Task Based Information Retrieval
Lead Research Organisation:
University College London
Department Name: Computer Science
Abstract
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.
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.
Planned Impact
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/
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/
People |
ORCID iD |
Emine Yilmaz (Principal Investigator / Fellow) |
Publications
Aldo Lipani
(2019)
A User Model for Query-Sessions
Bulathwela S
(2022)
Power to the Learner: Towards Human-Intuitive and Integrative Recommendations with Open Educational Resources
in Sustainability
Bulathwela S
(2020)
SUM'20: State-based User Modelling
Bulathwela S.
(2020)
TrueLearn: A family of bayesian algorithms to match lifelong learners to open educational resources
in AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
Bulathwela S.
(2020)
Towards an Integrative Educational Recommender for Lifelong Learners
in AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
Burnie A
(2020)
Analysing Social Media Forums to Discover Potential Causes of Phasic Shifts in Cryptocurrency Price Series
in Frontiers in Blockchain
Culpepper J
(2018)
Research Frontiers in Information Retrieval Report from the Third Strategic Workshop on Information Retrieval in Lorne (SWIRL 2018)
in ACM SIGIR Forum
Description | We have developed a new metric for the task based evaluation of information retrieval systems. This metric could be useful for offline evaluation of conversational retrieval systems, for which we are not aware of any metric that can be used in a completely offline test collection. We have two publications related to this work (appeared at ACM ICTIR 2019) and one paper to appear in ACM TOIS 2021. We have also developed a method that can be used to automatically identify the type of attributes a user may be looking for, given a question. Given a question (e.g. book a trip to London), the method is useful to automatically identify the additional necessary information that needs to be asked to the users (e.g. dates, budget, etc.). This work has been accepted to ACM SIGIR 2020. We have developed several methods for dialogue state tracking. The methods developed give the best performance on current datasets. We have also created a new dataset for dialogue state tracking and made it publicly available. The dataset constructed is a cleaner version of the commonly used Multiwoz dataset, hence islikely to be used widely used by researchers. |
Exploitation Route | The metric we have developed could potentially be used by search engines or intelligent assistants to evaluate the quality of their system in terms of helping users complete their tasks. The dataset constructed could be the primary dataset used for the task of dialogue state tracking. |
Sectors | Digital/Communication/Information Technologies (including Software) |
Description | Some of our research has led to the creation of the start-up, UserContext.AI. Even though the start-up is not active at this point, we plan to continue working on commercialising some of our ideas. I am currently also involved in the creation of another start-up, Humanloop, which aims at enabling humans and AI work together. As part of Humanloop, we plan to explore process automation as one application domain, which are based on some of the ideas we have developed as part of this project. Another start-up ContextScout, that was found by a PhD student from UCL was inspired by a public talk I gave related to the Task Based Information Retrieval project and have built a large team of researchers and engineers trying to commercialise the ideas related to this project. |
First Year Of Impact | 2020 |
Sector | Digital/Communication/Information Technologies (including Software) |
Impact Types | Economic |
Description | ACM WSDM 2018 Workshop Learn-IR: Learning from User Interactions |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
URL | https://task-ir.github.io/wsdm2018-learnIR-workshop/ |
Description | Dagstuhl Seminar on Conversational Search |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Implementation circular/rapid advice/letter to e.g. Ministry of Health |
Impact | The event was attended by some of the top researchers working on conversational search. At the end of the event a report describing the challenges in the area of conversational search was created. The event was also useful in creating definitions for what conversational search is and what the associated components of a conversational search system is. |
URL | https://www.dagstuhl.de/en/program/calendar/semhp/?semnr=19461 |
Description | Lecture at the ACM SIGIR/SIGKDD Africa Summer School on Machine Learning for Data Mining and Search |
Geographic Reach | Africa |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | I gave a lecture at the ACM SIGIR/SIGKDD Africa Summer School on Machine Learning for Data Mining and Search. The lecture was attended by graduate students and faculty members from all around South Africa. It was particularly aimed at training people and introduce them to do research in this area. We also had a lab session so they were able to get information about the practicalities of the subject. |
URL | http://sigir.org/afirm2020/ |
Description | Organised the ACM WSDM 2020 Workshop on State Based User Modelling |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | I organised a workshop on State Based User Modelling, where we had several invited talks related to the field. The workshop was registered by more than 50 people and involved detail discussions about various applications of state based user modelling and associated research challenges. |
