Nutri-bullets Hybrid: Consensual Multi-document Summarization
We present a method for generating comparative summaries that highlight 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Document SummarizationLanguage ModelingLanguage ModellingMulti-Document SummarizationNutritionText InfillingSimilar Papers 제목 키워드 기반
Nutri-bullets: Summarizing Health Studies by Composing Segments
We introduce \emph{Nutri-bullets}, a multi-document summarization task for health and nutrition. First, we present two datasets of food and health summaries from multiple scientific studies. Furthermore, we propose a nov…
Document SummarizationLanguage ModelingLanguage ModellingMulti-Document Summarization+1Nutribullets Hybrid: Multi-document Health Summarization
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 requir…
Language ModelingLanguage ModellingNutritionText InfillingSmartBullets: A Cloud-Assisted Bullet Screen Filter based on Deep Learning
Bullet-screen is a technique that enables the website users to send real-time comment `bullet' cross the screen. Compared with the traditional review of a video, bullet-screen provides new features of feeling expression …
Ranking sentences from product description & bullets for better search
Products in an ecommerce catalog contain information-rich fields like description and bullets that can be useful to extract entities (attributes) using NER based systems. However, these fields are often verbose and conta…
Extractive SummarizationNERreinforcement-learningReinforcement Learning+2Semantic Nutrition Estimation: Predicting Food Healthfulness from Text Descriptions
Accurate nutritional assessment is critical for public health, but existing profiling systems require detailed data often unavailable or inaccessible from colloquial text descriptions of food. This paper presents a machi…