Elamur Research⌕
☰
home / papers / 2024 / Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction

Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction

Paper · 2024 · Mohan Raj Chanthran, Lay-Ki Soon, Huey Fang Ong et al.

Summary

Malaysian English (ME) is a local variety of English shaped by Malay, Chinese and Tamil. It contains borrowed words, mixed-language compounds and locally derived forms that confuse NER systems trained on Standard English. The authors first tested spaCy, Flair, Stanza and Malaya, all using OntoNotes 5.0-trained models, on 30 hand-labelled ME sentences. Every tool scored below 0.6 micro F1, and all of them struggled most with LOC, GPE and EVENT. In response, the authors scraped 14,320 articles (the MEN-Corpus) from New Straits Times, Malay Mail and Bernama English. They chose a representative sample of 200 articles, which four trained annotators labelled for entities, including nested ones, and for relations. Agreement was measured with IAA, and a subject-matter expert settled disagreements. The final MEN-Dataset holds 6,061 entities and 3,268 relation instances, and it is released together with its guideline. Fine-tuning spaCy on this data improved entity recognition on ME text. This shows that a small, variety-specific resource can close gaps that large Standard English corpora leave open.

Key points

  • The baseline probe on 30 ME sentences gave these micro F1 scores: spaCy 0.58 (best), Flair 0.55, Malaya 0.55 and Stanza 0.43.
  • The MEN-Corpus contains 14,320 articles across the Nation, Business and Sports sections. NST contributed 6,877 of them, Bernama 5,354 and Malay Mail 2,089.
  • The MEN-Dataset has 200 articles, 6,061 entities and 3,268 relations. About 60% of the PERSON, ORGANIZATION, ROLE, TITLE and FACILITY mentions are strongly Malaysia-specific.
  • The relation inventory has 101 labels, drawn from DocRED (only 50 of its 84 adopted labels actually appear) and from ACE-2005, plus a catch-all "Others" label.
  • The paper compares the fine-tuned spaCy models spacy-trf and spacy-blank. The data and guideline are available at github.com/mohanraj-nlp/MEN-Dataset.

Interesting ideas

  • I1. Before building a resource, run a quick probe of several off-the-shelf tools on a few dozen hand-labelled sentences, and break errors down by category to show where they fail.
  • I2. The authors sort variety-specific vocabulary into loan words, compound blends and derived words, such as "datukship", "Johorean" and "non-halal", where English affixes attach to foreign stems.
  • I3. Each relation label comes with allowed head and tail entity types, for example Org-Aff.Employment linking PER to ORG or LOC, and an explicit "Others" label catches pairs that fit no defined relation.
  • I4. Entities are annotated as nested spans, as in "Sekolah Kebangsaan (SK) Parit Penghulu relief centre", where a named school sits inside a larger facility name.
  • I5. Annotator disagreements are measured with IAA and then resolved by an expert adjudicator, rather than by majority vote.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): A cheap per-category probe on a new text genre or English variety would show which pipeline stages degrade before any silver data is generated.
  • I2 (tokens): The morphology and lemma components in crate en could recognise English derivational affixes on unknown or foreign stems, giving an explainable lemma plus affix rather than an opaque out-of-vocabulary token.
  • I3 (world): Type signatures on knowledge-graph relations can reject impossible links in the text world, and an explicit fallback relation keeps unknown links visible instead of silently dropping them.
  • I4 (world): The entity layer could store a nested mention as a part-of or located-in pair of entities, so that questions about either the outer facility or the inner school can be answered.
  • I5 (learn): When the witness parsers disagree on silver data, the disputed items could go to a higher LLM teacher tier acting as adjudicator, while the agreement rate is logged as a quality metric.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Monash University MalaysiaSubang Jaya · Malaysia4 works · 10 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksBiochemistry, Genetics and Molecular Biology · 234 worksMolecular Biology · 231 works

🧭 Topics 3Research subjects and languages the work is about.English · 2,263 worksInformation extraction · 167 worksNamed entity recognition · 200 works