URL | https://www.k4all.org/event/wsdmsum20/ |
Description | THE 3RD STRATEGIC WORKSHOP ON INFORMATION RETRIEVAL IN LORNE (SWIRL) |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Implementation circular/rapid advice/letter to e.g. Ministry of Health |
URL | https://sites.google.com/view/swirl3/home |
Description | Web Conference 2018: Tutorial on Understanding & Inferring User Tasks and Needs |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Gave a tutorial on understanding and inferring user tasks and needs at one of the top conferences in the field (The Web Conference). Through this, many PhD students and industrial practitioners were able to learn about some of the state of the art techniques used for this purpose. |
URL | https://www2018.thewebconf.org/program/tutorials-track/tutorial-222/ |
Description | Workshop Organisation |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Education of the attendees regarding approaches and latest research on proactive information retrieval. |
URL | https://pasircikm2022.github.io/PASIRCIKM/ |
Description | Bloomberg Data Science Research Grant |
Amount | $60,000 (USD) |
Organisation | Bloomberg |
Sector | Private |
Country | United States |
Start | 10/2018 |
End | 10/2019 |
Description | Workshop on Action, Task and User Journey Modeling Unrestricted Gift |
Amount | $20,000 (USD) |
Organisation | |
Sector | Private |
Country | United States |
Start | 11/2022 |
Title | User Model for Task Based Evaluation |
Description | To satisfy their information needs, users usually carry out searches on retrieval systems by continuously trading off between the examination of search results retrieved by under-specified queries and the refinement of these queries through reformulation. In Information Retrieval (IR), a series of query reformulations is known as a query-session. Research in IR evaluation has traditionally been focused on development of measures for the ad-hoc task, for which a retrieval system aims to retrieve the best documents for a single query. Thus, most IR evaluation measures, with a few exceptions, are not suitable to evaluate retrieval scenarios that call for multiple refinements over a query-session. In this paper, by formally modelling a user's expected behaviour over query-sessions, we derive a session-based evaluation measure, which results in a generalisation of the evaluation measure Rank Biased Precision (RBP). We demonstrate the quality of this new session-based evaluation measure, named Session RBP (sRBP), by evaluating its user model against the observed user behaviour over the query-sessions of the 2014 TREC Session track. |
Type Of Material | Technology assay or reagent |
Year Produced | 2019 |
Provided To Others? | No |
Impact | The work is currently under submission to the SIGIR 2019 conference. Once published, the proposed model could be used by the information retrieval community to measure the quality of a search system or intelligent assistant in terms of its help for providing task assistance to the users. |
Title | Task2KB: A public task-oriented knowledge base |
Description | Search engines and conversational assistants are commonly used to help users complete their every day tasks such as booking travel, cooking, etc. While there are some existing datasets that can be used for this purpose, their coverage is limited to very few domains. In this paper, we propose a novel knowledge base, 'Task2KB', which is constructed using data crawled from WikiHow, an online knowledge resource offering instructional articles on a wide range of tasks. Task2KB encapsulates various types of task-related information and attributes, such as requirements, detailed step description, and available methods to complete tasks. Due to its higher coverage compared to existing related knowledge graphs, Task2KB can be highly useful in the development of general purpose task completion assistants |
Type Of Material | Database/Collection of data |
Year Produced | 2023 |
Provided To Others? | Yes |
Impact | Enabling research community to develop task oriented conversational systems and search engines by using the task representations available in the knowledge graph. |
URL | https://www.task2kb.uk/ |
Description | Offline Metrics for Conversation Satisfaction |
Organisation | Spotify |
Country | Sweden |
Sector | Private |
PI Contribution | We have developed a metric that can be used to predict user satisfaction in context of a multi-turn conversation. |
Collaborator Contribution | Ben Carterette from Spotify is an expert on devising evaluation metrics. We have been working with him for developing evaluation metrics to predict user satisfaction. |
Impact | How Am I Doing?: Evaluating Conversational Search Systems Offline. Aldo Lipani, Ben Carterette and Emine Yilmaz. Accepted to appear in ACM Transations on Information Systems (TOIS) 2021. Aldo Lipani, Ben Carterette, Emine Yilmaz: From a User Model for Query Sessions to Session Rank Biased Precision (sRBP). ICTIR 2019: 109-116. |
Start Year | 2019 |
Description | Task Attribute Information Identification |
Organisation | Bloomberg |
Country | United States |
Sector | Private |
PI Contribution | We have been having a close collaboration for several years now. This collaboration have led to several publications, some of which are to appear this year. |
