47 citations · 58 across the 13 of their papers we have counts for
13 papers
Open Assistant Toolkit -- version 2
Sophie Fischer, Federico Rossetto, Carlos Gemmell +5
We present the second version of the Open Assistant Toolkit (OAT-v2), an open-source task-oriented conversational system for composing generative neural models. OAT-v2 is a scalabl…
GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants
Sophie Fischer, Carlos Gemmell, Niklas Tecklenburg +3
We tackle the challenge of building real-world multimodal assistants for complex real-world tasks. We describe the practicalities and challenges of developing and deploying GRILLBo…
DREQ: Document Re-Ranking Using Entity-based Query Understanding
Shubham Chatterjee, Iain Mackie, Jeff Dalton
While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual entities within a document have on…
GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval
Iain Mackie, Ivan Sekulic, Shubham Chatterjee +2
Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs…
Adaptive Latent Entity Expansion for Document Retrieval
Iain Mackie, Shubham Chatterjee, Sean MacAvaney +1
Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall.…
Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval
Iain Mackie, Shubham Chatterjee, Jeffrey Dalton
Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance…
Generative Relevance Feedback with Large Language Models
Iain Mackie, Shubham Chatterjee, Jeffrey Dalton
Current query expansion models use pseudo-relevance feedback to improve first-pass retrieval effectiveness; however, this fails when the initial results are not relevant. Instead o…
DocuT5: Seq2seq SQL Generation with Table Documentation
Elena Soare, Iain Mackie, Jeffrey Dalton
Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans woul…
Query-Specific Knowledge Graphs for Complex Finance Topics
Iain Mackie, Jeffrey Dalton
Across the financial domain, researchers answer complex questions by extensively "searching" for relevant information to generate long-form reports. This workshop paper discusses a…
GRILLBot: An Assistant for Real-World Tasks with Neural Semantic Parsing and Graph-Based Representations
Carlos Gemmell, Iain Mackie, Paul Owoicho +3
GRILLBot is the winning system in the 2022 Alexa Prize TaskBot Challenge, moving towards the next generation of multimodal task assistants. It is a voice assistant to guide users t…
VILT: Video Instructions Linking for Complex Tasks
Sophie Fischer, Carlos Gemmell, Iain Mackie +1
This work addresses challenges in developing conversational assistants that support rich multimodal video interactions to accomplish real-world tasks interactively. We introduce th…
CODEC: Complex Document and Entity Collection
Iain Mackie, Paul Owoicho, Carlos Gemmell +3
CODEC is a document and entity ranking benchmark that focuses on complex research topics. We target essay-style information needs of social science researchers, i.e. "How has the U…
How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset
Iain Mackie, Jeffery Dalton, Andrew Yates
Deep Learning Hard (DL-HARD) is a new annotated dataset designed to more effectively evaluate neural ranking models on complex topics. It builds on TREC Deep Learning (DL) topics b…