Argument Mining (AM) involves identifying and extracting Argumentative Components (ACs) and their corresponding Argumentative Relations (ARs). Most of the prior works have broken down these tasks into multiple sub-tasks. Existing end-to-end setups primarily use the dependency parsing approach. This work introduces a generative paradigm-based end-to-end framework argTANL. argTANL frames the argumentative structures into label-augmented text, called Augmented Natural Language (ANL). This framework jointly extracts both ACs and ARs from a given argumentative text. Additionally, this study explores the impact of Argumentative and Discourse markers on enhancing the model’s performance within the proposed framework. Two distinct frameworks, Marker-Enhanced argTANL (ME-argTANL) and argTANL with specialized Marker-Based Fine-Tuning, are proposed to achieve this. Extensive experiments are conducted on three standard AM benchmarks to demonstrate the superior performance of the ME-argTANL.

Argument Mining (AM) helps in automating the extraction of complex argumentative structures such as Argument Components (ACs) like Premise, Claim etc. and Argumentative Relations (ARs) like Support, Attack etc. in an argumentative text. Due to the inherent complexity of reasoning involved with this task, modelling dependencies between ACs and ARs is challenging. Most of the recent approaches formulate this task through a generative paradigm by flattening the argumentative structures. In contrast to that, this study jointly formulates the key tasks of AM in an end-to-end fashion using Autoregressive Argumentative Structure Prediction (AASP) framework. The proposed AASP framework is based on the autoregressive structure prediction framework that has given good performance for several NLP tasks. AASP framework models the argumentative structures as constrained pre-defined sets of actions with the help of a conditional pre-trained language model. These actions build the argumentative structures step-by-step in an autoregressive manner to capture the flow of argumentative reasoning in an efficient way. Extensive experiments conducted on three standard AM benchmarks demonstrate that AASP achieves state-of-the-art (SoTA) results across all AM tasks in two benchmarks and delivers strong results in one benchmark.

Extensive application of machine learning in the areas that impact human lives has significantly spurred considerable interest in developing algorithms that are demonstrably fair. Recent efforts in this field have led to the creation of numerous algorithms addressing the paradigm of clustering with fairness constraints. In this research, we adopt disparate impact criteria from supervised learning scenarios and incorporate it into clustering by specifically focusing on decision boundary fairness. The existing fairness definitions in clustering scenarios mostly deal with Balance of the clusters or the representation of sensitive groups in the clusters. We developed a new algorithm called Fair Maximum Margin Clustering (FMMC), by incorporating the disparate impact criteria into the Maximum Margin Clustering (MMC) algorithm. The FMMC algorithm ensures that the distance of each data point from hyperplane is uncorrelated with that data point’s sensitive attribute value. This constraint is designed to prevent any sensitive group from being negatively impacted by the decision boundary. We show that the performance of the FMMC algorithm is better than that of MMC algorithm in terms of traditional fairness measures such as Balance. We also demonstrate that the FMMC algorithm achieves fair clustering while maintaining the clustering performance of the original MMC algorithm. We validate the effectiveness of our approach through experiments on synthetic and real-world datasets.

Web elements associate with a set of visual features based on their data modality. For example, text associated with font-size and font-family whereas images associate with intensity and color. The unavailability of methods to relate these heterogeneous visual features limiting the attention-based analyses on webpages. In this paper, we propose a novel approach to establish the correlation between text and image visual features that influence users' attention. We pair the visual features of text and images based on their associated fixation-indices obtained from eye-tracking. From paired data, a common subspace is learned using Canonical Correlation Analysis (CCA) to maximize the correlation between them. The performance of the proposed approach is analyzed through a controlled eye-tracking experiment conducted on 51 real-world webpages. A very high correlation of 99.48% is achieved between text and images with text related font families and image related color features influencing the correlation.