Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension

Yuan, Fei; Shou, Linjun; Bai, Xuanyu; Gong, Ming; Liang, Yilong; Duan, Nan; Fu, Yan; Jiang, Daxin

doi:10.18653/v1/2020.acl-main.87

Cited by 23 publications

(38 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine Reading Comprehension. Machine reading comprehension (MRC) (Rajpurkar et al, 2016) has received increasing attention recently, which requires a model to extract an answer span to a question from reference documents (Yu et al, 2018;Devlin et al, 2019;Zheng et al, 2020;Yuan et al, 2020). Owing to the rise of pre-training models (Devlin et al, 2018), a machine is able to achieve highly competitive results on classic datasets (e.g.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, the more challenging distantly supervised MRC task, TriviaQA (Joshi et al, 2017) was proposed, in which the provided evidences are noisy and collected based on the distant supervision. (Yuan et al, 2020) proposed a multilingual MRC task to facilitate the study on low resource languages. (Lee et al, 2019b) focused on annotating the unlabeled data with heuristic method and refine the labels by an extra Refinery model for multilingual MRC task.…”

Section: Related Workmentioning

confidence: 99%

“…Machine reading comprehension (MRC) (Rajpurkar et al, 2016) is a well-known NLP task, and has made significant progress in recent years (Yu et al, 2018;Devlin et al, 2019;Yuan et al, 2020). To learn a well-performed MRC system, large amount of human annotated data is required.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Zhang¹,

Zhou

Wang³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise. Existing related methods usually incorporate extra submodels to help filter noise before the noisy data is input to main models. However, these multistage methods often make training difficult, and the qualities of submodels are hard to be controlled. In this paper, we first explore and analyze the essential characteristics of noise from the perspective of loss distribution, and find that in the early stage of training, noisy samples usually lead to significantly larger loss values than clean ones. Based on the observation, we propose a hierarchical loss correction strategy to avoid fitting noise and enhance clean supervision signals, including using an unsupervisedly fitted Gaussian mixture model to calculate the weight factors for all losses to correct the loss distribution, and employ a hard bootstrapping loss to modify loss function. Experimental results on different weakly supervised MRC datasets show that the proposed methods can help improve models significantly.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Zhang¹,

Zhou

Wang³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…These language models aim to learn language agnostic contextual representations by leveraging large-scale monolingual and parallel corpuses, which show great potential on cross-lingual tasks, such as sentence classification tasks (Hsu et al, 2019;Pires et al, 2019;Conneau et al, 2018). However, there is still a big gap between the performance of CLMRC in rich-resource languages and that in low-resource languages, since CLMRC requires the capability of fine-grained representation at the phase-level (Yuan et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…To further boost the performance of multilingual PLM on CLMRC task, Yuan et al (2020) propose two auxiliary tasks mixMRC and LAKM on top of multilingual PLM. Those auxiliary tasks improve the answer boundary detection quality in low-resource languages.…”

Section: Introductionmentioning

confidence: 99%

Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation

Liu¹,

Shou²,

Pei³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Cross-lingual Machine Reading Comprehension (CLMRC) remains a challenging problem due to the lack of large-scale annotated datasets in low-source languages, such as Arabic, Hindi, and Vietnamese. Many previous approaches use translation data by translating from a rich-source language, such as English, to low-source languages as auxiliary supervision. However, how to effectively leverage translation data and reduce the impact of noise introduced by translation remains onerous. In this paper, we tackle this challenge and enhance the cross-lingual transferring performance by a novel augmentation approach named Language Branch Machine Reading Comprehension (LBMRC). A language branch is a group of passages in one single language paired with questions in all target languages. We train multiple machine reading comprehension (MRC) models proficient in individual language based on LBMRC. Then, we devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages. Combining the LBMRC and multilingual distillation can be more robust to the data noises, therefore, improving the model's cross-lingual ability. Meanwhile, the produced single multilingual model can apply to all target languages, which saves the cost of training, inference, and maintenance for multiple models. Extensive experiments on two CLMRC benchmarks clearly show the effectiveness of our proposed method. * Equal contribution. Work was done when Junhao Liu was an intern at Microsoft STCA.

show abstract

Enhancing Low-Resource Languages Question Answering with Syntactic Graph

Zhu²,

Zhang³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension

Cited by 23 publications

References 20 publications

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation

Enhancing Low-Resource Languages Question Answering with Syntactic Graph

Contact Info

Product

Resources

About