Text Summarization with Latent Queries
This addresses the need for more flexible summarization systems that can handle specific user queries, representing a novel method for a known bottleneck in the field.
The paper tackles the problem of query-focused summarization, where existing systems often fail to support diverse user intents, by introducing LaQSum, a unified system that learns latent queries from documents for abstractive summarization with any query forms, and it robustly outperforms strong comparison systems across various benchmarks.
The availability of large-scale datasets has driven the development of neural models that create summaries from single documents, for generic purposes. When using a summarization system, users often have specific intents with various language realizations, which, depending on the information need, can range from a single keyword to a long narrative composed of multiple questions. Existing summarization systems, however, often either fail to support or act robustly on this query focused summarization task. We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimizes a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Despite learning from only generic summarization data and requiring no further optimization for downstream summarization tasks, our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.