Automatic Open Wikidata Information Extraction from Indonesian Text

Author:

Doxolodeo Kerenza1

Affiliation:

1. University of Indonesia

Abstract

Abstract

Open Information Extraction can be used to aid NLP pipeline, especially if it is linked to a knowledge graph. This is the first attempt to perform OIE in Indonesian text by leveraging pre-existing massive knowledge graph such as Wikidata. The model were given "easier" dataset sample to classify and "harder" dataset sample to classify based on its predicate's RDFS label. It achieves 70.14% F1 on the easier one and 46.68% F1 on the harder one. We also experimented with a pipeline that extracts triple "from the open", but the model struggles with triple that conveys relationship with two geographical place.

Publisher

Research Square Platform LLC

Reference12 articles.

1. Rosyiq, Ahmad and Hayah, Aina Rahmah and Hidayanto, Achmad Nizar and Naisuty, Meisuchi and Suhanto, Agus and Budi, Nur Fitriah Avuning (2019) Information extraction from Twitter using DBpedia ontology: Indonesia tourism places. IEEE, 91--96, 2019 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

2. Li, Xiaoli and Liu, Bing (2003) Learning to classify texts using positive and unlabeled data. Citeseer, 587--592, 2003, 3, IJCAI

3. Ghosh, Iman. Ranked: The 100 most spoken languages around the world. Feb, 2020, Iman Ghosh, Visual Capitalist, https://www.visualcapitalist.com/100-most-spoken-languages/

4. Wang, Chenguang and Liu, Xiao and Chen, Zui and Hong, Haoyun and Tang, Jie and Song, Dawn (2021) Zero-Shot Information Extraction as a Unified Text-to-Triple Translation. 1225--1238, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

5. Suan Lim, Ee and Qi Leong, Wei and Thanh Nguyen, Ngan and Adhista, Dea and Ming Kng, Wei and Chandra Tjh, William and Purwarianti, Ayu (2023) {ICON}: Building a Large-Scale Benchmark Constituency Treebank for the {I}ndonesian Language. Association for Computational Linguistics, Washington, D.C., Constituency parsing is an important task of informing how words are combined to form sentences. While constituency parsing in English has seen significant progress in the last few years, tools for constituency parsing in Indonesian remain few and far between. In this work, we publish ICON (Indonesian CONstituency treebank), the hitherto largest publicly-available manually-annotated benchmark constituency treebank for the Indonesian language with a size of 10,000 sentences and approximately 124,000 constituents and 182,000 tokens, which can support the training of state-of-the-art transformer-based models. We establish strong baselines on the ICON dataset using the Berkeley Neural Parser with transformer-based pre-trained embeddings, with the best performance of 88.85{%} F1 score coming from our own version of SpanBERT (IndoSpanBERT). We further analyze the predictions made by our best-performing model to reveal certain idiosyncrasies in the Indonesian language that pose challenges for constituency parsing., 37--53, https://aclanthology.org/2023.tlt-1.5, March, Proceedings of the 21st International Workshop on Treebanks and Linguistic Theories (TLT, GURT/SyntaxFest 2023), Dakota, Daniel and Evang, Kilian and K{\"u}bler, Sandra and Levin, Lori

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3