30 accepted papers
The Euclidean space is the familiar space for training neural models and performing arithmetic operations.However, many data types inherently possess complex geometries, and model training methods involve operating over their latent representations, which cannot be effectively captured in the Euclid…
Document structure editing involves manipulating localized textual, visual, and layout components in document images based on the user’s requests. Past works have shown that multimodal grounding of user requests in the document image and identifying the accurate structural components and their assoc…
We present a novel task of document-level script event prediction, which aims to predict the next event given a candidate list of narrative events in long-form documents. To enable this, we introduce DocSEP, a challenging dataset in two new domains - contractual documents and Wikipedia articles, whe…
Suicide is a serious public health issue, but it is preventable with timely intervention. Emerging studies have suggested there is a noticeable increase in the number of individuals sharing suicidal thoughts online. As a result, utilising advance Natural Language Processing techniques to build autom…
Predicting price variations of financial instruments for risk modeling and stock trading is challenging due to the stochastic nature of the stock market. While recent advancements in the Financial AI realm have expanded the scope of data and methods they use, such as textual and audio cues from fina…
The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in this area has been restricted to computer vision and risk ass…
Steganography is the art of hiding a secret message signal inside a publicly visible carrier with minimum perceptual loss in the carrier. In order to better hide information, it is critical to optimally represent the message-carrier wave interference while blending the message with the carrier. We p…
Recent studies have shown that social media has increasingly become a platform for users to express suicidal thoughts outside traditional clinical settings. With advances in Natural Language Processing strategies, it is now possible to design automated systems to assess suicide risk. However, such s…
Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often perform sub-optimally for abusive words as they are underrepresented in training corp…
Interpolative data augmentation has proven to be effective for NLP tasks. Despite its merits, the sample selection process in mixup is random, which might make it difficult for the model to generalize better and converge faster. We propose CIAug, a novel curriculum-based learning method that builds…
The rapid spread of information over social media influences quantitative trading and investments. The growing popularity of speculative trading of highly volatile assets such as cryptocurrencies and meme stocks presents a fresh challenge in the financial realm. Investigating such “bubbles” - period…
Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embed…
Financial prediction is complex due to the stochastic nature of the stock market. Semi-structured financial documents present comprehensive financial data in tabular formats, such as earnings, profit-loss statements, and balance sheets, and can often contain rich technical analysis along with a text…
Analyzing the temporal sequence of texts from sources such as social media, news, and parliamentary debates is a challenging problem as it exhibits time-varying scale-free properties and fine-grained timing irregularities. We propose a Hyperbolic Hawkes Attention Network (HYPHEN), which learns a dat…
In this paper, we present InterMix, an interference-based regularization and data augmentation strategy for automatic sound classification. InterMix creates virtual training examples by creating an interference-based mixed representation for a sampled phase difference and mixup ratio. InterMix can b…
Directed Acyclic Graphs and trees are widely prevalent in several real-world applications. These hierarchical structures show intriguing properties such as scale-free and bipartite nature, with fine-grained temporal irregularities among nodes. Building on advances in geometrical deep learning, we ex…
Non-Fungible Tokens (NFTs) are a relatively unexplored class of assets. Designing strategies to forecast NFT trends is an intricate task due to its extremely volatile nature. The market is largely driven by public sentiment and “hype”, which in turn has a high correlation with conversations taking p…
Volatility prediction is complex due to the stock market’s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and risk, but ignores the rich acoustic features in the company executives’ speech. Re…
Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their latent states representations - vectors that often possess complex hierarchical…
While emotion recognition is a well-studied task, it remains unexplored to a large extent in cross-lingual settings. Speech Emotion Recognition (SER) in low-resource languages poses difficulties as existing approaches for knowledge transfer do not generalize seamlessly. Probing the learning process…
In the financial realm, profit generation greatly relies on the complicated task of stock prediction. Lately, neural methods have shown success in exploiting stock affecting signals from textual data across news and tweets to forecast stock performance. However, the dynamic, stochastic, and variably…
Risk prediction is an essential task in financial markets. Merger and Acquisition (M&A) calls provide key insights into the claims made by company executives about the restructuring of the financial firms. Extracting vocal and textual cues from M&A calls can help model the risk associated with such…
The #MeToo movement on social media platforms initiated discussions over several facets of sexual harassment in our society. Prior work by the NLP community for automated identification of the narratives related to sexual abuse disclosures barely explored this social phenomenon as an independent tas…
It is challenging to design profitable and practical trading strategies, as stock price movements are highly stochastic, and the market is heavily influenced by chaotic data across sources like news and social media. Existing NLP approaches largely treat stock prediction as a classification or regre…
Quantitative trading and investment decision making are intricate financial tasks that rely on accurate stock selection. Despite advances in deep learning that have made significant progress in the complex and highly stochastic stock prediction problem, modern solutions face two significant limitati…
Recent psychological studies indicate that individuals exhibiting suicidal ideation increasingly turn to social media rather than mental health practitioners. Personally contextualizing the buildup of such ideation is critical for accurate identification of users at risk. In this work, we propose a…
Political discourses provide a forum for representatives to express their opinions and contribute towards policy making. Analyzing these discussions is crucial for recognizing possible delegates and making better voting choices in an independent nation. A politician's vote on a proposition is us…
Models with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution. We introduce Emix, a data augmentation method that uses interpolations of word embeddings and hidden layer representations to construct virtual examples. We show that Emix…
Parliamentary debates present a valuable language resource for analyzing comprehensive options in electing representatives under a functional, free society. However, the esoteric nature of political speech coupled with non-linguistic aspects such as political cohesion between party members presents…
Recently, several image processing and deep learning techniques have been applied to automate the detection of Acute Lymphoblastic Leukemia cells (ALL). However, most of them have consistently focused on classification mature stage cell images into binary categories of ALL or normal cells. The real…