• Publications
  • Influence
Exploring the Role of Conversational Cues in Guided Task Support with Virtual Assistants
TLDR
The role of implicit conversational cues in guided task completion scenarios is explored and a set of design implications for the design of guided task experiences in contemporary conversational assistants are presented.
VERSE: Bridging Screen Readers and Voice Assistants for Enhanced Eyes-Free Web Search
People with visual impairments often rely on screen readers when interacting with computer systems. Increasingly, these individuals also make extensive use of voice-based virtual assistants (VAs). We
Knowledge Graphs versus Hierarchies: An Analysis of User Behaviours and Perspectives in Information Seeking
TLDR
This paper examines two different spatial representations of search results: knowledge graphs and hierarchical trees and shows that knowledge graphs can effectively reduce the need to read source content with no reduction in the quality of the information gathered by the user.
Complex questions : Let me Google it for you
TLDR
This paper focuses on automatically generating training data for automatically determining the combination of terms appearing in the question that best returns the answer, and hopes to learn to extract short queries from long questions that have no existing answers.
Exploring Conversational Search With Humans, Assistants, and Wizards
Chatbots and conversational assistants are becoming increasingly popular. However, for information seeking scenarios, these systems still have very limited conversational abilities, and primarily
Bridging Screen Readers and Voice Assistants for Enhanced Eyes-Free Web Search
People with visual impairments often rely on screen readers when interacting with computer systems. Increasingly, these individuals also make extensive use of voice-based virtual assistants (VAs). We
Offline Evaluation without Gain
TLDR
It is demonstrated that compatibility can replace and extend current offline evaluation measures that depend on fixed relevance grades that must be mapped to gain values, such as NDCG.
Offline Evaluation by Maximum Similarity to an Ideal Ranking
TLDR
This work proposes a radical simplification of NDCG to replace it, and proposes rank biased overlap (RBO) to compute this rank similarity, since it was specifically created to address the requirements of rank similarity between search results.
Assessing top-k preferences
TLDR
The assessment process for partial preference judgments is explored, with the aim of identifying and ordering the top items in the pool, rather than fully ordering the entire pool, by replacing NDCG with a new measure that can reflect factors beyond relevance.
VERSE
...
...