Cite

Cite as Mohan Raj Chanthran, Lay-Ki Soon, Huey Fang Ong and Bhawani Selvaretnam. 2024. Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{chanthran2024malaysian,
  title = {{Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction}},
  author = {Mohan Raj Chanthran, Lay-Ki Soon, Huey Fang Ong and Bhawani Selvaretnam},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  year = {2024},
  url = {https://aclanthology.org/2024.lrec-main.959/}
}

References

37 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gavin Abercrombie, Verena Rieser, and Dirk Hovy. 2023. Consistency is key: Disentangling label variation in natural language processing with intra-annotator agreement. find
  2. David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D’souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jesujoba Alabi, Seid Muhie Yimam, Tajuddeen Gwadabe, Ignatius Ezeani, Rubungo Andre Niyongabo, Jonathan Mukiibi, Verrah Otiende, Iroro Orife, Davis David, Samba Ngom, Tosin Adewumi, Paul Rayson, Mofetoluwa Adeyemi, Gerald Muriuki, Emmanuel Anebi, Chiamaka Chukwuneke, Nkiruka Odu, Eric Peter Wairagala, Samuel Oyerinde, Clemencia Siro, Tobius Saul Bateesa, Temilola Oloyede, Yvonne Wambui, Victor Akinode, Deborah Nabagereka, Maurice Katusiime, Ayodele Awokoya, Mouhamadane MBOUP, Dibora Gebreyohannes, Henok Tilaye, Kelechi Nwaike, Degaga Wolde, Abdoulaye Faye, Blessing Sibanda, Orevaoghene Ahia, Bonaventure F. P. Dossou, Kelechi Ogueji, Thierno Ibrahima DIOP, Abdoulaye Diallo, Adewale Akinfaderin, Tendai Marengereke, and Salomey Osei. 2021. Masakhaner: Named entity recognition for african languages. ↗
  3. Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. Flair: An easy-to-use framework for state-of-the-art nlp. In NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 54–59.
  4. Ron Artstein. 2017. Inter-annotator Agreement, pages 297–313. Springer Netherlands, Dordrecht. find
  5. Lukas Biewald. 2020. Experiment tracking with weights and biases. Software available from wandb.com. find
  6. Alex Brandsen, Suzan Verberne, Milco Wansleeben, and Karsten Lambers. 2020. Creating a dataset for named entity recognition in the archaeology domain. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4573–4577, Marseille, France. European Language Resources Association. ↗
  7. Weerayut Buaphet, Can Udomcharoenchaikit, Peerat Limkonchotiwat, Attapol Rutherford, and Sarana Nutanong. 2022. Thai nested named entity recognition corpus. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1473–1486, Dublin, Ireland. Association for Computational Linguistics. find
  8. Leonardo Campillos-Llanos, Ana Valverde-Mateos, Adrián Capllonch-Carrión, and Antonio Moreno-Sandoval. 2021. A clinical trials corpus annotated with UMLS entities to enhance the access to evidence-based medicine. BMC Med Inform Decis Mak, 21(1):69. ↗
  9. Yee Seng Chan and Dan Roth. 2011. Exploiting syntactico-semantic structures for relation extraction. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 551–560, Portland, Oregon, USA. Association for Computational Linguistics.
  10. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. find
  11. Ralph Grishman and Beth Sundheim. 1996. Message Understanding Conference- 6: A brief history. In COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics.
  12. Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2018. FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4803–4809, Brussels, Belgium. Association for Computational Linguistics. find
  13. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: The 90% solution. In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, NAACL-Short ’06, page 57–60, USA. Association for Computational Linguistics. find
  14. George Hripcsak and Adam Rothschild. 2005. Agreement, the f-measure, and reliability in information retrieval. Journal of the American Medical Informatics Association : JAMIA, 12:296–8. ↗
  15. Zolkepli Husein. 2018. Malaya. https://github.com/huseinzol05/malaya. ↗
  16. Rasmus Hvingelby, Amalie Brogaard Pauli, Maria Barrett, Christina Rosted, Lasse Malm Lidegaard, and Anders Søgaard. 2020. DaNE: A named entity resource for Danish. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4597–4604, Marseille, France. European Language Resources Association. find
  17. T.S. Imm. 2014. Exploring the malaysian english newspaper corpus for lexicographic evidence. 32:167–185. find
