Search

The detection of hate speech has become increasingly important in combating online hostility and its real-world consequences. Despite recent advancements, there is limited research addressing hate speech detection in Devanagari-scripted languages, where resources and tools are scarce. While large language models (LLMs) have shown promise in language-related tasks, traditional fine-tuning approaches are often infeasible given the size of the models. In this paper, we propose a Parameter Efficient Fine tuning (PEFT) based solution for hate speech detection and target identification. We evaluate multiple LLMs on the Devanagari dataset provided by (Thapa et al., 2025), which contains annotated instances in 2 languages - Hindi and Nepali. The results demonstrate the efficacy of our approach in handling Devanagari-scripted content.

Missing frequency channels pose a problem for estimating $P(k_\perp,k_\parallel)$ the redshifted 21-cm power spectrum (PS) from radio-interferometric visibility data. This is particularly severe for the Murchison Widefield Array (MWA), which has a periodic pattern of missing channels that introduce spikes along $k_\parallel$. The Tracking Tapered Gridded Estimator (TTGE) overcomes this by first correlating the visibilities in the frequency domain to estimate the multi-frequency angular power spectrum (MAPS) $C_\ell(\Delta\nu)$ that has no missing frequency separation $\Delta\nu$. We perform a Fourier transform along $\Delta\nu$ to estimate $P(k_\perp,k_\parallel)$. Considering our earlier work, simulations demonstrate that the TTGE can estimate $P(k_\perp,k_\parallel)$ without any artifacts due to the missing channels. However, the spikes were still found to persist for the actual data, which is foreground-dominated. The current work presents a detailed investigation considering both simulations and actual data. We find that the spikes arise due to a combination of the missing channels and the strong spectral dependence of the foregrounds. Based on this, we propose and demonstrate a technique to mitigate the spikes. Applying this, we find the values of $P(k_\perp,k_\parallel)$ in the region $0.004 \leq k_\perp \leq 0.048\,{\rm Mpc^{-1}}$ and $k_\parallel > 0.35 \,{\rm Mpc^{-1}}$ to be consistent with zero within the expected statistical fluctuations. We obtain the $2\sigma$ upper limit of $\Delta_{\rm UL}^2(k)=(918.17)^2\,{\rm mK^2}$ at $k=0.404\,{\rm Mpc^{-1}}$ for the mean squared brightness temperature fluctuations of the $z=8.2$ epoch of reionization (EoR) 21-cm signal. This upper limit is from just $\sim 17$ minutes of observation for a single pointing direction. We expect tighter constraints when we combine all $162$ different pointing directions of the drift scan observation., Comment: 11 pages, 16 figures, comments are welcome

Researchers have found that fake news spreads much times faster than real news. This is a major problem, especially in today's world where social media is the key source of news for many among the younger population. Fact verification, thus, becomes an important task and many media sites contribute to the cause. Manual fact verification is a tedious task, given the volume of fake news online. The Factify5WQA shared task aims to increase research towards automated fake news detection by providing a dataset with an aspect-based question answering based fact verification method. Each claim and its supporting document is associated with 5W questions that help compare the two information sources. The objective performance measure in the task is done by comparing answers using BLEU score to measure the accuracy of the answers, followed by an accuracy measure of the classification. The task had submissions using custom training setup and pre-trained language-models among others. The best performing team posted an accuracy of 69.56%, which is a near 35% improvement over the baseline., Comment: Accepted at defactify3@aaai2024

Given the widespread dissemination of misinformation on social media, implementing fact-checking mechanisms for online claims is essential. Manually verifying every claim is very challenging, underscoring the need for an automated fact-checking system. This paper presents our system designed to address this issue. We utilize the Averitec dataset (Schlichtkrull et al., 2023) to assess the performance of our fact-checking system. In addition to veracity prediction, our system provides supporting evidence, which is extracted from the dataset. We develop a Retrieve and Generate (RAG) pipeline to extract relevant evidence sentences from a knowledge base, which are then inputted along with the claim into a large language model (LLM) for classification. We also evaluate the few-shot In-Context Learning (ICL) capabilities of multiple LLMs. Our system achieves an 'Averitec' score of 0.33, which is a 22% absolute improvement over the baseline. Our Code is publicly available on https://github.com/ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llms., Comment: Accepted in The Seventh FEVER Workshop at EMNLP 2024

