arXiv subjects

Tanmoy Chakraborty

Publications and source records attributed to Tanmoy Chakraborty.

At least 199 records · Page 11Linked to original sources

arXiv2021

See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization

In recent years, abstractive text summarization with multimodal inputs has started drawing attention due to its ability to accumulate information from different source modalities and generate a fluent textual summary. However, existing methods use short videos as the visual modality and short summary as the ground-truth, therefore, perform poorly on lengthy videos and long ground-truth summary. Additionally, there exists no benchmark dataset to generalize this task on videos of varying lengths. In this paper, we introduce AVIATE, the first large-scale dataset for abstractive text summarization with videos of diverse duration, compiled from presentations in well-known academic conferences like NDSS, ICML, NeurIPS, etc. We use the abstract of corresponding research papers as the reference summaries, which ensure adequate quality and uniformity of the ground-truth. We then propose FLORAL, a factorized multi-modal Transformer based decoder-only language model, which inherently captures the intra-modal and inter-modal dynamics within various input modalities for the text summarization task. FLORAL utilizes an increasing number of self-attentions to capture multimodality and performs significantly better than traditional encoder-decoder based networks. Extensive experiments illustrate that FLORAL achieves significant improvement over the baselines in both qualitative and quantitative evaluations on the existing How2 dataset for short videos and newly introduced AVIATE dataset for videos with diverse duration, beating the best baseline on the two datasets by $1.39$ and $2.74$ ROUGE-L points respectively.

cs.LG↗

arXiv2021

QUINT: Node embedding using network hashing

Representation learning using network embedding has received tremendous attention due to its efficacy to solve downstream tasks. Popular embedding methods (such as deepwalk, node2vec, LINE) are based on a neural architecture, thus unable to scale on large networks both in terms of time and space usage. Recently, we proposed BinSketch, a sketching technique for compressing binary vectors to binary vectors. In this paper, we show how to extend BinSketch and use it for network hashing. Our proposal named QUINT is built upon BinSketch, and it embeds nodes of a sparse network onto a low-dimensional space using simple bi-wise operations. QUINT is the first of its kind that provides tremendous gain in terms of speed and space usage without compromising much on the accuracy of the downstream tasks. Extensive experiments are conducted to compare QUINT with seven state-of-the-art network embedding methods for two end tasks - link prediction and node classification. We observe huge performance gain for QUINT in terms of speedup (up to 7000x) and space saving (up to 80x) due to its bit-wise nature to obtain node embedding. Moreover, QUINT is a consistent top-performer for both the tasks among the baselines across all the datasets. Our empirical observations are backed by rigorous theoretical analysis to justify the effectiveness of QUINT. In particular, we prove that QUINT retains enough structural information which can be used further to approximate many topological properties of networks with high confidence.

cs.SI↗

arXiv2021

Assessing the Quality of the Datasets by Identifying Mislabeled Samples

Due to the over-emphasize of the quantity of data, the data quality has often been overlooked. However, not all training data points contribute equally to learning. In particular, if mislabeled, it might actively damage the performance of the model and the ability to generalize out of distribution, as the model might end up learning spurious artifacts present in the dataset. This problem gets compounded by the prevalence of heavily parameterized and complex deep neural networks, which can, with their high capacity, end up memorizing the noise present in the dataset. This paper proposes a novel statistic -- noise score, as a measure for the quality of each data point to identify such mislabeled samples based on the variations in the latent space representation. In our work, we use the representations derived by the inference network of data quality supervised variational autoencoder (AQUAVS). Our method leverages the fact that samples belonging to the same class will have similar latent representations. Therefore, by identifying the outliers in the latent space, we can find the mislabeled samples. We validate our proposed statistic through experimentation by corrupting MNIST, FashionMNIST, and CIFAR10/100 datasets in different noise settings for the task of identifying mislabelled samples. We further show significant improvements in accuracy for the classification task for each dataset.

