Pre-trained transformer models, such as BERT and T5, have shown to be highly effective at ad hoc passage and document ranking. Due to the inherent sequence length limits of these …
Y Deng, W Zhang, W Xu, Y Shen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall …
As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term …
Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform …
Considering the widespread use of mobile and voice search, answer passage retrieval for non-factoid questions plays a critical role in modern information retrieval systems. Despite …
D Cohen, L Yang, WB Croft - … ACM SIGIR conference on research & …, 2018 - dl.acm.org
With the rise in mobile and voice search, answer passage retrieval acts as a critical component of an effective information retrieval system for open domain question answering …
Retrieving finer grained text units such as passages or sentences as answers for non-factoid Web queries is becoming increasingly important for applications such as mobile Web …
H Song, Z Ren, S Liang, P Li, J Ma… - Proceedings of the Tenth …, 2017 - dl.acm.org
We aim at summarizing answers in community question-answering (CQA). While most previous work focuses on factoid question-answering, we focus on the non-factoid question …
When asked, large language models~(LLMs) like ChatGPT claim that they can assist with relevance judgments but it is not clear whether automated judgments can reliably be used in …