Active learning strategies for extracting phrase-level topics from scientific literature

TY - JOUR

T1 - Active learning strategies for extracting phrase-level topics from scientific literature

AU - Yue, Tao

AU - Li, Yu

AU - Runjie, Zhang

N1 - Publisher Copyright: © 2020, Chinese Academy of Sciences. All rights reserved.

PY - 2020

Y1 - 2020

N2 - [Objective] This paper explores methods of extracting information from scientific literature with the help of active learning strategies, aiming to address the issue of lacking annotated corpus. [Methods] We constructed our new model based on three representative active learning strategies (MARGIN, NSE, MNLP) and one novel LWP strategy, as well as the neural network model (namely CNN-BiLSTM-CRF). Then, we extracted the task and method related information from texts with much fewer annotations. [Results] We examined our model with scientific articles with 10%~30% selectively annotated texts. The proposed model yielded the same results as those of models with 100% annotated texts. It significantly reduced the labor costs of corpus construction. [Limitations] The number of scientific articles in our sample corpus was small, which led to low precision issues. [Conclusions] The proposed model significantly reduces its reliance on the scale of annotated corpus. Compared with the existing active learning strategies, the MNLP yielded better results and normalizes the sentence length to improve the model’s stability. In the meantime, MARGIN performs well in the initial iteration to identify the low-value instances, while LWP is suitable for dataset with more semantic labels.

AB - [Objective] This paper explores methods of extracting information from scientific literature with the help of active learning strategies, aiming to address the issue of lacking annotated corpus. [Methods] We constructed our new model based on three representative active learning strategies (MARGIN, NSE, MNLP) and one novel LWP strategy, as well as the neural network model (namely CNN-BiLSTM-CRF). Then, we extracted the task and method related information from texts with much fewer annotations. [Results] We examined our model with scientific articles with 10%~30% selectively annotated texts. The proposed model yielded the same results as those of models with 100% annotated texts. It significantly reduced the labor costs of corpus construction. [Limitations] The number of scientific articles in our sample corpus was small, which led to low precision issues. [Conclusions] The proposed model significantly reduces its reliance on the scale of annotated corpus. Compared with the existing active learning strategies, the MNLP yielded better results and normalizes the sentence length to improve the model’s stability. In the meantime, MARGIN performs well in the initial iteration to identify the low-value instances, while LWP is suitable for dataset with more semantic labels.

KW - Active Learning

KW - Information Extraction

KW - Neural Network

UR - https://www.scopus.com/pages/publications/85101630135

U2 - 10.11925/infotech.2096-3467.2020.0281

DO - 10.11925/infotech.2096-3467.2020.0281

M3 - Article

AN - SCOPUS:85101630135

SN - 2096-3467

VL - 4

SP - 134

EP - 143

JO - Data Analysis and Knowledge Discovery

JF - Data Analysis and Knowledge Discovery

IS - 10

ER -