Retrieval of legal knowledge by the general public is a challenging problem due to the technicality of the professional knowledge and the lack of fundamental understanding by laypersons on the subject. Traditional information retrieval techniques assume that users are capable of formulating succinct and precise queries for effective document retrieval. In practice, however, the wide gap between the highly technical contents and untrained users makes legal knowledge retrieval very difficult. We propose a methodology, called QBR, which employs a Questions Bank (QB) as an effective medium for bridging the knowledge gap. We show how the QB is used to derive training samples to enhance the embedding of knowledge units within documents, which leads to effective fine-grained knowledge retrieval. We discuss and evaluate through experiments various advantages of QBR over traditional methods. These include more accurate, efficient, and explainable document retrieval, better comprehension of retrieval results, and highly effective fine-grained knowledge retrieval. We also present some case studies and show that QBR achieves social impact by assisting citizens to resolve everyday legal concerns.

Generating large-scale, domain-specific, multilingual multi-turn dialogue datasets remains a significant hurdle for training effective Multi-Turn Intent Classification models in chatbot systems. In this paper, we introduce Chain-of-Intent, a novel mechanism that combines Hidden Markov Models with Large Language Models (LLMs) to generate contextually aware, intent-driven conversations through self-play. By extracting domain-specific knowledge from e-commerce chat logs, we estimate conversation turns and intent transitions, which guide the generation of coherent dialogues. Leveraging LLMs to enhance emission probabilities, our approach produces natural and contextually consistent questions and answers. We also propose MINT-CL, a framework for multi-turn intent classification using multi-task contrastive learning, improving classification accuracy without the need for extensive annotated data. Evaluations show that our methods outperform baselines in dialogue quality and intent classification accuracy, especially in multilingual settings, while significantly reducing data generation efforts. Furthermore, we release MINT-E, a multilingual, intent-aware multi-turn e-commerce dialogue corpus to support future research in this area.

The advent of ChatGPT seems to represent a quantum leap in the capacity of artificial intelligence (AI) to reshape the world we live in. Things are moving quickly, and organisations must begin now to think about how they can harness the power of AI to improve their performance beyond what basic process automation has long made possible. Customer service is especially ripe for the kind of improvements that AI can bring. Whether for providers of consumer goods or services ranging from healthcare to insurance and financial products--customer service operations have long been plagued by chronic inefficiencies. AI can help to reverse that.

Rammas, DEWA's virtual AI employee, is available on seven channels for customer service. These include DEWA's smart app (iOS and Android), DEWA's website and social media account on Facebook, Amazon's Alexa, and Google Assistant, robots, and WhatsApp Business. Rammas provides round-the-clock multiple services and answers enquiries in English and Arabic. DEWA employs AI to enhance customer and employee happiness as well as improve the performance of its systems through'Rammas for You' and'Rammas at Work' and'Powered by Rammas'. Rammas has answered more than 6.4 million enquiries since its inception in the first quarter of 2017 and until the end of June 2022.

Chris Wyper, Director of Global Industry Strategy, Retail and E-commerce at Talkdesk, explores how retailers can leverage AI solutions to achieve more personalised CX and stand out in a competitive market. The rise of personalised or hyper-personalised service is one of the most significant changes we've seen across the retail sector over recent years. It might seem a little ironic that, at a time when personal interactions in-store and on the phone have decreased, the process of making a purchase has actually become less transactional and more personalised. Digitisation has paved the way for retailers to gather more data and analytics. Not only has this digitisation helped retailers better understand their customers, it's enabled them to respond in real-time to meet their needs..

The present-day world of online retail behemoths of Amazon, Argos and Asos etc undeniably leaves a small to medium sized businesses (SMEs) with a clear disadvantage when it comes to eCommerce. Despite their relative lack of exposure and customer loyalty there are, however, a number of ways that an SME can compete with the big dogs. One of these is through customer experience – something that AI chatbot perfectly facilitate. Especially when it comes to one of the deadliest challenges for any retailer: seasonal economic fluctuations. Seasonal changes massively shift the retail market and are extra testing to an SME that relies on a much smaller customer base.

Theories of public trust in chatbots in the public sector are presented. An online experiment was conducted to test the hypotheses. The public's initial trust in chatbots depends on the area of enquiry. Initial public trust was lower in the area of parental support than waste separation. Communicating certain purposes for using a chatbot is slightly trust-enhancing.

Last week, mayors representing over 750 million people, across the world's leading cities, published a statement of principles, warning against a return to "business as usual" as the world recovers from COVID-19. This advice is as relevant for enterprises as it is for society as a whole. COVID-19 has exposed a lack of resilience, severely impacting operational continuity. Indeed, Eurozone business activity fell to an all-time low in April. With the pandemic impacting every part of society, there are human considerations to every decision we make. While clearly the most important factor, public health professionals are already doing a great job of covering this issue.

The new report on the global Artificial Intelligence in the Telecommunication market is an extensive study on the overall prospects of the Artificial Intelligence in the Telecommunication market over the assessment period. Further, the report provides a thorough understanding of the key dynamics of the Artificial Intelligence in the Telecommunication market including the current trends, opportunities, drivers, and restraints. The report introspects the micro and macro-economic factors that are expected to nurture the growth of the Artificial Intelligence in the Telecommunication market in the upcoming years and the impact of the COVID-19 pandemic on the Artificial Intelligence in the Telecommunication . In addition, the report offers valuable insights pertaining to the supply chain challenges market players are likely to face in the upcoming months and solutions to tackle the same. The report suggests that the global Artificial Intelligence in the Telecommunication market is projected to reach a value of US$XX by the end of 2029 and grow at a CAGR of XX% through the forecast period (2019-2029).

The travel sector has arguably been slower than other industries to take up machine learning – a subset of the larger field of Artificial Intelligence – focusing on automation methods to learn and predict, from past data. Is it a cultural phenomenon? The travel industry is among most traditional of all in terms of its main selling point – the personalised, human-facing customer experience – and has struggled to come to terms with machines replacing human recommendation and action. Today's customer is seeking more answers, more quickly, from companies before and after buying products and services – and the modern traveller is no exception. Traditional travel firms need to move with the times and respond to customer expectations.