  18. Noriah Ismail, Normah Ismail, and Kamalanathan Ramakrishnan. 2007. Malaysian english versus standard english: Which is favored? find
  19. Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P. Lungren, Andrew Y. Ng, Curtis P. Langlotz, and Pranav Rajpurkar. 2021. Radgraph: Extracting clinical entities and relations from radiology reports. ↗
  20. Mustafa Jarrar, Mohammed Khalilia, and Sana Ghanem. 2022. Wojood: Nested arabic named entity corpus and recognition using bert.
  21. Hang Jiang, Yining Hua, Doug Beeferman, and Deb Roy. 2022. Annotating the Tweebank corpus on named entity recognition and building NLP models for social media analysis. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7199–7208, Marseille, France. European Language Resources Association. find
  22. Yi Luan, Luheng He, Mari Ostendorf, and Hannaneh Hajishirzi. 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction.
  23. Shervin Malmasi, Anjie Fang, Besnik Fetahu, Sudipta Kar, and Oleg Rokhlenko. 2022. Multiconer: A large-scale multilingual dataset for complex named entity recognition. ↗
  24. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60, Baltimore, Maryland. Association for Computational Linguistics. Ines Montani, Matthew Honnibal, Matthew Honnibal, Adriane Boyd, Sofie Van Landeghem, Henning Peters, Paul O’Leary McCann, jim geovedi, Jim O’Regan, Maxim Samsonov, Daniël de Kok, György Orosz, Marcus Blättermann, Madeesh Kannan, Duygu Altinok, Raphael Mitsch, Søren Lind Kristiansen, Edward, Lj Miranda, Peter Baumgartner, Raphaël Bournhonesque, Richard Hudson, Explosion Bot, Roman, Leander Fiedler, Ryn Daniels, kadarakos, Wannaphong Phatthiyaphaibun, and Schero1994. 2022. explosion/spaCy: v3.7.1: Bug fix for ‘spacy.cli‘ module loading.
  25. Hiroki Nakayama, Takahiro Kubo, Junya Kamura, Yasufumi Taniguchi, and Xu Liang. 2018. doccano: Text annotation tool for human. Software available from https://github.com/doccano/doccano. ↗
  26. Wuraola Fisayo Oyewusi, Olubayo Adekanmbi, Ifeoma Okoh, Vitus Onuigwe, Mary Idera Salami, Opeyemi Osakuade, Sharon Ibejih, and Usman Abdullahi Musa. 2021. Naijaner : Comprehensive named entity recognition for 5 nigerian languages. ↗
  27. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. ↗
  28. Sunil Kumar Sahu, Fenia Christopoulou, Makoto Miwa, and Sophia Ananiadou. 2019. Inter-sentence relation extraction with document-level graph convolutional neural network. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4309– 4316, Florence, Italy. Association for Computational Linguistics.
  29. Agam Shah, Ruchit Vithani, Abhinav Gullapalli, and Sudheer Chava. 2023. Finer: Financial named entity recognition dataset and weak-supervision model. find
  30. Kumutha Swampillai and Mark Stevenson. 2011. Extracting relations within and across sentences. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 25–32, Hissar, Bulgaria. Association for Computational Linguistics. find
  31. Siew Tan. 2009. Lexical borrowing in malaysian english: Influences of malay. Lexis, 3. ↗
  32. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147. ↗
  33. Christopher Walker. 2005. Multilingual Training Corpus LDC2006T06. Web Download. Philadelphia: Linguistic Data Consortium. find
  34. Difeng Wang, Wei Hu, Ermei Cao, and Weijian Sun. 2020. Global-to-local neural networks for document-level relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3711–3721, Online. Association for Computational Linguistics. find
  35. Yuan Yao, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie Zhou, and Maosong Sun. 2021. CodRED: A cross-document relation extraction dataset for acquiring knowledge in the wild. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4452– 4472, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  36. Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, and Maosong Sun. 2019. DocRED: A large-scale document-level relation extraction dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 764–777, Florence, Italy. Association for Computational Linguistics. ↗
  37. Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, and Christopher D. Manning. 2017. Position-aware attention and supervised data improve slot filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), pages 35–45. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chanthran-2024-malaysian-english-news-decoded-linguistic/