Papers by Jeff Dalton
DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities (2024.emnlp-main)
Copied to clipboard
| Challenge: | Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. |
| Approach: | They propose to enhance the LSR vocabulary with Wikipedia concepts and entities, enabling the model to resolve ambiguities more effectively and stay current with evolving knowledge. |
| Outcome: | The proposed model outperforms state-of-the-art models across three entity-rich document ranking datasets. |
ToolWriter: Question Specific Tool Synthesis for Tabular Data (2023.emnlp-main)
Copied to clipboard
| Challenge: | Tabular question answering (TQA) requires joint reasoning of natural language with large amounts of semi-structured data. |
| Approach: | They propose to use query-specific programs to generate query-based tools to simplify large tables and detect when to apply them to transform tables. |
| Outcome: | The proposed tool improves state-of-the-art on two tabular question-answering datasets. |
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances on neural approaches to natural language processing have triggered a renaissance in end-to-end neural open-domain chatbots. |
| Approach: | They propose to use offline and online steps to evaluate the quality of clarifying questions in various open-domain dialogues to improve the quality and accuracy of the system response. |
| Outcome: | The proposed pipeline is suitable as a foundation for further research. |
Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models rely on a traditional cross-entropy loss function during training, which may not be optimal for improving the joint goal accuracy. |
| Approach: | They propose a Turn-based Loss Function that penalises the model if it inaccurately predicts a slot value at the early turns more so than in later turns to improve joint goal accuracy. |
| Outcome: | The proposed techniques improve the state-of-the-art model by approximately 7-8% relative reduction in error and achieve a new state- of-the art joint goal accuracy with 59.50 and 54.90 on MultiWOZ2.1 and MultiWOz2.2, respectively. |
Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations (2022.aacl-main)
Copied to clipboard
Francesco Dalla Serra, William Clackett, Hamish MacKinnon, Chaoyang Wang, Fani Deligianni, Jeff Dalton, Alison Q. O’Neil
| Challenge: | Existing approaches to generate text radiology reports are prone to errors and poor clinical accuracy. |
| Approach: | They propose a two-step pipeline that subdivides the problem into factual triple extraction followed by free-text report generation. |
| Outcome: | The proposed pipeline shows that the generated reports exhibit realistic style but lack clinical accuracy. |
TAPS: Tool-Augmented Personalisation via Structured Tagging (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to personalise tool use overlook the role of personalisation in guiding tool use. |
| Approach: | They propose a tool-augmented large language model that integrates user preferences into goal-oriented dialogue agents by leveraging a structured tagging tool and an uncertainty-based tool detector. |
| Outcome: | The proposed solution significantly improves the ability of LLMs to incorporate user preferences, achieving the new state-of-the-art for open source models on the NLSI task. |
Controllable Chest X-Ray Report Generation from Longitudinal Representations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Radiology reports are detailed text descriptions of the content of medical scans. |
| Approach: | They propose a method to align, concatenate and fuse the current and prior visual information into a joint longitudinal representation which can be provided to a multimodal report generation model. |
| Outcome: | The proposed method achieves state-of-the-art results while enabling anatomy-wise controllable report generation. |