Context-Aware Answer Extraction in Question Answering

Seonwoo, Yeon; Kim, Jihoon; Ha, Jung-Woo; Oh, Alice

doi:10.18653/v1/2020.emnlp-main.189

Cited by 19 publications

(14 citation statements)

References 16 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ebisu_uit team presents a novel method for training Vietnamese reading comprehension. To tackle the Machine reading comprehension task in Vietnamese, they apply BLANC (BLock AttentioN for Context prediction) [32] on pretrained language models. With this strategy, this model produced good results.…”

Section: The Ebisu_uit Teammentioning

confidence: 99%

VLSP 2021-ViMRC Challenge: Vietnamese Machine Reading Comprehension

Nguyen

Tran²,

Nguyễn

et al. 2022

JCSCE

View full text Add to dashboard Cite

One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data. While many datasets have been developed for MRC research for other languages, there is a lack of such resources for the Vietnamese language. Although many datasets and methodologies have been developed for English and Chinese, many Vietnamese machine reading comprehension limitations need to be solved further. Existing Vietnamese datasets for MRC research concentrate solely on answerable questions. However, in reality, questions can be unanswerable for which the correct answer is not stated in the given textual data. To address the weakness, we provide the research community with a benchmark dataset named UIT-ViQuAD 2.0 for evaluating the MRC task and question answering systems for the Vietnamese language. We use UIT-ViQuAD 2.0 as a benchmark dataset for the shared task on Vietnamese machine reading comprehension (VLSP2021-MRC) at the Eighth Workshop on Vietnamese Language and Speech Processing (VLSP 2021). This task attracted 77 participant teams from 34 universities and other organizations. Each participant was provided with the training data, including 28,457 annotated question-answer pairs, and returned the result on a public test set of more than 3,821 questions and a private test set of 3,712 questions. In this article, we present details of the organization of the shared task, an overview of the methods employed by shared-task participants, and the results. The highest performances in this competition are 77.24% (in EM) and 67.43% (in F1-score) on the private test set. The Vietnamese MRC systems proposed by the top 3 teams use XLM-RoBERTa, a powerful pre-trained language model based on the transformer architecture that has achieved state-of-the-art results on many natural language processing tasks. We believe that releasing the UIT-ViQuAD 2.0 dataset motivates more researchers to improve Vietnamese machine reading comprehension.

show abstract

Section: The Ebisu_uit Teammentioning

confidence: 99%

VLSP 2021-ViMRC Challenge: Vietnamese Machine Reading Comprehension

Nguyen

Tran²,

Nguyễn

et al. 2022

JCSCE

View full text Add to dashboard Cite

show abstract

“…However, most previous research did not focus on giving answers in the context of the question. BLANC [4] is proposed that solved this problem, and we applied it to our reading module.…”

Section: Related Workmentioning

confidence: 99%

“…According to the published BLANC article [4], using BLANC to help increase the readability of the model resulted in an accuracy increase of 2-3% compared to the baseline models on English datasets. The baseline models will extract the answer with the highest probability from the given passage.…”

Section: Introductionmentioning

confidence: 99%

“…Table 1 shows an example of the correct answer that appears multiple times in the passage 1. An overall illustration of BLANC [4] suggested BLANC to overcome this challenge, which is built on two primary ideas: utilizing a block attention method to learn the soft-labels and using the soft-labels method to predict the context of the question. Specifically, we will present more details in section 3.2.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ViMRC - VLSP 2021: Context-Aware Answer Extraction in Vietnamese Question Answering

2022

JCSCE

View full text Add to dashboard Cite

MRC is challenging the natural language processing fields; machines automatically have to answer questions based on specific passages for this task. In recent years, machine reading comprehension (MRC) has received much attention; many articles have been written about this task. However, most of those articles only develop models in two main languages, English and Chinese. In this article, we propose to apply a new model to the task of reading comprehension in Vietnamese. Specifically, we use BLANC (BLock AttentioN for Context prediction) on pre-trained baseline models to solve the Machine reading comprehension (MRC) task on Vietnamese. We have achieved good results when using BLANC on the baseline model. Specifically, with the MRC task at the VLSP share-task 2021, we scored 76.877% of F1-score on the private test and ranked 2nd in the total. This shows that BLANC works very well in MRC tasks and further enhances the Vietnamese MRC development.

show abstract

“…Recently, Machine Reading Comprehension (MRC) has attracted wide attention and achieved remarkable success when solving specific tasks in stationary environments, such as answering factual questions with wikipedia articles or answering narrative questions with web search logs (Seo et al, 2017;Seonwoo et al, 2020;Zhang et al, 2021;Wu and Xu, 2020). However, the answering scenario changes over time in real-world applications.…”

Section: Introductionmentioning

confidence: 99%

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

Wu¹,

Xu²,

Fang³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

View full text Add to dashboard Cite

Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However, it is a great challenge to learn a new domain incrementally without catastrophically forgetting previous knowledge. In this paper, MA-MRC, a continual MRC model with uncertainty-aware fixed Memory and Adversarial domain adaptation, is proposed. In MA-MRC, a fixed size memory stores a small number of samples in previous domain data along with an uncertainty-aware updating strategy when new domain data arrives. For incremental learning, MA-MRC not only keeps a stable understanding by learning both memory and new domain data, but also makes full use of the domain adaptation relationship between them by adversarial learning strategy. The experimental results show that MA-MRC is superior to strong baselines and has a substantial incremental learning ability without catastrophically forgetting under two different continual MRC settings.

show abstract

Context-Aware Answer Extraction in Question Answering

Cited by 19 publications

References 16 publications

VLSP 2021-ViMRC Challenge: Vietnamese Machine Reading Comprehension

VLSP 2021-ViMRC Challenge: Vietnamese Machine Reading Comprehension

ViMRC - VLSP 2021: Context-Aware Answer Extraction in Vietnamese Question Answering

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

Contact Info

Product

Resources

About