Log In Sign Up

Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction

by   Kareem Ahmed, et al.

We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Such knowledge takes the form of an ontology defining relations and their permissible arguments. Previous approaches set out to integrate such knowledge in their learning approaches either through self-training, or through approximations that lose the precise meaning of the logical expressions. By contrast, our approach employs semantic loss which captures the precise meaning of a logical sentence through maintaining a probability distribution over all possible states, and guiding the model to solutions which minimize any constraint violations. With a focus on low-data regimes, we show that semantic loss outperforms the baselines by a wide margin.


page 1

page 2

page 3

page 4


End-to-End Relation Extraction using Markov Logic Networks

The task of end-to-end relation extraction consists of two sub-tasks: i)...

Jointly Extracting Relations with Class Ties via Effective Deep Ranking

Connections between relations in relation extraction, which we call clas...

Semantic Loss Application to Entity Relation Recognition

Usually, entity relation recognition systems either use a pipe-lined mod...

Multi-view Inference for Relation Extraction with Uncertain Knowledge

Knowledge graphs (KGs) are widely used to facilitate relation extraction...

A Neural Architecture for Person Ontology population

A person ontology comprising concepts, attributes and relationships of p...

ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select

We study the problem of extracting N-ary relation tuples from scientific...