cs.LG↗

arXiv2021

DESYR: Definition and Syntactic Representation Based Claim Detection on the Web

The formulation of a claim rests at the core of argument mining. To demarcate between a claim and a non-claim is arduous for both humans and machines, owing to latent linguistic variance between the two and the inadequacy of extensive definition-based formalization. Furthermore, the increase in the usage of online social media has resulted in an explosion of unsolicited information on the web presented as informal text. To account for the aforementioned, in this paper, we proposed DESYR. It is a framework that intends on annulling the said issues for informal web-based text by leveraging a combination of hierarchical representation learning (dependency-inspired Poincare embedding), definition-based alignment, and feature projection. We do away with fine-tuning computer-heavy language models in favor of fabricating a more domain-centric but lighter approach. Experimental results indicate that DESYR builds upon the state-of-the-art system across four benchmark claim datasets, most of which were constructed with informal texts. We see an increase of 3 claim-F1 points on the LESA-Twitter dataset, an increase of 1 claim-F1 point and 9 macro-F1 points on the Online Comments(OC) dataset, an increase of 24 claim-F1 points and 17 macro-F1 points on the Web Discourse(WD) dataset, and an increase of 8 claim-F1 points and 5 macro-F1 points on the Micro Texts(MT) dataset. We also perform an extensive analysis of the results. We make a 100-D pre-trained version of our Poincare-variant along with the source code.

cs.CL↗

arXiv2021

Detecting and analyzing collusive entities on YouTube

In this work, we provide an in-depth analysis of collusive entities on YouTube fostered by various blackmarket services. Following this, we propose models to detect three types of collusive YouTube entities - videos seeking collusive likes, channels seeking collusive subscriptions, and videos seeking collusive comments. The third type of entity is associated with temporal information. To detect videos and channels for collusive likes and subscriptions respectively, we utilize one-class classifiers trained on our curated collusive entities and a set of novel features. The SVM-based model shows significant performance with a true positive rate of 0.911 and 0.910 for detecting collusive videos and collusive channels respectively. To detect videos seeking collusive comments, we propose CollATe, a novel end-to-end neural architecture that leverages time-series information of posted comments along with static metadata of videos. CollATe is composed of three components - metadata feature extractor (which derives metadata-based features from videos), anomaly feature extractor (which utilizes the comment time-series data to detect sudden changes in the commenting activity), and comment feature extractor (which utilizes the text of the comments posted during collusion and computes a similarity score between the comments). Extensive experiments show the effectiveness of CollATe (with a true positive rate of 0.905) over the baselines.

cs.SI↗

arXiv2021

DECIFE: Detecting Collusive Users Involved in Blackmarket Following Services on Twitter

The popularity of Twitter has fostered the emergence of various fraudulent user activities - one such activity is to artificially bolster the social reputation of Twitter profiles by gaining a large number of followers within a short time span. Many users want to gain followers to increase the visibility and reach of their profiles to wide audiences. This has provoked several blackmarket services to garner huge attention by providing artificial followers via the network of agreeable and compromised accounts in a collusive manner. Their activity is difficult to detect as the blackmarket services shape their behavior in such a way that users who are part of these services disguise themselves as genuine users. In this paper, we propose DECIFE, a framework to detect collusive users involved in producing 'following' activities through blackmarket services with the intention to gain collusive followers in return. We first construct a heterogeneous user-tweet-topic network to leverage the follower/followee relationships and linguistic properties of a user. The heterogeneous network is then decomposed to form four different subgraphs that capture the semantic relations between the users. An attention-based subgraph aggregation network is proposed to learn and combine the node representations from each subgraph. The combined representation is finally passed on to a hypersphere learning objective to detect collusive users. Comprehensive experiments on our curated dataset are conducted to validate the effectiveness of DECIFE by comparing it with other state-of-the-art approaches. To our knowledge, this is the first attempt to detect collusive users involved in blackmarket 'following services' on Twitter.

cs.SI↗

arXiv2021

GraphAnoGAN: Detecting Anomalous Snapshots from Attributed Graphs

Finding anomalous snapshots from a graph has garnered huge attention recently. Existing studies address the problem using shallow learning mechanisms such as subspace selection, ego-network, or community analysis. These models do not take into account the multifaceted interactions between the structure and attributes in the network. In this paper, we propose GraphAnoGAN, an anomalous snapshot ranking framework, which consists of two core components -- generative and discriminative models. Specifically, the generative model learns to approximate the distribution of anomalous samples from the candidate set of graph snapshots, and the discriminative model detects whether the sampled snapshot is from the ground-truth or not. Experiments on 4 real-world networks show that GraphAnoGAN outperforms 6 baselines with a significant margin (28.29% and 22.01% higher precision and recall, respectively compared to the best baseline, averaged across all datasets).

