TitleMAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction
AuthorsYang, Pengcheng
Luo, Fuli
Chen, Peng
Liu, Tianyu
Sun, Xu
AffiliationPeking Univ, Beijing Inst Big Data Res, Deep Learning Lab, Beijing, Peoples R China
Peking Univ, Sch EECS, MOE Key Lab Computat Linguist, Beijing, Peoples R China
Issue Date2019
Publisher57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)
AbstractThe task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages. Previous work has shown that morphological variation is an intractable challenge for the UBLI task, where the induced translation in failure case is usually morphologically related to the correct translation. To tackle this challenge, we propose a morphology-aware alignment model for the UBLI task. The proposed model aims to alleviate the adverse effect of morphological variation by introducing grammatical information learned by the pre-trained denoising language model. Results show that our approach can substantially outperform several state-of-the-art unsupervised systems, and even achieves competitive performance compared to supervised methods.
URIhttp://hdl.handle.net/20.500.11897/552794
IndexedISSHP
CPCI-S(ISTP)
Appears in Collections:信息科学技术学院
计算语言学教育部重点实验室

Files in This Work
There are no files associated with this item.

Web of Science®



Checked on Last Week

百度学术™



Checked on Current Time




License: See PKU IR operational policies.