1 code implementation • 1 Mar 2024 • Sophie Fischer, Federico Rossetto, Carlos Gemmell, Andrew Ramsay, Iain Mackie, Philip Zubel, Niklas Tecklenburg, Jeffrey Dalton
We present the second version of the Open Assistant Toolkit (OAT-v2), an open-source task-oriented conversational system for composing generative neural models.
1 code implementation • 12 Feb 2024 • Sophie Fischer, Carlos Gemmell, Niklas Tecklenburg, Iain Mackie, Federico Rossetto, Jeffrey Dalton
We tackle the challenge of building real-world multimodal assistants for complex real-world tasks.
no code implementations • 9 Oct 2023 • Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni, Jeffrey Dalton, Alison Q O'Neil
Previous approaches to automated radiology reporting generally do not provide the prior study as input, precluding comparison which is required for clinical accuracy in some types of scans, and offer only unreliable methods of interpretability.
no code implementations • 30 Aug 2023 • Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni, Jeffrey Dalton, Alison Q. O'Neil
Automated approaches to radiology reporting require the image to be encoded into a suitable token representation for input to the language model.
no code implementations • 29 Jun 2023 • Iain Mackie, Shubham Chatterjee, Sean MacAvaney, Jeffrey Dalton
First, we demonstrate that applying a strong neural re-ranker before sparse or dense PRF can improve the retrieval effectiveness by 5-8%.
no code implementations • 16 Jun 2023 • Iain Mackie, Ivan Sekulic, Shubham Chatterjee, Jeffrey Dalton, Fabio Crestani
Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion.
no code implementations • 12 May 2023 • 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.
1 code implementation • 26 Apr 2023 • Paul Owoicho, Ivan Sekulić, Mohammad Aliannejadi, Jeffrey Dalton, Fabio Crestani
To this end, we propose a user simulator-based framework for multi-turn interactions with a variety of mixed-initiative CS systems.
no code implementations • 25 Apr 2023 • 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.
no code implementations • 17 Mar 2023 • Carlos Gemmell, Jeffrey Dalton
Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data.
no code implementations • 11 Nov 2022 • Elena Soare, Iain Mackie, Jeffrey Dalton
We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table.
no code implementations • 8 Nov 2022 • Iain Mackie, Jeffrey Dalton
This workshop paper discusses automating the construction of query-specific document and entity knowledge graphs (KGs) for complex research topics.
no code implementations • 31 Aug 2022 • Carlos Gemmell, Iain Mackie, Paul Owoicho, Federico Rossetto, Sophie Fischer, Jeffrey Dalton
GRILLBot is the winning system in the 2022 Alexa Prize TaskBot Challenge, moving towards the next generation of multimodal task assistants.
1 code implementation • 24 Aug 2022 • Mirelle Bueno, Carlos Gemmell, Jeffrey Dalton, Roberto Lotufo, Rodrigo Nogueira
Our experimental results show that generating step-by-step rationales and introducing marker tokens are both required for effective extrapolation.
2 code implementations • 23 Aug 2022 • Sophie Fischer, Carlos Gemmell, Iain Mackie, Jeffrey Dalton
This work addresses challenges in developing conversational assistants that support rich multimodal video interactions to accomplish real-world tasks interactively.
2 code implementations • 9 May 2022 • Iain Mackie, Paul Owoicho, Carlos Gemmell, Sophie Fischer, Sean MacAvaney, Jeffrey Dalton
We also show that the manual query reformulations significantly improve document ranking and entity ranking performance.
1 code implementation • EMNLP 2021 • Mohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin, Jeffrey Dalton, Mikhail Burtsev
Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response.
no code implementations • 9 Mar 2021 • Shahrzad Naseri, Jeffrey Dalton, Andrew Yates, James Allan
We find that CEQE outperforms static embedding-based expansion methods on multiple collections (by up to 18% on Robust and 31% on Deep Learning on average precision) and also improves over proven probabilistic pseudo-relevance feedback (PRF) models.
no code implementations • 6 Jul 2020 • Carlos Gemmell, Federico Rossetto, Jeffrey Dalton
Tools capable of automatic code generation have the potential to augment programmer's capabilities.
1 code implementation • 30 Mar 2020 • Jeffrey Dalton, Chenyan Xiong, Jamie Callan
A common theme through the runs is the use of BERT-based neural reranking methods.