This paper describes our approach for SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). The task deals with identification and categorization of sexist content into fine-grained categories for explainability in sexism classification. The explainable categorization is proposed through a set of three hierarchical tasks that constitute a taxonomy of sexist content, each task being more granular than the former for categorization of the content. Our team (iREL) participated in all three hierarchical subtasks. Considering the inter-connected task structure, we study multilevel training to study the transfer learning from coarser to finer tasks. Our experiments based on pretrained transformer architectures also make use of additional strategies such as domain-adaptive pretraining to adapt our models to the nature of the content dealt with, and use of the focal loss objective for handling class imbalances. Our best-performing systems on the three tasks achieve macro-F1 scores of 85.93, 69.96 and 54.62 on their respective validation sets.

The Clickbait Challenge targets spoiling the clickbaits using short pieces of information known as spoilers to satisfy the curiosity induced by a clickbait post. The large context of the article associated with the clickbait and differences in the spoiler forms, make the task challenging. Hence, to tackle the large context, we propose an Information Condensation-based approach, which prunes down the unnecessary context. Given an article, our filtering module optimised with a contrastive learning objective first selects the parapraphs that are the most relevant to the corresponding clickbait.The resulting condensed article is then fed to the two downstream tasks of spoiler type classification and spoiler generation. We demonstrate and analyze the gains from this approach on both the tasks. Overall, we win the task of spoiler type classification and achieve competitive results on spoiler generation.

Generating domain-specific content such as legal clauses based on minimal user-provided information can be of significant benefit in automating legal contract generation. In this paper, we propose a controllable graph-based mechanism that can generate legal clauses using only the topic or type of the legal clauses. Our pipeline consists of two stages involving a graph-based planner followed by a clause generator. The planner outlines the content of a legal clause as a sequence of keywords in the order of generic to more specific clause information based on the input topic using a controllable graph-based mechanism. The generation stage takes in a given plan and generates a clause. The pipeline consists of a graph-based planner followed by text generation. We illustrate the effectiveness of our proposed two-stage approach on a broad set of clause topics in contracts.

This paper provides a comparison of different deep learning methods for identifying misogynous memes for SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification. In this task, we experiment with architectures in the identification of misogynous content in memes by making use of text and image-based information. The different deep learning methods compared in this paper are: (i) unimodal image or text models (ii) fusion of unimodal models (iii) multimodal transformers models and (iv) transformers further pretrained on a multimodal task. From our experiments, we found pretrained multimodal transformer architectures to strongly outperform the models involving the fusion of representation from both the modalities.

The task of multilingual news article similarity entails determining the degree of similarity of a given pair of news articles in a language-agnostic setting. This task aims to determine the extent to which the articles deal with the entities and events in question without much consideration of the subjective aspects of the discourse. Considering the superior representations being given by these models as validated on other tasks in NLP across an array of high and low-resource languages and this task not having any restricted set of languages to focus on, we adopted using the encoder representations from these models as our choice throughout our experiments. For modeling the similarity task by using the representations given by these models, a Siamese architecture was used as the underlying architecture. In experimentation, we investigated on several fronts including features passed to the encoder model, data augmentation and ensembling among our major experiments. We found data augmentation to be the most effective working strategy among our experiments.