Multi-Granularity Guided Fusion-in-Decoder
This work addresses a key challenge in ODQA for improving answer accuracy by discerning relevant evidence, though it appears incremental as it builds on the Fusion-in-Decoder architecture.
The paper tackles the problem of generating incorrect outputs from plausible contexts in Open-domain Question Answering by proposing Multi-Granularity guided Fusion-in-Decoder (MGFiD), which outperforms existing models on Natural Questions and TriviaQA datasets.
In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results. The model architecture that uses concatenated multiple contexts in the decoding phase, i.e., Fusion-in-Decoder, demonstrates promising performance but generates incorrect outputs from seemingly plausible contexts. To address this problem, we propose the Multi-Granularity guided Fusion-in-Decoder (MGFiD), discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. It aggregates evident sentences into an anchor vector that instructs the decoder. Additionally, it improves decoding efficiency by reusing the results of passage re-ranking for passage pruning. Through our experiments, MGFiD outperforms existing models on the Natural Questions (NQ) and TriviaQA (TQA) datasets, highlighting the benefits of its multi-granularity solution.