Task Based Information Retrieval

The need for search often arises from a person's need to achieve a goal, or a task such as booking travels, buying a house, etc. Contemporary search engines focus on retrieving documents relevant to the query submitted as opposed to understanding and supporting the underlying information needs (or tasks) that have led a person to submit the query. Therefore, search engine users often have to submit multiple queries to the current systems to achieve a single information need.

Having identified that users often have to reformulate their queries in order to achieve their final goal, most current search engines attempt to assist users towards a better expression of their needs by suggesting queries to them, other than the query currently issued. However, query suggestions mainly focus on helping the user refine their current query, as opposed to helping them identify and explore aspects related to their current complex tasks. For example, when a user issues the query "flights to Barcelona", it is clear that the user is planning to travel to Barcelona and it is very likely that the user will also need to search for hotels in Barcelona or for shuttles from Barcelona airport. Since query suggestions mainly focus on refining the current query, suggestions provided by commonly used search engines are mostly of the form "flights to Barcelona from LOCATION", or "FLIGHT-CAREER-NAME flights to Barcelona" and the result pages provided by these systems do not contain any information that could help users book hotels or shuttles from the airport.

For very common tasks such as arranging travels, it may be possible to manually identify and guide the user through a list of (sub)tasks that need to be achieved in order to complete a certain task (booking a flight, finding a hotel, looking for points of interest, etc. when the user tries to arrange travel). However, given the variety of tasks search engines are used for, this would only be possible for a very small subset of them.

Furthermore, quite often search engines are used for achieving such complex tasks that often the searcher themself lacks the task knowledge necessary to decide which step to tackle next. For example, a searcher looking for information about how to maintain a car with no prior knowledge would first need to use the search engine to identify the parts of the car that need maintenance and issue separate queries to learn about maintaining each part. Hence, retrieval systems that can automatically detect the task the user is trying to achieve and guide them through the process are needed, where a search task has been previously defined as an atomic information need that consists of a set of related (sub)tasks.

Even though designing information retrieval (IR) systems that can characterize/identify tasks, and can respond to them efficiently is listed as one of the grand challenges in information retrieval, very little progress has been made in this direction. The main goal of this proposal is to devise task oriented retrieval systems, retrieval systems that can automatically detect the task that the user is trying to achieve and guide them through the process (steps) needed to achieve the task.

The proposed research is expected to have a high impact in society and in the economy. Functioning task oriented IR systems would completely change the way people interact with IR systems, enabling them to reach relevant information faster. It is estimated that an enterprise employing 1,000 knowledge workers annually wastes nearly $2,5 million due to an inability to find information, $5 million due to duplicating information that already exists within the enterprise, and $15 million due to opportunity costs caused by time wasted looking for information and recreating information that already existed but couldn't be found [1]. Furthermore, given the widespread usage of IR systems in everyday lives, devising systems that enable end users to reach required information with less effort would significantly improve the search experience of a broad set of users ranging from patent office workers to journalists, as well as every day users of the web. Thus, task based IR systems could bring enormous economic benefits to society in terms of enhanced productivity, reduced costs for businesses and new e-commerce opportunities.

With interfaces over which IR systems are being used getting smaller (e.g. smart phones, smart watches), there is an increasing need for devising IR systems that can provide end users with required information with less input from them. The proposed research is likely to significantly improve the experience of the end users of such systems. Given this, we believe that next generation search engines need to be task based, and that major search engine companies such as Google will soon start investing on the design of such systems. This fellowship would enable the design of such systems to originate from an academic institution in the UK, possibly leading to new companies that can potentially reach the success of Google. This would enable the UK to be a leader in the design of next generation IR systems, which could improve the UK economy.

Placing the user in the task-subtask space provides tremendous opportunity to contextually target the user in terms of recommendations, advertisements, etc. Thus, potential benefits of the proposed research go beyond a traditional search setting and would lead to different ways of thinking about recommendation, advertisements, QA systems, mobile applications and intelligent assistants, leading to improved experience for end users of these systems. Hence, the proposed work is likely to have impact in existing businesses working in these areas. Furthermore, since the proposed search can be seen as a new way of thinking about information retrieval and access systems, it is expected to lead to new businesses and start-ups (e.g. QA systems guiding users through tasks, new phone apps/web portals addressing common major tasks, etc.). These businesses could significantly affect the UK economy and lead to new job opportunities for the society.

Search Solutions organized by the British Computing Society Information Retrieval Specialist Group is an annual event widely attended by people from the industry. In order to reach different types of businesses from the industry outside of existing collaborations, the PI plans to publicize the proposed research through Search Solutions by giving a talk or a tutorial.
Digital Catapult is an initiative whose goal is to increase the number of digital businesses in the UK by helping academics with leading expertise to commercialize their work. It has worked with over 2000 SMEs and has led to several new businesses [2]. The PI is already in touch with the Digital Catapult and has been invited to give a keynote talk at the venue. Through her connections at the Digital Catapult, she plans to reach further businesses and explore opportunities to start a business related to the proposal.

References
[1] S. Feldman, C. Sherman. The high cost of not finding information. Technical Report, IDC, April '03.
[2] https://digital.catapult.org.uk/