Effective Approaches to Neural Query Language Identification

Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie

Abstract
Query language identification (Q-LID) plays a crucial role in a cross-lingual search engine. There exist two main challenges in Q-LID: (1) insufficient contextual information in queries for disambiguation; and (2) the lack of query-style training examples for low-resource languages. In this article, we propose a neural Q-LID model by alleviating the above problems from both model architecture and data augmentation perspectives. Concretely, we build our model upon the advanced Transformer model. In order to enhance the discrimination of queries, a variety of external features (e.g., character, word, as well as script) are fed into the model and fused by a multi-scale attention mechanism. Moreover, to remedy the low resource challenge in this task, a novel machine translation–based strategy is proposed to automatically generate synthetic query-style data for low-resource languages. We contribute the first Q-LID test set called QID-21, which consists of search queries in 21 languages. Experimental results reveal that our model yields better classification accuracy than strong baselines and existing LID systems on both query and traditional LID tasks.1
Anthology ID:
2022.cl-4.14
Volume:
Computational Linguistics, Volume 48, Issue 4 - December 2022
Month:
December
Year:
2022
Address:
Cambridge, MA
Venue:
CL
SIG:
Publisher:
MIT Press
Note:
Pages:
887–906
Language:
URL:
https://aclanthology.org/2022.cl-4.14
DOI:
10.1162/coli_a_00451
Bibkey:
Cite (ACL):
Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, and Jun Xie. 2022. Effective Approaches to Neural Query Language Identification. Computational Linguistics, 48(4):887–906.
Cite (Informal):
Effective Approaches to Neural Query Language Identification (Ren et al., CL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2022.cl-4.14.pdf
PDF Search