cs.LG↗

arXiv2021

Incomplete Gamma Integrals for Deep Cascade Prediction using Content, Network, and Exogenous Signals

The behaviour of information cascades (such as retweets) has been modelled extensively. While point process-based generative models have long been in use for estimating cascade growths, deep learning has greatly enhanced diverse feature integration. We observe two significant temporal signals in cascade data that have not been emphasized or reported to our knowledge. First, the popularity of the cascade root is known to influence cascade size strongly; but the effect falls off rapidly with time. Second, there is a measurable positive correlation between the novelty of the root content (with respect to a streaming external corpus) and the relative size of the resulting cascade. Responding to these observations, we propose GammaCas, a new cascade growth model as a parametric function of time, which combines deep influence signals from content (e.g., tweet text), network features (e.g., followers of the root user), and exogenous event sources (e.g., online news). Specifically, our model processes these signals through a customized recurrent network, whose states then provide the parameters of the cascade rate function, which is integrated over time to predict the cascade size. The network parameters are trained end-to-end using observed cascades. GammaCas outperforms seven recent and diverse baselines significantly on a large-scale dataset of retweet cascades coupled with time-aligned online news -- it beats the best baseline with an 18.98% increase in terms of Kendall's $τ$ correlation and $35.63$ reduction in Mean Absolute Percentage Error. Extensive ablation and case studies unearth interesting insights regarding retweet cascade dynamics.

cs.SI↗

arXiv2021

Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations

Sarcasm detection and humor classification are inherently subtle problems, primarily due to their dependence on the contextual and non-verbal information. Furthermore, existing studies in these two topics are usually constrained in non-English languages such as Hindi, due to the unavailability of qualitative annotated datasets. In this work, we make two major contributions considering the above limitations: (1) we develop a Hindi-English code-mixed dataset, MaSaC, for the multi-modal sarcasm detection and humor classification in conversational dialog, which to our knowledge is the first dataset of its kind; (2) we propose MSH-COMICS, a novel attention-rich neural architecture for the utterance classification. We learn efficient utterance representation utilizing a hierarchical attention mechanism that attends to a small portion of the input sentence at a time. Further, we incorporate dialog-level contextual attention mechanism to leverage the dialog history for the multi-modal classification. We perform extensive experiments for both the tasks by varying multi-modal inputs and various submodules of MSH-COMICS. We also conduct comparative analysis against existing approaches. We observe that MSH-COMICS attains superior performance over the existing models by > 1 F1-score point for the sarcasm detection and 10 F1-score points in humor classification. We diagnose our model and perform thorough analysis of the results to understand the superiority and pitfalls.

cs.CL↗

arXiv2021

HIT: A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation

Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of scopes in improving the quality of language representation particularly for code-mixed languages. In this paper, we propose HIT, a robust representation learning method for code-mixed texts. HIT is a hierarchical transformer-based framework that captures the semantic relationship among words and hierarchically learns the sentence-level semantics using a fused attention mechanism. HIT incorporates two attention modules, a multi-headed self-attention and an outer product attention module, and computes their weighted sum to obtain the attention weights. Our evaluation of HIT on one European (Spanish) and five Indic (Hindi, Bengali, Tamil, Telugu, and Malayalam) languages across four NLP tasks on eleven datasets suggests significant performance improvement against various state-of-the-art systems. We further show the adaptability of learned representation across tasks in a transfer learning setup (with and without fine-tuning).

cs.CL↗

arXiv2021

Fighting an Infodemic: COVID-19 Fake News Dataset

Along with COVID-19 pandemic we are also fighting an `infodemic'. Fake news and rumors are rampant on social media. Believing in rumors can cause significant harm. This is further exacerbated at the time of a pandemic. To tackle this, we curate and release a manually annotated dataset of 10,700 social media posts and articles of real and fake news on COVID-19. We benchmark the annotated dataset with four machine learning baselines - Decision Tree, Logistic Regression, Gradient Boost, and Support Vector Machine (SVM). We obtain the best performance of 93.46% F1-score with SVM. The data and code is available at: https://github.com/parthpatwa/covid19-fake-news-dectection

cs.CL↗

arXiv2021

Unexpected variations in the kinetics of solid solution alloys due to local interactions

