Text-embedding models often exhibit biases arising from the data on which they are trained. In this paper, we examine a hitherto unexplored bias in text-embeddings: bias arising from the presence of $\textit{names}$ such as persons, locations, organizations etc. in the text. Our study shows how the presence of $\textit{name-bias}$ in text-embedding models can potentially lead to erroneous conclusions in assessment of thematic similarity.Text-embeddings can mistakenly indicate similarity between texts based on names in the text, even when their actual semantic content has no similarity or indicate dissimilarity simply because of the names in the text even when the texts match semantically. We first demonstrate the presence of name bias in different text-embedding models and then propose $\textit{text-anonymization}$ during inference which involves removing references to names, while preserving the core theme of the text. The efficacy of the anonymization approach is demonstrated on two downstream NLP tasks, achieving significant performance gains. Our simple and training-optimization-free approach offers a practical and easily implementable solution to mitigate name bias.

Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper, we conduct a comprehensive examination of the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks. Using several general and cultural commonsense benchmarks, we find that (1) LLMs have a significant discrepancy in performance when tested on culture-specific commonsense knowledge for different cultures; (2) LLMs' general commonsense capability is affected by cultural context; and (3) The language used to query the LLMs can impact their performance on cultural-related tasks. Our study points to the inherent bias in the cultural understanding of LLMs and provides insights that can help develop culturally aware language models.

The evolution of legal datasets and the advent of large language models (LLMs) have significantly transformed the legal field, particularly in the generation of case judgment summaries. However, a critical concern arises regarding the potential biases embedded within these summaries. This study scrutinizes the biases present in case judgment summaries produced by legal datasets and large language models. The research aims to analyze the impact of biases on legal decision making. By interrogating the accuracy, fairness, and implications of biases in these summaries, this study contributes to a better understanding of the role of technology in legal contexts and the implications for justice systems worldwide. In this study, we investigate biases wrt Gender-related keywords, Race-related keywords, Keywords related to crime against women, Country names and religious keywords. The study shows interesting evidences of biases in the outputs generated by the large language models and pre-trained abstractive summarization models. The reasoning behind these biases needs further studies.

Recent progress in generative models has resulted in models that produce both realistic as well as relevant images for most textual inputs. These models are being used to generate millions of images everyday, and hold the potential to drastically impact areas such as generative art, digital marketing and data augmentation. Given their outsized impact, it is important to ensure that the generated content reflects the artifacts and surroundings across the globe, rather than over-representing certain parts of the world. In this paper, we measure the geographical representativeness of common nouns (e.g., a house) generated through DALL.E 2 and Stable Diffusion models using a crowdsourced study comprising 540 participants across 27 countries. For deliberately underspecified inputs without country names, the generated images most reflect the surroundings of the United States followed by India, and the top generations rarely reflect surroundings from all other countries (average score less than 3 out of 5). Specifying the country names in the input increases the representativeness by 1.44 points on average for DALL.E 2 and 0.75 for Stable Diffusion, however, the overall scores for many countries still remain low, highlighting the need for future models to be more geographically inclusive. Lastly, we examine the feasibility of quantifying the geographical representativeness of generated images without conducting user studies.

Today is the era of intelligence in machines. With the advances in Artificial Intelligence, machines have started to impersonate different human traits, a chatbot is the next big thing in the domain of conversational services. A chatbot is a virtual person who is capable to carry out a natural conversation with people. They can include skills that enable them to converse with the humans in audio, visual, or textual formats. Artificial intelligence conversational entities, also called chatbots, conversational agents, or dialogue system, are an excellent example of such machines. Obtaining the right information at the right time and place is the key to effective disaster management. The term "disaster management" encompasses both natural and human-caused disasters. To assist citizens, our project is to create a COVID Assistant to provide the need of up to date information to be available 24 hours. With the growth in the World Wide Web, it is quite intelligible that users are interested in the swift and relatedly correct information for their hunt. A chatbot can be seen as a question-and-answer system in which experts provide knowledge to solicit users. This master thesis is dedicated to discuss COVID Assistant chatbot and explain each component in detail. The design of the proposed chatbot is introduced by its seven components: Ontology, Web Scraping module, DB, State Machine, keyword Extractor, Trained chatbot, and User Interface.

An important step in data analysis is data exploration and representation. In this tutorial we will see how by combining a technique called Principal Component Analysis (PCA) together with Cluster Analysis we can represent in a two-dimensional space data defined in a higher dimensional one while, at the same time, being able to group this data in similar groups or clusters and find hidden relationships in our data. More concretely, PCA reduces data dimensionality by finding principal components. These are the directions of maximum variation in a dataset. By reducing a dataset original features or variables to a reduced set of new ones based on the principal components, we end up with the minimum number of variables that keep the maximum amount of variation or information about how the data is distributed. If we end up with just two of these new variables, we will be able to represent each sample in our data in a two-dimensional chart (e.g. a scatterplot). As an unsupervised data analysis technique, clustering organises data samples by proximity based on its variables.

An important step in data analysis is data exploration and representation. In this tutorial we will see how by combining a technique called Principal Component Analysis (PCA) together with Cluster Analysis we can represent in a two-dimensional space data defined in a higher dimensional one while, at the same time, being able to group this data in similar groups or clusters and find hidden relationships in our data. More concretely, PCA reduces data dimensionality by finding principal components. These are the directions of maximum variation in a dataset. By reducing a dataset original features or variables to a reduced set of new ones based on the principal components, we end up with the minimum number of variables that keep the maximum amount of variation or information about how the data is distributed. If we end up with just two of these new variables, we will be able to represent each sample in our data in a two-dimensional chart (e.g. a scatterplot). As an unsupervised data analysis technique, clustering organises data samples by proximity based on its variables.

We are presenting a method to recognise geographical references in free text. Our tool must work on various languages with a mi ni-mum of language-dependent resources, except a gazetteer. The main difficulty is to disa mbiguate these place names by distinguis hing places from persons and by selecting the mo st likely place out of a list of homographi c place names world-wide. The system uses a number of language-independent clues and he uristics to disambiguate place name homogra phs. The final aim is to index texts with the countries and cities they mention and to automatically visualise this information on geographical maps using various tools.