Concept Extraction Using Pointer-Generator Networks

Abstract

Concept extraction is crucial for a number of downstream applications. However, surprisingly enough, straightforward single token/nominal chunk-concept alignment or dictionary lookup techniques such as DBpedia Spotlight still prevail. We propose a generic opendomain OOV-oriented extractive model that is based on distant supervision of a pointer-generator network leveraging bidirectional LSTMs and a copy mechanism. The model has been trained on a large annotated corpus compiled specifically for this task from 250K Wikipedia pages, and tested on regular pages, where the pointers to other pages are considered as ground truth concepts. The outcome of the experiments shows that our model significantly outperforms standard techniques and, when used on top of DBpedia Spotlight, further improves its performance. The experiments furthermore show that the model can be readily ported to other datasets on which it equally achieves a state-of-the-art performance.

Large-Scale Multi-granular Concept Extraction Based on Machine Reading Comprehension

“…In this paper, we only focus on extracting the concepts already existing in the texts rather than concept generation. Hence we pay attention to extraction models rather than generative models [2,34]. The existing CE methods can be divided into three categories.…”

“…Most of the existing concept acquisition approaches are based on generation or extraction from texts. Generation methods often generate coarse-grained concepts from free texts since they are inclined to generate high-frequency words [2,34]. Extraction methods mainly have three types of models.…”