Nutribullets Hybrid: Multi-document Health Summarization
This addresses the challenge of summarizing inconsistent health information for users, though it is incremental as it adapts existing concept-to-text methods to a specific domain.
The paper tackles the problem of generating comparative health summaries from multiple documents despite limited parallel training data, introducing a hybrid approach that achieves more faithful and relevant summarization while maintaining fluency comparable to conventional methods.
We present a method for generating comparative summaries that highlights similarities and contradictions in input documents. The key challenge in creating such summaries is the lack of large parallel training data required for training typical summarization systems. To this end, we introduce a hybrid generation approach inspired by traditional concept-to-text systems. To enable accurate comparison between different sources, the model first learns to extract pertinent relations from input documents. The content planning component uses deterministic operators to aggregate these relations after identifying a subset for inclusion into a summary. The surface realization component lexicalizes this information using a text-infilling language model. By separately modeling content selection and realization, we can effectively train them with limited annotations. We implemented and tested the model in the domain of nutrition and health -- rife with inconsistencies. Compared to conventional methods, our framework leads to more faithful, relevant and aggregation-sensitive summarization -- while being equally fluent.