Understanding satire and humor is a challenging task for even current Vision-Language models. In this paper, we propose the challenging tasks of Satirical Image Detection (detecting whether an image is satirical), Understanding (generating the reason behind the image being satirical), and Completion (given one half of the image, selecting the other half from 2 given options, such that the complete image is satirical) and release a high-quality dataset YesBut, consisting of 2547 images, 1084 satirical and 1463 non-satirical, containing different artistic styles, to evaluate those tasks. Each satirical image in the dataset depicts a normal scenario, along with a conflicting scenario which is funny or ironic. Despite the success of current Vision-Language Models on multimodal tasks such as Visual QA and Image Captioning, our benchmarking experiments show that such models perform poorly on the proposed tasks on the YesBut Dataset in Zero-Shot Settings w.r.t both automated as well as human evaluation. Additionally, we release a dataset of 119 real, satirical photographs for further research. The dataset and code are available at https://github.com/abhi1nandy2/yesbut_dataset., Comment: EMNLP 2024 Main (Long), 18 pages, 14 figures, 12 tables

Drift scan observations provide the broad sky coverage and instrumental stability needed to measure the Epoch of Reionization (EoR) 21-cm signal. In such observations, the telescope's pointing center (PC) moves continuously on the sky. The Tracking Tapered Gridded Estimator (TTGE) combines observations from different PC to estimate $P(k_{\perp}, k_{\parallel})$ the 21-cm power spectrum, centered on a tracking center (TC) which remains fixed on the sky. The tapering further restricts the sky response to a small angular region around TC, thereby mitigating wide-field foregrounds. Here we consider $154.2 \, {\rm MHz}$ ($z = 8.2$) Murchison Widefield Array (MWA) drift scan observations. The periodic pattern of flagged channels, present in MWA data, is known to introduce artefacts which pose a challenge for estimating $P(k_{\perp}, k_{\parallel})$. We demonstrate that the TTGE is able to recover $P(k_{\perp}, k_{\parallel})$ without any artefacts, and estimate $P(k)$ within $5 \%$ accuracy over a large $k$-range. We also present preliminary results for a single PC, combining 9 nights of observation $(17 \, {\rm min}$ total). We find that $P(k_{\perp}, k_{\parallel})$ exhibits streaks at a fixed interval of $k_{\parallel}=0.29 \, {\rm Mpc}^{-1}$, which matches $\Delta \nu_{\rm per}=1.28 \, {\rm MHz}$ that is the period of the flagged channels. The streaks are not as pronounced at larger $k_{\parallel}$, and in some cases they do not appear to extend across the entire $k_{\perp}$ range. The rectangular region $0.05 \leq k_{\perp} \leq 0.16 \, {\rm Mpc^{-1}}$ and $0.9 \leq k_{\parallel} \leq 4.6 \, {\rm Mpc^{-1}}$ is found to be relatively free of foreground contamination and artefacts, and we have used this to place the $2\sigma$ upper limit $\Delta^2(k) < (1.85 \times 10^4)^2\, {\rm mK^2}$ on the EoR 21-cm mean squared brightness temperature fluctuations at $k=1 \,{\rm Mpc}^{-1}$., Comment: 15 pages, 11 figures, accepted for publication in PASA

We study here the collective quantum optical effect of superradiance in neuroprotein architectures. This phenomenon arises from the interaction of the electromagnetic field with an organized network of tryptophan chromophores, where each can be effectively modeled as a two-level quantum emitter. Building on our prior experimental confirmation of single-photon superradiance in microtubules, we predict that bright superradiant states will also emerge in simulated actin filament bundles and amyloid fibrils, which manifests in the form of high quantum yields that are robust to static disorder up to five times that of room temperature. For microtubules and amyloid fibrils, the quantum yield is enhanced with increasing system size, contrary to the conventional expectations of quantum effects in a thermally equilibrated environment. We conduct our analyses using a non-Hermitian Hamiltonian derived from the Lindblad equation for an open quantum system that describes the interaction of a chromophore network with the electromagnetic field, in the single-photon limit. Our detailed quantum yield predictions in realistic neuroprotein structures -- including analysis of the potential information-processing applications of correlated superradiant and subradiant states at divergent timescales -- provide motivation for a range of in vitro experiments to confirm these quantum enhancements, which can serve in vivo as a mechanism for dissipating or downconverting high-energy UV metabolic photon emissions in intensely oxidative pathological environments, including those found in Alzheimer's disease and related dementias., Comment: 41 pages, 11 figures, 2 tables

Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of efficiency, due to the longer input prompt. In this paper, we propose a strategy to make LLMs as efficient as 0-shot text classifiers, while getting comparable or better accuracy than ICL. Our solution targets the low resource setting, i.e., when only 4 examples per class are available. Using a single LLM and few-shot real data we perform a sequence of generation, filtering and Parameter-Efficient Fine-Tuning steps to create a robust and efficient classifier. Experimental results show that our approach leads to competitive results on multiple text classification datasets., Comment: Accepted at LREC-COLING 2024

Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building conversational agents. However, there is still an imminent challenge of accurately discerning context-dependent words and phrases. In this work, we propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing leveraging the power of deep learning models in accurately delivering spot-on transcriptions across a wide variety of vocabularies and speaking styles. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models integrating both language and acoustic modeling for better accuracy. We infused our network with the use of a transformer-based model to properly rescore the word lattice achieving remarkable capabilities with a palpable reduction in Word Error Rate (WER). We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.

Synthetic data generation methods, and in particular, private synthetic data generation methods, are gaining popularity as a means to make copies of sensitive databases that can be shared widely for research and data analysis. Some of the fundamental operations in data analysis include analyzing aggregated statistics, e.g., count, sum, or median, on a subset of data satisfying some conditions. When synthetic data is generated, users may be interested in knowing if their aggregated queries generating such statistics can be reliably answered on the synthetic data, for instance, to decide if the synthetic data is suitable for specific tasks. However, the standard data generation systems do not provide "per-query" quality guarantees on the synthetic data, and the users have no way of knowing how much the aggregated statistics on the synthetic data can be trusted. To address this problem, we present a novel framework named DP-PQD (differentially-private per-query decider) to detect if the query answers on the private and synthetic datasets are within a user-specified threshold of each other while guaranteeing differential privacy. We give a suite of private algorithms for per-query deciders for count, sum, and median queries, analyze their properties, and evaluate them experimentally.

Analyzing memes on the internet has emerged as a crucial endeavor due to the impact this multi-modal form of content wields in shaping online discourse. Memes have become a powerful tool for expressing emotions and sentiments, possibly even spreading hate and misinformation, through humor and sarcasm. In this paper, we present the overview of the Memotion 3 shared task, as part of the DeFactify 2 workshop at AAAI-23. The task released an annotated dataset of Hindi-English code-mixed memes based on their Sentiment (Task A), Emotion (Task B), and Emotion intensity (Task C). Each of these is defined as an individual task and the participants are ranked separately for each task. Over 50 teams registered for the shared task and 5 made final submissions to the test set of the Memotion 3 dataset. CLIP, BERT modifications, ViT etc. were the most popular models among the participants along with approaches such as Student-Teacher model, Fusion, and Ensembling. The best final F1 score for Task A is 34.41, Task B is 79.77 and Task C is 59.82., Comment: Defactify2 @AAAI 2023

The mixing of two or more languages is called Code-Mixing (CM). CM is a social norm in multilingual societies. Neural Language Models (NLMs) like transformers have been effective on many NLP tasks. However, NLM for CM is an under-explored area. Though transformers are capable and powerful, they cannot always encode positional information since they are non-recurrent. Therefore, to enrich word information and incorporate positional information, positional encoding is defined. We hypothesize that Switching Points (SPs), i.e., junctions in the text where the language switches (L1 -> L2 or L2 -> L1), pose a challenge for CM Language Models (LMs), and hence give special emphasis to SPs in the modeling process. We experiment with several positional encoding mechanisms and show that rotatory positional encodings along with switching point information yield the best results. We introduce CONFLATOR: a neural language modeling approach for code-mixed languages. CONFLATOR tries to learn to emphasize switching points using smarter positional encoding, both at unigram and bigram levels. CONFLATOR outperforms the state-of-the-art on two tasks based on code-mixed Hindi and English (Hinglish): (i) sentiment analysis and (ii) machine translation., Comment: Workshop on Computational Approaches to Linguistic Code-Switching @EMNLP2023

