Originally published on Towards AI. I came across this wonderful paper on Prompting while going through this amazing course on Advanced NLP (UMass). Being a survey paper, they have given a holistic explanation of this latest paradigm in NLP. Over multiple articles, we will be discussing the key highlights from the paper and learn why Prompting is considered to be "The Second Sea Change in NLP". To appreciate what is prompting and to get started, Part 1 discusses 4 major paradigms that have occurred over the past years.

COVID-19 has transformed how we travel, work and live. As we emerge from the pandemic, our transport, energy and internet patterns will again undergo a seismic shift, and so will the infrastructure systems that underlie them: our roads, railways, water supply, electrical grids and telecommunications. To plan and optimise these systems, operators need to forecast future usage. Forecasting energy demand and renewable energy generation, for instance, can help operators to avoid unnecessary use of fossil fuels. Artificial intelligence (AI), and more specifically machine learning (ML), can play a crucial role in making these forecasts, helping to guide the evolution of our infrastructure systems.

By Rajiv Saxena Police in Detroit, while investigating, were trying to figure out who stole five watches from a Shinola retail store. Authorities mentioned that the thief took off with an estimated $3,800 worth of merchandise. Investigators pulled a security video that had recorded the incident from cameras installed in the store and neighbourhood, which is very common in the US. Detectives zoomed in on the grainy footage and ran the person who appeared to be primary through'facial recognition software'. A hit came back: Robert Julian - Borchak Williams, 42, of Farmington Hills, Michigan, about 25 miles northwest of Detroit. In January, police pulled up to Williams' home and arrested him while he stood on his front lawn in front of his wife and two daughters, ages 2 and 5, who cried as they watched their father being taken away in the patrol car.

A Slate staff writer who regularly reports on Christianity responds to Andrew D. Hudson's "A Priest, a Rabbi, and a Robot Walk Into a Bar." The Michigan-based company Covenant Eyes markets itself to Christians who want to stop viewing pornography. Its software takes screenshots of a user's screen activity, uses A.I. to scan it for pornographic imagery, and then sends regular reports to the user and a designated "ally" who has agreed to hold him accountable. The company's name comes from a Bible verse that reads, "I made a covenant with my eyes not to look lustfully at a young woman." Everyone wants technology to reflect their own worldview, and religious conservatives are no exception.

As new technology drives a sea change across the customer experience sector, it is important to evaluate how the public honestly values personal interaction as a service need. Webhelp conducted research with the polling experts YouGov asking 2,000 British adults for their thoughts on Artificial Intelligence (AI) and how it might change the way that brands offer customer service. Webhelp UK's CEO, David Turner, looks at the importance of the human touch. Rules in CX are being rewritten. It's getting harder to predict the future but we can still try.

Almost everything you hear about artificial intelligence today is thanks to deep learning. This category of algorithms works by using statistics to find patterns in data, and it has proved immensely powerful in mimicking human skills such as our ability to see and hear. To a very narrow extent, it can even emulate our ability to reason. These capabilities power Google's search, Facebook's news feed, and Netflix's recommendation engine--and are transforming industries like health care and education. But though deep learning has singlehandedly thrust AI into the public eye, it represents just a small blip in the history of humanity's quest to replicate our own intelligence.

Almost everything you hear about artificial intelligence today is thanks to deep learning. This category of algorithms works by using statistics to find patterns in data, and it has proved immensely powerful in mimicking human skills such as our ability to see and hear. To a very narrow extent, it can even emulate our ability to reason. These capabilities power Google's search, Facebook's news feed, and Netflix's recommendation engine--and are transforming industries like health care and education. But though deep learning has singlehandedly thrust AI into the public eye, it represents just a small blip in the history of humanity's quest to replicate our own intelligence.

The billowing compute and data demands that spurred the oil and gas industry to be the largest commercial users of high-performance computing are now propelling the competitive sector to deploy the latest AI technologies. Beyond the requirement for accurate and speedy seismic and reservoir simulation, oil and gas operations face torrents of sensor, geolocation, weather, drilling and seismic data. Just the sensor data alone from one off-shore rig can accrue to hundreds of terabytes of data annually, however most of this remains unanalyzed, dark data.

Kantar Millward Brown, a leading global research agency helping businesses grow strong brands, has released its annual Media and Digital Predictions for 2018. For the 10th year running, the company's predictions provide marketers with a clear guide to the challenges and opportunities of the next 12 months, helping them shape their media and digital marketing strategies. The challenge with non-traditional forms of advertising is how to prove effectiveness; whether the objective is to make people more aware, change perceptions, or take action. The impact and return on investment can be compared directly with other brand and behavioral metrics, but brands must be clear about their objectives and consider how to measure effectiveness early in the process. How brands communicate with people will continue to evolve rapidly away from just standard paid media.

Unsupervised discovery of synonymous phrases is useful in a variety of tasks ranging from text mining and search engines to semantic analysis and machine translation. This paper presents an unsupervised corpus-based conditional model: Near-Synonym System (NeSS) for finding phrasal synonyms and near synonyms that requires only a large monolingual corpus. The method is based on maximizing information-theoretic combinations of shared contexts and is parallelizable for large-scale processing. An evaluation framework with crowd-sourced judgments is proposed and results are compared with alternate methods, demonstrating considerably superior results to the literature and to thesaurus look up for multi-word phrases. Moreover, the results show that the statistical scoring functions and overall scalability of the system are more important than language specific NLP tools. The method is language-independent and practically useable due to accuracy and real-time performance via parallel decomposition.