2015
DOI: 10.1007/978-3-319-18117-2_36
|View full text |Cite
|
Sign up to set email alerts
|

Information Extraction with Active Learning: A Case Study in Legal Text

Abstract: Abstract. Active learning has been successfully applied to a number of NLP tasks. In this paper, we present a study on Information Extraction for natural language licenses that need to be translated to RDF. The final purpose of our work is to automatically extract from a natural language document specifying a certain license a machine-readable description of the terms of use and reuse identified in such license. This task presents some peculiarities that make it specially interesting to study: highly repetitiv… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2016
2016
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 11 publications
0
3
0
Order By: Relevance
“…Active learning is particularly useful when the unlabeled data samples are abundant, whereas manually labelling all of them is expensive or infeasible. Active learning is widely used in many areas, such as text classification [18], information extraction [9], image classification [21], and speech recognition [30].…”
Section: Active Learningmentioning
confidence: 99%
“…Active learning is particularly useful when the unlabeled data samples are abundant, whereas manually labelling all of them is expensive or infeasible. Active learning is widely used in many areas, such as text classification [18], information extraction [9], image classification [21], and speech recognition [30].…”
Section: Active Learningmentioning
confidence: 99%
“…Active learning has also been used in information extraction (Culotta, Kristjansson, McCallum, & Viola, 2006;Finn & Kushmerick, 2003;Jones, Ghani, Mitchell, & Riloff, 2003;Scheffer, Decomain, & Wrobel, 2001) and word sense disambiguation (Chan & Ng, 2007;Chen, Schein, Ungar, & Palmer, 2006;Zhu & Hovy, 2007;Zhu, Wang, & Hovy, 2008). Olsson tified as most beneficial for the classification algorithm-for example, see Cardellino et al (2015) and Holzinger (2016) for further discussion on machine learning with oracle-in-the-loop or human in-the-loop. An important characteristic of active learning in text categorization is that it can reduce the human effort in text labelling by developing effective querying strategies.…”
Section: Active Learningmentioning
confidence: 99%
“…If there is an approach to automatically extract key events from the materials of cases accurately, both labor and time costs would be reduced. It would also benefit further works if we store both the structured information and original materials in the database (Cardellino et al, 2015; Hao et al, 1996).…”
Section: Introductionmentioning
confidence: 99%