In the context of data visualization, as in other grounded settings, referents are created by the task the agents engage in and are salient because they belong to the shared physical setting. Our focus is on resolving references to visualizations on large displays; crucially, reference resolution is directly involved in the process of creating new entities, namely new visualizations. First, we developed a reference resolution model for a conversational assistant. We trained the assistant on controlled dialogues for data visualizations involving a single user. Second, we ported the conversational assistant including its reference resolution model to a different domain, supporting two users collaborating on a data exploration task. We explore how the new setting affects reference detection and resolution; we compare the performance in the controlled vs unconstrained setting, and discuss the general lessons that we draw from this adaptation.

Depression, a widespread mental health disorder, affects a significant portion of the global population. Timely identification and intervention play a crucial role in ensuring effective treatment and support. Therefore, this research paper proposes a fine-tuned RoBERTa-based model for identifying depression in social media posts. In addition to the proposed model, Sentence-BERT is employed to encode social media posts into vector representations. These encoded vectors are then utilized in eight different popular classical machine learning models. The proposed fine-tuned RoBERTa model achieved a best macro F1-score of 0.55 for the development dataset and a comparable score of 0.41 for the testing dataset. Additionally, combining Sentence-BERT with Naive Bayes (S-BERT + NB) outperformed the fine-tuned RoBERTa model, achieving a slightly higher macro F1-score of 0.42. This demonstrates the effectiveness of the approach in detecting depression from social media posts.

This paper addresses the issue of Hope Speech detection using machine learning techniques. Designing a robust model that helps in predicting the target class with higher accuracy is a challenging task in machine learning, especially when the distribution of the class labels is highly imbalanced. This study uses and compares the experimental outcomes of the different oversampling techniques. Many models are implemented to classify the comments into Hope and Non-Hope speech, and it found that machine learning algorithms perform better than deep learning models. The English language dataset used in this research was developed by collecting YouTube comments and is part of the task “ACL-2022:Hope Speech Detection for Equality, Diversity, and Inclusion”. The proposed model achieved a weighted F1-score of 0.55 on the test dataset and secured the first rank among the participated teams.

Language should be accommodating of equality and diversity as a fundamental aspect of communication. The language of internet users has a big impact on peer users all over the world. On virtual platforms such as Facebook, Twitter, and YouTube, people express their opinions in different languages. People respect others’ accomplishments, pray for their well-being, and cheer them on when they fail. Such motivational remarks are hope speech remarks. Simultaneously, a group of users encourages discrimination against women, people of color, people with disabilities, and other minorities based on gender, race, sexual orientation, and other factors. To recognize hope speech from YouTube comments, the current study offers an ensemble approach that combines a support vector machine, logistic regression, and random forest classifiers. Extensive testing was carried out to discover the best features for the aforementioned classifiers. In the support vector machine and logistic regression classifiers, char-level TF-IDF features were used, whereas in the random forest classifier, word-level features were used. The proposed ensemble model performed significantly well among English, Spanish, Tamil, Malayalam, and Kannada YouTube comments.

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.

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.

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.