With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent. The detrimental impact of fake news emphasizes the need for research focused on automating the detection of false information and verifying its accuracy. In this work, we present the outcome of the Factify 2 shared task, which provides a multi-modal fact verification and satire news dataset, as part of the DeFactify 2 workshop at AAAI'23. The data calls for a comparison based approach to the task by pairing social media claims with supporting documents, with both text and image, divided into 5 classes based on multi-modal relations. In the second iteration of this task we had over 60 participants and 9 final test-set submissions. The best performances came from the use of DeBERTa for text and Swinv2 and CLIP for image. The highest F1 score averaged for all five classes was 81.82%., Comment: Defactify2 @AAAI 2023

Word embeddings, i.e., semantically meaningful vector representation of words, are largely influenced by the distributional hypothesis "You shall know a word by the company it keeps" (Harris, 1954), whereas modern prediction-based neural network embeddings rely on design choices and hyperparameter optimization. Word embeddings like Word2Vec, GloVe etc. well capture the contextuality and real-world analogies but contemporary convolution-based image embeddings such as VGGNet, AlexNet, etc. do not capture contextual knowledge. The popular king-queen analogy does not hold true for most commonly used vision embeddings. In this paper, we introduce a pre-trained joint embedding (JE), named IMAGINATOR, trained on 21K distinct image objects level from 1M image+text pairs. JE is a way to encode multimodal data into a vector space where the text modality serves as the ground-ing key, which the complementary modality (in this case, the image) is anchored with. IMAGINATOR encapsulates three individual representations: (i) object-object co-location, (ii) word-object co-location, and (iii) word-object correlation. These three ways capture complementary aspects of the two modalities which are further combined to obtain the final JEs. Generated JEs are intrinsically evaluated to assess how well they capture the contextuality and real-world analogies. We also evaluate pre-trained IMAGINATOR JEs on three downstream tasks: (i) image captioning, (ii) Image2Tweet, and (iii) text-based image retrieval. IMAGINATOR establishes a new standard on the aforementioned down-stream tasks by outperforming the current SoTA on all the selected tasks. IMAGINATOR will be made publicly available. The codes are available at https://github.com/varunakk/IMAGINATOR

The internet gives the world an open platform to express their views and share their stories. While this is very valuable, it makes fake news one of our society's most pressing problems. Manual fact checking process is time consuming, which makes it challenging to disprove misleading assertions before they cause significant harm. This is he driving interest in automatic fact or claim verification. Some of the existing datasets aim to support development of automating fact-checking techniques, however, most of them are text based. Multi-modal fact verification has received relatively scant attention. In this paper, we provide a multi-modal fact-checking dataset called FACTIFY 2, improving Factify 1 by using new data sources and adding satire articles. Factify 2 has 50,000 new data instances. Similar to FACTIFY 1.0, we have three broad categories - support, no-evidence, and refute, with sub-categories based on the entailment of visual and textual data. We also provide a BERT and Vison Transformer based baseline, which achieves 65% F1 score in the test set. The baseline codes and the dataset will be made available at https://github.com/surya1701/Factify-2.0., Comment: Defactify2 @AAAI2023

Memes are the new-age conveyance mechanism for humor on social media sites. Memes often include an image and some text. Memes can be used to promote disinformation or hatred, thus it is crucial to investigate in details. We introduce Memotion 3, a new dataset with 10,000 annotated memes. Unlike other prevalent datasets in the domain, including prior iterations of Memotion, Memotion 3 introduces Hindi-English Codemixed memes while prior works in the area were limited to only the English memes. We describe the Memotion task, the data collection and the dataset creation methodologies. We also provide a baseline for the task. The baseline code and dataset will be made available at https://github.com/Shreyashm16/Memotion-3.0, Comment: Defactify2 @AAAI

