Pith. sign in

REVIEW

Active Learning for Event Extraction with Memory-based Loss Prediction Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.03073 v3 pith:QKJTPYJR submitted 2021-11-26 cs.CL cs.AI

Active Learning for Event Extraction with Memory-based Loss Prediction Model

classification cs.CL cs.AI
keywords sampleannotationeventcostdomainexistingextractionlearning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Event extraction (EE) plays an important role in many industrial application scenarios, and high-quality EE methods require a large amount of manual annotation data to train supervised learning models. However, the cost of obtaining annotation data is very high, especially for annotation of domain events, which requires the participation of experts from corresponding domain. So we introduce active learning (AL) technology to reduce the cost of event annotation. But the existing AL methods have two main problems, which make them not well used for event extraction. Firstly, the existing pool-based selection strategies have limitations in terms of computational cost and sample validity. Secondly, the existing evaluation of sample importance lacks the use of local sample information. In this paper, we present a novel deep AL method for EE. We propose a batch-based selection strategy and a Memory-Based Loss Prediction model (MBLP) to select unlabeled samples efficiently. During the selection process, we use an internal-external sample loss ranking method to evaluate the sample importance by using local information. Finally, we propose a delayed training strategy to train the MBLP model. Extensive experiments are performed on three domain datasets, and our method outperforms other state-of-the-art methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.