KnowFi: Knowledge Extraction from Long Fictional Texts

Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum

Keywords: relation extraction, long fictional texts, distant supervision, knowledge extraction

TL;DR: This paper presents a method for knowledge extraction from long fictional texts, called KnowFi, that combines BERT-enhanced neural learning with judicious selection and aggregation of text passages.

Abstract:

Knowledge base construction has recently been extended to fictional domains like multi-volume novels and TV/movie series, aiming to support explorative queries for fans and sub-culture studies by humanities researchers. This task involves the extraction of relations between entities. State-of-the-art methods are geared for short input texts and basic relations, but fictional domains require tapping very long texts and need to cope with non-standard relations where distant supervision becomes sparse.
This work addresses these challenges by a novel method, called KnowFi, that combines BERT-enhanced neural learning with judicious selection and aggregation of text passages. Experiments with several fictional domains demonstrate the gains that KnowFi achieves over the best prior methods for neural relation extraction.

Subject Areas: Information Extraction

Archival Status: Archival