Lune

ACL Findings2021

Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation

Peerat Limkonchotiwat, Wannaphong Phatthiyaphaibun, Raheem Sarwar, Ekapol Chuangsuwanich, Sarana Nutanong

Abstract

While word segmentation is a solved problem in many languages, it is still a challenge in continuous-script or low-resource languages. Like other NLP tasks, word segmentation is domain-dependent, which can be a challenge in low-resource languages like Thai and Urdu since there can be domains with insufficient data. This investigation proposes a new solution to adapt an existing domaingeneric model to a target domain, as well as a data augmentation technique to combat the low-resource problems. In addition to domain adaptation, we also propose a framework to handle out-of-domain inputs using an ensemble of domain-specific models called Multi-Domain Ensemble (MDE). To assess the effectiveness of the proposed solutions, we conducted extensive experiments on domain adaptation and out-of-domain scenarios. Moreover, we also proposed a multiple task dataset for Thai text processing, including word segmentation. For domain adaptation, we compared our solution to the state-of-the-art Thai word segmentation (TWS) method and obtained improvements from 93.47% to 98.48% at the character level and 84.03% to 96.75% at the word level. For out-of-domain scenarios, our MDE method significantly outperformed the state-of-the-art TWS and multi-criteria methods. Furthermore, to demonstrate our method's generalizability, we also applied our MDE framework to other languages, namely Chinese, Japanese, and Urdu, and obtained improvements similar to Thai's.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence GenerationKun Li, Chengbo Chen, Xiaojun Quan, Qing Ling et al.ACL 2020 · 101 citations
  3. Enhance Robustness of Sequence Labelling with Masked Adversarial TrainingLuoxin Chen, Xinyue Liu, Weitong Ruan, Jianhua LuEMNLP Findings 2020 · 67 citations
  4. Attention Is All You Need for Chinese Word SegmentationSufeng Duan, Hai ZhaoEMNLP 2020 · 30 citations
  5. Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word OrderYi Liao, Xin Jiang, Qun LiuACL 2020 · 28 citations

Related papers

  1. Entropy-guided Vocabulary Augmentation of Multilingual Language Models for Low-resource TasksArijit Nag, Bidisha Samanta, Animesh Mukherjee, Niloy Ganguly et al.ACL Findings 2023 · 3 citations
  2. Distilling Multiple Domains for Neural Machine TranslationAnna Currey, Prashant Mathur, Georgiana DinuEMNLP 2020 · 19 citations
  3. MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine TranslationRumeng Li, Xun Wang, Hong YuAAAI 2020 · 42 citations
  4. PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity RecognitionTao Zhang, Congying Xia, Philip S. Yu, Zhiwei Liu et al.EMNLP 2021 · 22 citations
  5. Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning ApproachVíctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, Felipe Sánchez-MartínezEMNLP 2021 · 21 citations
Dusk over the sea between two cliffs drawn in fine vertical lines