eliminate online dictionary attacks by implementing a challenge-response system. This challenge-response system is designed in a fashion that it does not pose any difficulty to a genuine user but is time consuming and computationally intensive for an adversary trying to launch a large number of login requests per unit time as in the case of an online dictionary attack. The protocol is stateless and thus less vulnerable to DoS (Denial of Service) attacks.

0 citations0 reviewsNo code linkedOpen access