Collaborator Contribution | Edgar Meij (Bloomberg) is an expert in knowledge graphs. This project involves identifying attributes relevant to a question automatically in a task based conversational system, for which we have utilised external knowledge graphs. Jeff Dalton (Glasgow) has been working on conversational systems and contributed their expertise on that. |
Impact | This collaboration has led to several publications: * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: CrossBERT: A Triplet Neural Architecture for Ranking Entity Properties. SIGIR 2020: 2049-2052. * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation. EMNLP (Findings) 2021: 1674-1683 * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: Similarity-based Multi-Domain Dialogue State Tracking with Copy Mechanisms for Task-based Virtual Personal Assistants. The Web Conference 2022. To Appear. |
Start Year | 2019 |
Description | Task Attribute Information Identification |
Organisation | University of Glasgow |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We have been having a close collaboration for several years now. This collaboration have led to several publications, some of which are to appear this year. |
Collaborator Contribution | Edgar Meij (Bloomberg) is an expert in knowledge graphs. This project involves identifying attributes relevant to a question automatically in a task based conversational system, for which we have utilised external knowledge graphs. Jeff Dalton (Glasgow) has been working on conversational systems and contributed their expertise on that. |
Impact | This collaboration has led to several publications: * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: CrossBERT: A Triplet Neural Architecture for Ranking Entity Properties. SIGIR 2020: 2049-2052. * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation. EMNLP (Findings) 2021: 1674-1683 * Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz: Similarity-based Multi-Domain Dialogue State Tracking with Copy Mechanisms for Task-based Virtual Personal Assistants. The Web Conference 2022. To Appear. |
Start Year | 2019 |
Company Name | USERCONTEXT.AI LIMITED |
Description | Commercialise the methods developed as part of the Task Based Information Retrieval project. Currently inactive as one of the co-founders moved to the industry. |
Year Established | 2017 |
Impact | Currently not active. |
Website | http://usercontext.ai/ |
Company Name | HUMANLOOP LTD |
Description | Humanloop aims at building models in which AI and humans can work together. Currently focuses on proving tools for fine tuning large language models. |
Year Established | 2020 |
Impact | Selected in Y combinator, funded by UCL Technology Fund (seed funding), and Index Ventures. |
Website | https://humanloop.com/ |
Description | Dagstuhl Event on Conversational Search |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | I attended a Dagstuhl event on Conversational Search and was involved in defining the research challenges in devising conversational systems. |
Year(s) Of Engagement Activity | 2019 |
URL | https://www.dagstuhl.de/en/program/calendar/semhp/?semnr=19461 |
Description | Gave a tutorial on Deep Learning; aiming at training students/academic industrial practitioners from Africa |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Postgraduate students |
Results and Impact | More than 50 students/academics/industrial practitioners learned about deep learning and got further training via a lab session. |
Year(s) Of Engagement Activity | 2019 |
URL | http://sigir.org/afirm2019/ |
Description | ITU ACM Women in Engineering Invited Speaker |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Undergraduate students |
Results and Impact | Gave a talk at the ACM Women on Engineering event about challenges on being a women in a male dominated environment, giving advice and motivation to the students. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.youtube.com/watch?v=_s1-T8yfnu8&ab_channel=ITUACMStudentChapter |
Description | Invited Talk at Georgetown University |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Invited talk on Research Challenges in Devising the Next Generation Information Retrieval and Access Systems. |
Year(s) Of Engagement Activity | 2021 |
Description | Invited Talk at the London Hopper Colloqium |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | Invited talk titled "New Ways of Thinking about Search with New Devices" at the London Hopper Colloqium, October 2020, which is aiming at encouraging participation of women in science. |
Year(s) Of Engagement Activity | 2020 |
URL | https://www.bcs.org/events/2020/october/webinar-london-hopper-colloquium-2020-1/ |
Description | Invited Talk at the Umass CIIR Talk Series |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Gave a talk at the well-known Umass talk series. The talk series are well-known and are followed by many people outside of the university. The talk was also broadcast via Youtube. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.youtube.com/watch?v=nLlKEVhfa30&t=811s |
Description | Invited talk at the Supporting and Understanding of Conversational Dialogue |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | Invited talk and panel discussion at a workshop on conversational systems, during which I have shared my perspective on task based information retrieval. |
Year(s) Of Engagement Activity | 2021 |
