Neural Architectures for Open-Type Relation Argument Extraction
This work addresses the challenge of extracting open-type arguments for entities not covered by standard named entity taggers, which is incremental as it builds on existing relation extraction and question answering methods.
The paper tackles the problem of extracting non-standard entity types, such as book titles, from text given a query entity and a relation, introducing the Open-Type Relation Argument Extraction (ORAE) task and releasing a distantly supervised dataset based on WikiData. It develops neural models that yield large improvements over a strong neural question answering baseline, with a GRU-based encoder and CRF tagger achieving the best results.
In this work, we introduce the task of Open-Type Relation Argument Extraction (ORAE): Given a corpus, a query entity Q and a knowledge base relation (e.g.,"Q authored notable work with title X"), the model has to extract an argument of non-standard entity type (entities that cannot be extracted by a standard named entity tagger, e.g. X: the title of a book or a work of art) from the corpus. A distantly supervised dataset based on WikiData relations is obtained and released to address the task. We develop and compare a wide range of neural models for this task yielding large improvements over a strong baseline obtained with a neural question answering system. The impact of different sentence encoding architectures and answer extraction methods is systematically compared. An encoder based on gated recurrent units combined with a conditional random fields tagger gives the best results.