Heart murmurs provide valuable information about mechanical activity of the heart, which aids in diagnosis of various heart valve diseases. This work does automatic and accurate heart murmur detection from phonocardiogram (PCG) recordings. Two public PCG datasets (CirCor Digiscope 2022 dataset and PCG 2016 dataset) from Physionet online database are utilized to train and test three custom neural networks (NN): a 1D convolutional neural network (CNN), a long short-term memory (LSTM) recurrent neural network (RNN), and a convolutional RNN (C-RNN). We first do pre-processing which includes the following key steps: denoising, segmentation, re-labeling of noise-only segments, data normalization, and time-frequency analysis of the PCG segments using wavelet scattering transform. We then conduct four experiments, first three (E1-E3) using PCG 2022 dataset, and fourth (E4) using PCG 2016 dataset. It turns out that our custom 1D-CNN outperforms other two NNs (LSTM-RNN and C-RNN). Further, our 1D-CNN model outperforms the related work in terms of accuracy, weighted accuracy, F1-score and AUROC, for experiment E3 (that utilizes the cleaned and re-labeled PCG 2022 dataset). As for experiment E1 (that utilizes the original PCG 2022 dataset), our model performs quite close to the related work in terms of weighted accuracy and F1-score., Comment: 11 pages, 8 figures, 10 tables, under review with a journal

Intensity mapping with the redshifted 21-cm line is an emerging tool in cosmology. Drift scan observations, where the antennas are fixed to the ground and the telescope's pointing center (PC) changes continuously on the sky due to earth's rotation, provide broad sky coverage and sustained instrumental stability needed for 21-cm intensity mapping. Here we present the Tracking Tapered Grided Estimator (TTGE) to quantify the power spectrum of the sky signal estimated directly from the visibilities measured in drift scan radio interferometric observations. The TTGE uses the data from the different PC to estimate the power spectrum of the signal from a small angular region located around a fixed tracking center (TC). The size of this angular region is decided by a suitably chosen tapering window function which serves to reduce the foreground contamination from bright sources located at large angles from the TC. It is possible to cover the angular footprint of the drift scan observations using multiple TC, and combine the estimated power spectra to increase the signal to noise ratio. Here we have validated the TTGE using simulations of $154 \, {\rm MHz}$ MWA drift scan observations. We show that the TTGE can recover the input model angular power spectrum $C_{\ell}$ within $20 \%$ accuracy over the $\ell$ range $40 < \ell < 700$., Comment: Accepted for publication in MNRAS

Joint embedding (JE) is a way to encode multi-modal data into a vector space where text remains as the grounding key and other modalities like image are to be anchored with such keys. Meme is typically an image with embedded text onto it. Although, memes are commonly used for fun, they could also be used to spread hate and fake information. That along with its growing ubiquity over several social platforms has caused automatic analysis of memes to become a widespread topic of research. In this paper, we report our initial experiments on Memotion Analysis problem through joint embeddings. Results are marginally yielding SOTA., Comment: Accepted as Student Abstract at AAAI-22

Over the past decade, we have seen exponential growth in online content fueled by social media platforms. Data generation of this scale comes with the caveat of insurmountable offensive content in it. The complexity of identifying offensive content is exacerbated by the usage of multiple modalities (image, language, etc.), code-mixed language and more. Moreover, even after careful sampling and annotation of offensive content, there will always exist a significant class imbalance between offensive and non-offensive content. In this paper, we introduce a novel Code-Mixing Index (CMI) based focal loss which circumvents two challenges (1) code-mixing in languages (2) class imbalance problem for Dravidian language offense detection. We also replace the conventional dot product-based classifier with the cosine-based classifier which results in a boost in performance. Further, we use multilingual models that help transfer characteristics learnt across languages to work effectively with low resourced languages. It is also important to note that our model handles instances of mixed script (say usage of Latin and Dravidian-Tamil script) as well. To summarize, our model can handle offensive language detection in a low-resource, class imbalanced, multilingual and code-mixed setting., Comment: Accepted for publication at SN Computer Science Journal

NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic build-ing blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance in the seen examples. In this paper we present our initial observations on applying switching point based positional encoding techniques for CM language, specifically Hinglish (Hindi - English). Results are only marginally better than SOTA, but it is evident that positional encoding could bean effective way to train position sensitive language models for CM text., Comment: Accepted as Student Abstract at AAAI 2022