QA4IE: A Question Answering based Framework for Information Extraction
This work addresses the problem of extracting structured information from unstructured text for applications in natural language processing, offering a novel framework that improves over traditional IE methods, though it is incremental in leveraging QA techniques.
The paper tackles the limitations of existing Information Extraction (IE) systems, such as handling cross-sentence tuples and limited relation types, by proposing QA4IE, a framework that uses question answering approaches to extract high-quality relation triples, achieving great improvements on a new benchmark with 293K documents and 2M triples.
Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are severely restricted by limited relation types as well as informal relation specifications (e.g., free-text based relation tuples). In order to overcome these weaknesses, we propose a novel IE framework named QA4IE, which leverages the flexible question answering (QA) approaches to produce high quality relation triples across sentences. Based on the framework, we develop a large IE benchmark with high quality human evaluation. This benchmark contains 293K documents, 2M golden relation triples, and 636 relation types. We compare our system with some IE baselines on our benchmark and the results show that our system achieves great improvements.