Hate speech and offensive language recognition in social media platforms have been an active field of research over recent years. In non-native English spoken countries, social media texts are mostly in code mixed or script mixed/switched form. The current study presents extensive experiments using multiple machine learning, deep learning, and transfer learning models to detect offensive content on Twitter. The data set used for this study are in Tanglish (Tamil and English), Manglish (Malayalam and English) code-mixed, and Malayalam script-mixed. The experimental results showed that 1 to 6-gram character TF-IDF features are better for the said task. The best performing models were naive bayes, logistic regression, and vanilla neural network for the dataset Tamil code-mix, Malayalam code-mixed, and Malayalam script-mixed, respectively instead of more popular transfer learning models such as BERT and ULMFiT and hybrid deep models.

Many real-world problems require the combined application of multiple reasoning abilities—employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, “How much would the sea level rise if all ice in the world melted?” FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question-answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large-scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason.

Our goal is to develop an intelligent assistant to support users explore data via visualizations. We have collected a new corpus of conversations, CHICAGO-CRIME-VIS, geared towards supporting data visualization exploration, and we have annotated it for a variety of features, including contextualized dialogue acts. In this paper, we describe our strategies and their evaluation for dialogue act classification. We highlight how thinking aloud affects interpretation of dialogue acts in our setting and how to best capture that information. A key component of our strategy is data augmentation as applied to the training data, since our corpus is inherently small. We ran experiments with the Balanced Bagging Classifier (BAGC), Condiontal Random Field (CRF), and several Long Short Term Memory (LSTM) networks, and found that all of them improved compared to the baseline (e.g., without the data augmentation pipeline). CRF outperformed the other classification algorithms, with the LSTM networks showing modest improvement, even after obtaining a performance boost from domain-trained word embeddings. This result is of note because training a CRF is far less resource-intensive than training deep learning models, hence given a similar if not better performance, traditional methods may still be preferable in order to lower resource consumption.