Diffusion of atoms in solids is one of the most fundamental kinetic processes that ultimately governs many materials properties. Here, we report on a combined first-principles and kinetic Monte Carlo study of macroscopic diffusion properties of disordered Ti-Ta alloys over the entire composition range. Using simple cluster expansion model Hamiltonians parametrized on density functional theory data, we compute transport properties explicitly including local interactions between the two atomic species and compare them with the non-interacting diffusion model for disordered, random alloys. Surprisingly, we find that although these alloys thermodynamically behave as nearly random solid solutions, their kinetic properties deviate significantly from the behavior predicted by diffusion models for non-interacting systems. We attribute these differences in transport properties to the local interactions that create a rather corrugated potential energy landscape and consequently give rise to energetically non-degenerate end-states of diffusion processes which cannot be realized in a non-interacting disordered or other simpler diffusion models. The findings emphasize the limitations of the widely known non-interacting disordered diffusion model for such systems. Furthermore, we explain that changes in mobility in these alloys is predominantly due to changes in the correlation factor caused by the local interactions. Our work thus highlights the importance of explicitly including local interactions when assessing the transport properties of thermodynamically nearly disordered alloys.

cond-mat.mtrl-sci↗

arXiv2021

Transport and fluctuations in mass aggregation processes: mobility driven clustering

We calculate the bulk-diffusion coefficient and the conductivity in a broad class of conserved-mass aggregation processes on a ring of discrete sites. These processes involve chipping and fragmentation of masses, which diffuse around and aggregate upon contact with their neighboring masses. We find that, even in the absence of microscopic time reversibility, the systems satisfy an Einstein relation, which connects the ratio of the conductivity and the bulk-diffusion coefficient to mass fluctuation. Interestingly, when aggregation dominates over chipping, the conductivity or, equivalently, the mobility, gets enhanced. The enhancement in conductivity, in accordance with the Einstein relation, results in large mass fluctuations, implying a {\it mobility driven clustering} in the system. Indeed, in a certain parameter regime, we demonstrate that the conductivity diverges beyond a critical density, signaling the onset of a condensation transition observed in the past. In a striking similarity to Bose-Einstein condensation, the condensate formation along with the diverging conductivity thus underlies a dynamic "superfluidlike" transition in these nonequilibrium systems. Notably, the bulk-diffusion coefficient remains finite in all cases. Our analytic results are in a quite good agreement with simulations.

cond-mat.stat-mech↗

arXiv2021

Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detection

As the COVID-19 pandemic sweeps across the world, it has been accompanied by a tsunami of fake news and misinformation on social media. At the time when reliable information is vital for public health and safety, COVID-19 related fake news has been spreading even faster than the facts. During times such as the COVID-19 pandemic, fake news can not only cause intellectual confusion but can also place lives of people at risk. This calls for an immediate need to contain the spread of such misinformation on social media. We introduce CTF, the first COVID-19 Twitter fake news dataset with labeled genuine and fake tweets. Additionally, we propose Cross-SEAN, a cross-stitch based semi-supervised end-to-end neural attention model, which leverages the large amount of unlabelled data. Cross-SEAN partially generalises to emerging fake news as it learns from relevant external knowledge. We compare Cross-SEAN with seven state-of-the-art fake news detection methods. We observe that it achieves $0.95$ F1 Score on CTF, outperforming the best baseline by $9\%$. We also develop Chrome-SEAN, a Cross-SEAN based chrome extension for real-time detection of fake tweets.

cs.CL↗

arXiv2021

Combining exogenous and endogenous signals with a semi-supervised co-attention network for early detection of COVID-19 fake tweets

