Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances

09/06/2019
by   Marco Maggini, et al.
0

We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that are mentioned in the text portion that is currently being read. The agent is expected to learn to follow the narrations, thus disambiguating mentions and discovering new individuals. We focus on the case in which individuals are entities and relations, and we propose an end-to-end trainable memory network that learns to discover and disambiguate them in an online manner, performing one-shot learning, and dealing with a small number of sparse supervisions. Our system builds a not-given-in-advance knowledge base, and it improves its skills while reading unsupervised text. The model deals with abrupt changes in the narration, taking into account their effects when resolving co-references. We showcase the strong disambiguation and discovery skills of our model on a corpus of Wikipedia documents and on a newly introduced dataset, that we make publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/19/2019

Relation Discovery with Out-of-Relation Knowledge Base as Supervision

Unsupervised relation discovery aims to discover new relations from a gi...
research
05/06/2017

Learning Distributed Representations of Texts and Entities from Knowledge Base

We describe a neural network model that jointly learns distributed repre...
research
07/05/2021

Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution

We consider a joint information extraction (IE) model, solving named ent...
research
06/23/2020

ELSIM: End-to-end learning of reusable skills through intrinsic motivation

Taking inspiration from developmental learning, we present a novel reinf...
research
05/13/2021

Predicting Text Readability from Scrolling Interactions

Judging the readability of text has many important applications, for ins...
research
06/21/2023

Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking

Entity Linking (EL) is a fundamental task for Information Extraction and...
research
04/21/2021

AdaptiFont: Increasing Individuals' Reading Speed with a Generative Font Model and Bayesian Optimization

Digital text has become one of the primary ways of exchanging knowledge,...

Please sign up or login with your details

Forgot password? Click here to reset