URL | https://wsdm-sud.github.io/sud/index.html |
Description | Keynote Talk |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Keynote talk at the ICTIR Conference attended by some of the well known researchers. |
Year(s) Of Engagement Activity | 2022 |
URL | https://www.ictir2022.org/program/keynote-speakers |
Description | Keynote Talk |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | Keynote talk at UKRI CDT in Speech and Language Technologies and their Applications, University of Sheffield |
Year(s) Of Engagement Activity | 2022 |
URL | https://slt-cdt.sheffield.ac.uk/conference-2022/keynotes |
Description | Keynote Talk |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Keynote talk at the 42nd SGAI International Conference on Artificial Intelligence, December 2022 organised by the British Computing Society. The conference was attended by various researchers from the industry and academia. |
Year(s) Of Engagement Activity | 2022 |
URL | http://bcs-sgai.org/ai2022/?section=appstream_invited |
Description | Keynote Talk at the SIGIR 2021 Workshop on E-commerce |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Industry/Business |
Results and Impact | Gave a keynote talk at the SIGIR 2021 Workshop on Ecommerce. |
Year(s) Of Engagement Activity | 2021 |
URL | https://sigir-ecom.github.io/ |
Description | Keynote Talk at the Science and Information Conference |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Industry/Business |
Results and Impact | Gave one of the keynote talks at the Science and Information Conference. The participants consisted of researchers from the industry and academia. The topic was quite broad, hence the talks covered different areas of AI. The participants also had very different backgrounds, hence the questions and discussions were quite broad (which has led to a change in perspectives). |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.youtube.com/watch?v=RLsWpoo5xog&t=2319s |
Description | Keynote talk at the EMNLP 2019 Workshop on Fact Extraction and Verification |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | I gave a keynote talk titled "Fact Checking Using Stance Detection and User Replies" at the EMNLP 2019 Workshop on Fact Extraction and Verification |
Year(s) Of Engagement Activity | 2020 |
URL | https://fever.ai/2019/workshop.html |
Description | Panel Member at WSDM 2020 Workshop on Conversational Systems for E-Commerce Recommendations and Search |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Took part in a panel discussion about the open problems in conversational search. |
Year(s) Of Engagement Activity | 2020 |
URL | https://wsdm-converse.github.io/ |
Description | Panel Member on the Cutting Edge Stage: AI Your Smart Co-Worker |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Industry/Business |
Results and Impact | The event has been attended by many businesses and start-ups; hence, we were able to reach a broad audience, giving a perspective as to how AI and humans could work together in the workplace in the future. |
Year(s) Of Engagement Activity | 2020 |
URL | https://www.ucl.ac.uk/ai-centre/cogx-events-2020 |
Description | Panel on Artificial Intelligence for the Common Good |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Undergraduate students |
Results and Impact | Panel member at the "Stronger Together | Artificial Intelligence for the Common Good" event organised by the British Council and UNESCO. |
Year(s) Of Engagement Activity | 2023 |
Description | Panelist for An Event in Women in Science and Technology |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | Panel on Celebrating Women in Science and Technology organised by London School of Economics |
Year(s) Of Engagement Activity | 2023 |
URL | https://www.lse.ac.uk/contemporary-turkish-studies/forthcoming-events/2022-23/turkish-week/202303091... |
Description | Talk at Amazon Research Days 2018 |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Graduate students, industrial practitioners and researchers attended the talk and learned about the research we have been doing on task understanding. |
Year(s) Of Engagement Activity | 2018 |
URL | https://ard.amazon-ml.com/cambridge/ |
Description | Talk at Amazon Research Days Edinburgh |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | I gave an invited talk titled "Research Challenges in Devising Next Generation Information Access Systems". |
Year(s) Of Engagement Activity | 2019 |
Description | Talk at Bloomberg |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Industry/Business |
Results and Impact | Researchers and engineers from Bloomberg learned about the research we have been doing on task understanding. |
Year(s) Of Engagement Activity | 2018 |
Description | Talk at Google Conversational Search & Recommendation Workshop |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Industry/Business |
Results and Impact | I attended an invitation only workshop at Google and gave a talk in front of some of the top researchers in the area of conversational systems and recommendation. |
Year(s) Of Engagement Activity | 2019 |
URL | https://sites.google.com/view/csr-workshop2019/home |
Description | Talk at WSDM Workshop on State Based User Modelling |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Incorporating User State in Task Based Information Retrieval and Recommendation of Educational Resources |
Year(s) Of Engagement Activity | 2020 |
URL | https://www.k4all.org/event/wsdmsum20/ |