Fake tweets are observed to be ever-increasing, demanding immediate countermeasures to combat their spread. During COVID-19, tweets with misinformation should be flagged and neutralized in their early stages to mitigate the damages. Most of the existing methods for early detection of fake news assume to have enough propagation information for large labeled tweets -- which may not be an ideal setting for cases like COVID-19 where both aspects are largely absent. In this work, we present ENDEMIC, a novel early detection model which leverages exogenous and endogenous signals related to tweets, while learning on limited labeled data. We first develop a novel dataset, called CTF for early COVID-19 Twitter fake news, with additional behavioral test sets to validate early detection. We build a heterogeneous graph with follower-followee, user-tweet, and tweet-retweet connections and train a graph embedding model to aggregate propagation information. Graph embeddings and contextual features constitute endogenous, while time-relative web-scraped information constitutes exogenous signals. ENDEMIC is trained in a semi-supervised fashion, overcoming the challenge of limited labeled data. We propose a co-attention mechanism to fuse signal representations optimally. Experimental results on ECTF, PolitiFact, and GossipCop show that ENDEMIC is highly reliable in detecting early fake tweets, outperforming nine state-of-the-art methods significantly.

cs.CL↗

arXiv2021

ABOME: A Multi-platform Data Repository of Artificially Boosted Online Media Entities

The rise of online media has incentivized users to adopt various unethical and artificial ways of gaining social growth to boost their credibility within a short time period. In this paper, we introduce ABOME, a novel multi-platform data repository consisting of artificially boosted (also known as blackmarket-driven collusive entities) online media entities such as Twitter tweets/users and YouTube videos/channels, which are prevalent but often unnoticed in online media. ABOME allows quick querying of collusive entities across platforms. These include details of collusive entities involved in blackmarket services to gain artificially boosted appraisals in the form of likes, retweets, views, comments, follows and subscriptions. ABOME contains data related to tweets and users on Twitter, YouTube videos and YouTube channels. We believe that ABOME is a unique data repository that can be used as a benchmark to identify and analyze blackmarket-driven fraudulent activities in online media. We also develop SearchBM, an API and a web portal that offers a free service to identify blackmarket entities.

cs.SI↗

arXiv2021

An Embedding-based Joint Sentiment-Topic Model for Short Texts

Short text is a popular avenue of sharing feedback, opinions and reviews on social media, e-commerce platforms, etc. Many companies need to extract meaningful information (which may include thematic content as well as semantic polarity) out of such short texts to understand users' behaviour. However, obtaining high quality sentiment-associated and human interpretable themes still remains a challenge for short texts. In this paper we develop ELJST, an embedding enhanced generative joint sentiment-topic model that can discover more coherent and diverse topics from short texts. It uses Markov Random Field Regularizer that can be seen as a generalisation of skip-gram based models. Further, it can leverage higher-order semantic information appearing in word embedding, such as self-attention weights in graphical models. Our results show an average improvement of 10% in topic coherence and 5% in topic diversification over baselines. Finally, ELJST helps understand users' behaviour at more granular levels which can be explained. All these can bring significant values to the service and healthcare industries often dealing with customers.

cs.CL↗

arXiv2021

Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysis

Today's Internet is awash in memes as they are humorous, satirical, or ironic which make people laugh. According to a survey, 33% of social media users in age bracket [13-35] send memes every day, whereas more than 50% send every week. Some of these memes spread rapidly within a very short time-frame, and their virality depends on the novelty of their (textual and visual) content. A few of them convey positive messages, such as funny or motivational quotes; while others are meant to mock/hurt someone's feelings through sarcastic or offensive messages. Despite the appealing nature of memes and their rapid emergence on social media, effective analysis of memes has not been adequately attempted to the extent it deserves. In this paper, we attempt to solve the same set of tasks suggested in the SemEval'20-Memotion Analysis competition. We propose a multi-hop attention-based deep neural network framework, called MHA-MEME, whose prime objective is to leverage the spatial-domain correspondence between the visual modality (an image) and various textual segments to extract fine-grained feature representations for classification. We evaluate MHA-MEME on the 'Memotion Analysis' dataset for all three sub-tasks - sentiment classification, affect classification, and affect class quantification. Our comparative study shows sota performances of MHA-MEME for all three tasks compared to the top systems that participated in the competition. Unlike all the baselines which perform inconsistently across all three tasks, MHA-MEME outperforms baselines in all the tasks on average. Moreover, we validate the generalization of MHA-MEME on another set of manually annotated test samples and observe it to be consistent. Finally, we establish the interpretability of MHA-MEME.

cs.CL↗