REVIEW 2 cited by
Context-Aware Answer Extraction in Question Answering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text but in a context irrelevant to the given question. This discrepancy becomes especially important as the number of occurrences of the answer text in a passage increases. To resolve this issue, we propose \textbf{BLANC} (\textbf{BL}ock \textbf{A}ttentio\textbf{N} for \textbf{C}ontext prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases. We also conduct an experiment of training the models using SQuAD and predicting the supporting facts on HotpotQA and show that BLANC outperforms all baseline models in this zero-shot setting.
Forward citations
Cited by 2 Pith papers
-
DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering
DragonVerseQA is a 3,200-pair question-answering dataset for House of the Dragon and Game of Thrones episodes, built from summaries, reviews, and wiki data to support long-form narrative QA.
-
AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles
AlzheimerRAG, a PubMed-based multimodal retrieval-augmented generation system, is reported, but its PubMedQA results are in-sample because PubMedQA was used for both fine-tuning and testing.
Discussion (0). Continue with ORCID to comment.