The paper describes our submissions for the Social Media Mining for Health (SMM4H) workshop 2022 shared tasks. We participated in 2 tasks: (1) classification of adverse drug events (ADE) mentions in english tweets (Task-1a) and (2) classification of self-reported intimate partner violence (IPV) on twitter (Task 7). We proposed an approach that uses RoBERTa (A Robustly Optimized BERT Pretraining Approach) fine-tuned with a label distribution-aware margin loss function and post-hoc posterior calibration for robust inference against class imbalance. We achieved a 4% and 1 % increase in performance on IPV and ADE respectively when compared with the traditional fine-tuning strategy with unweighted cross-entropy loss.

The discovery of causality mentions from text is a core cognitive concept and appears in many natural language processing (NLP) applications. In this paper, we study the task of Event Causality Identification (ECI) from social-political news. The aim of the task is to detect causal relationships between event mention pairs in text. Although deep learning models have recently achieved a state-of-the-art performance on many tasks and applications in NLP, most of them still fail to capture rich semantic and syntactic structures within sentences which is key for causality classification. We present a solution for causal event detection from social-political news that captures semantic and syntactic information based on gated graph neural networks (GGNN) and contextualized language embeddings. Experimental results show that our proposed method outperforms the baseline model (BERT (Bidirectional Embeddings from Transformers) in terms of f1-score and accuracy.

Social media and online forums have made it easier for people to share their views and opinions on various topics in society. In this paper, we focus on posts discussing investment related topics. When it comes to investment , people can now easily share their opinions about online traded items and also provide rationales to support their arguments on social media. However, there are millions of posts to read with potential of having some posts from amateur investors or completely unrelated posts. Identifying the most important posts that could lead to higher maximal potential profit (MPP) and lower maximal loss for investment is not a trivial task. In this paper, propose to use determinantal point processes and variational autoencoders to identify high quality posts from the given rationales. Experimental results suggest that our method mines quality posts compared to random selection and also latent variable modeling improves improves the quality of selected posts.

This paper describes our system for the submission to the TextGraphs 2022 shared task at COLING 2022: Natural Language Premise Selection (NLPS) from mathematical texts. The task of NLPS is about selecting mathematical statements called premises in a knowledge base written in natural language and mathematical formulae that are most likely to be used to prove a particular mathematical proof. We formulated this task as an unsupervised semantic similarity task by first obtaining contextualized embeddings of both the premises and mathematical proofs using sentence transformers. We then obtained the cosine similarity between the embeddings of premises and proofs and then selected premises with the highest cosine scores as the most probable. Our system improves over the baseline system that uses bag of words models based on term frequency inverse document frequency in terms of mean average precision (MAP) by about 23.5% (0.1516 versus 0.1228).

Transformers have achieved a state of the art performance across most natural language processing tasks. However the performance of these models degrade when being trained on skewed class distributions (class imbalance) because training tends to be biased towards head classes with most of the data points . Classical methods that have been proposed to handle this problem (re-sampling and re-weighting) often suffer from unstable performance, poor applicability and poor calibration. In this paper, we propose to use Bayesian methods and Venn-Abers predictors for well calibrated and robust training against class imbalance. Our proposed approach improves f1-score of the baseline RoBERTa (A Robustly Optimized Bidirectional Embedding from Transformers Pretraining Approach) model by about 6 points (79.0% against 72.6%) when training with class imbalanced data.