Teach me to explain: A review of datasets for explainable natural language processing
S Wiegreffe, A Marasović - arXiv preprint arXiv:2102.12060, 2021 - arxiv.org
Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual
explanations. These explanations are used downstream in three ways: as data …
explanations. These explanations are used downstream in three ways: as data …
[HTML][HTML] Data extraction methods for systematic review (semi) automation: Update of a living systematic review
L Schmidt, ANF Mutlu, R Elmore, BK Olorisade… - …, 2021 - ncbi.nlm.nih.gov
Background: The reliable and usable (semi) automation of data extraction can support the
field of systematic review by reducing the workload required to gather information about the …
field of systematic review by reducing the workload required to gather information about the …
Prompt engineering for healthcare: Methodologies and applications
Prompt engineering is a critical technique in the field of natural language processing that
involves designing and optimizing the prompts used to input information into models, aiming …
involves designing and optimizing the prompts used to input information into models, aiming …
Fact or fiction: Verifying scientific claims
We introduce scientific claim verification, a new task to select abstracts from the research
literature containing evidence that SUPPORTS or REFUTES a given scientific claim, and to …
literature containing evidence that SUPPORTS or REFUTES a given scientific claim, and to …
Ms2: Multi-document summarization of medical studies
To assess the effectiveness of any medical intervention, researchers must conduct a time-
intensive and highly manual literature review. NLP systems can help to automate or assist in …
intensive and highly manual literature review. NLP systems can help to automate or assist in …
SemEval-2024 task 2: Safe biomedical natural language inference for clinical trials
Large Language Models (LLMs) are at the forefront of NLP achievements but fall short in
dealing with shortcut learning, factual inconsistency, and vulnerability to adversarial inputs …
dealing with shortcut learning, factual inconsistency, and vulnerability to adversarial inputs …
Semeval-2023 task 7: Multi-evidence natural language inference for clinical trial data
M Jullien, M Valentino, H Frost, P O'Regan… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper describes the results of SemEval 2023 task 7--Multi-Evidence Natural Language
Inference for Clinical Trial Data (NLI4CT)--consisting of 2 tasks, a Natural Language …
Inference for Clinical Trial Data (NLI4CT)--consisting of 2 tasks, a Natural Language …
MultiVerS: Improving scientific claim verification with weak supervision and full-document context
The scientific claim verification task requires an NLP system to label scientific documents
which Support or Refute an input claim, and to select evidentiary sentences (or rationales) …
which Support or Refute an input claim, and to select evidentiary sentences (or rationales) …
[HTML][HTML] Generating (factual?) narrative summaries of rcts: Experiments with neural multi-document summarization
BC Wallace, S Saha, F Soboczenski… - AMIA Summits on …, 2021 - ncbi.nlm.nih.gov
We consider the problem of automatically generating a narrative biomedical evidence
summary from multiple trial reports. We evaluate modern neural models for abstractive …
summary from multiple trial reports. We evaluate modern neural models for abstractive …
A zero-shot and few-shot study of instruction-finetuned large language models applied to clinical and biomedical tasks
We evaluate four state-of-the-art instruction-tuned large language models (LLMs)--ChatGPT,
Flan-T5 UL2, Tk-Instruct, and Alpaca--on a set of 13 real-world clinical and biomedical …
Flan-T5 UL2, Tk-Instruct, and Alpaca--on a set of 13 real-world clinical and biomedical …