Information Propagation by Composited Labels in Natural Language Processing

by   Takeshi Inagaki, et al.

In natural language processing (NLP), labeling on regions of text, such as words, sentences and paragraphs, is a basic task. In this paper, label is defined as map between mention of entity in a region on text and context of entity in a broader region on text containing the mention. This definition naturally introduces linkage of entities induced from inclusion relation of regions, and connected entities form a graph representing information flow defined by map. It also enables calculation of information loss through map using entropy, and entropy lost is regarded as distance between two entities over a path on graph.


page 1

page 2

page 3

page 4


ParsEL 1.0: Unsupervised Entity Linking in Persian Social Media Texts

In recent years, social media data has exponentially increased, which ca...

Entity Extraction with Knowledge from Web Scale Corpora

Entity extraction is an important task in text mining and natural langua...

Un résumeur à base de graphes, indépéndant de la langue

In this paper we present REG, a graph-based approach for study a fundame...

ISA-bEL: Intelligent Search Algorithm based on Entity Linking

Nowadays, the way in which the people interact with computers has change...

Chekhov's Gun Recognition

Chekhov's gun is a dramatic principle stating that every element in a st...

Discovering Power Laws in Entity Length

This paper presents a discovery that the length of the entities follows ...

Extracting and Validating Explanatory Word Archipelagoes using Dual Entropy

The logical connectivity of text is represented by the connectivity of w...