Deep Learning Approaches for Question Answering System

Sharma, Yashvardhan; Gupta, Sahil

doi:10.1016/j.procs.2018.05.090

Cited by 52 publications

(23 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5: if class is different from undefined then 6: if one candidate answer is a duplicate of another one then 7: Their weights are added together 8: The ensemble returns the candidate answer that has the highest weight. 9: else 10:…”

Section: Algorithm 2 Weighted Class-specific Voting Ensemblementioning

confidence: 99%

See 1 more Smart Citation

Ensemble Approach for Natural Language Question Answering Problem

Aniol¹,

Pietroń²,

Duda³

2019

2019 Seventh International Symposium on Computing and Networking Workshops (CANDARW)

View full text Add to dashboard Cite

Machine comprehension, answ ering a question depending on a given context paragraph is a typical task of Natural Language Understanding. It requires to model complex dependencies existing betw een the question and the context paragraph. There are many neural netw ork models attempting to solve the problem of question answ ering ([1], [3], [6], [12], [5]). The best models have been selected, studied and compared w ith each other. All the selected models are based on the neural attention mechanism concept. Additionally, studies on a SQUAD dataset w ere performed. The subsets of queries w ere extracted and then each model w as analyzed how it deals w ith specific group of queries. Based on these three architectures ensemble model w as created and tested on SQUAD dataset. It outperforms the best Mnemonic Reader model.

show abstract

Section: Algorithm 2 Weighted Class-specific Voting Ensemblementioning

confidence: 99%

“…These are Bidirectional Attention Flow (BiDAF) [2], QANet [23] model and Mnemonic Reader [24]. All of them use deep learning models ( [8], [9], [10]) combined with different types of attention mechanisms. Error analysis shows that each model obtains better results on different type of ques t ions.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Approach for Natural Language Question Answering Problem

Aniol¹,

Pietroń²,

Duda³

2019

2019 Seventh International Symposium on Computing and Networking Workshops (CANDARW)

View full text Add to dashboard Cite

show abstract

“…NER is also called "entity recognition", "entity extraction" and "entity segmentation", etc. It is the basis of many research questions in the field of Natural Language Processing such as relation extraction [2], event extraction [3], knowledge graph [4], machine translation [5], question answering system [6,7] and so on.…”

Section: Introductionmentioning

confidence: 99%

A review of Chinese named entity recognition

Cheng

Liu

et al. 2021

KSII TIIS

View full text Add to dashboard Cite

Named Entity Recognition (NER) is used to identify entity nouns in the corpus such as Location, Person and Organization, etc. NER is also an important basic of research in various natural language fields. The processing of Chinese NER has some unique difficulties, for example, there is no obvious segmentation boundary between each Chinese character in a Chinese sentence. The Chinese NER task is often combined with Chinese word segmentation, and so on. In response to these problems, we summarize the recognition methods of Chinese NER. In this review, we first introduce the sequence labeling system and evaluation metrics of NER. Then, we divide Chinese NER methods into rule-based methods, statistics-based machine learning methods and deep learning-based methods. Subsequently, we analyze in detail the model framework based on deep learning and the typical Chinese NER methods. Finally, we put forward the current challenges and future research directions of Chinese NER technology.

show abstract

“…Question answering system using the LSTM model has been extensively studied because LSTM can predict next word due to permanently store the status of words based on context of previous sentences [1] [2]. Di Wang et al proposed a method that combined Bidirectional Long-Short Term Memory (BiLSTM) and keywords matching to choose an answer sentence without using parsing syntax or any additional resources [3].…”

Section: Introductionmentioning

confidence: 99%

BERT+vnKG: Using Deep Learning and Knowledge Graph to Improve Vietnamese Question Answering System

Phan¹,

Do²

2020

IJACSA

View full text Add to dashboard Cite

A question answering (QA) system based on natural language processing and deep learning is a prominent area and is being researched widely. The Long Short-Term Memory (LSTM) model that is a variety of Recurrent Neural Network (RNN) used to be popular in machine translation, and question answering system. However, that model still has certainly limited capabilities, so a new model named Bidirectional Encoder Representation from Transformer (BERT) emerged to solve these restrictions. BERT has more advanced features than LSTM and shows state-of-the-art results in many tasks, especially in multilingual question answering system over the past few years. Nevertheless, we tried applying multilingual BERT model for a Vietnamese QA system and found that BERT model still has certainly limitation in term of time and precision to return a Vietnamese answer. The purpose of this study is to propose a method that solved above restriction of multilingual BERT and applied for question answering system about tourism in Vietnam. Our method combined BERT and knowledge graph to enhance accurately and find quickly for an answer. We experimented our crafted QA data about Vietnam tourism on three models such as LSTM, BERT fine-tuned multilingual for QA (BERT for QA), and BERT+vnKG. As a result, our model outperformed two previous models in terms of accuracy and time. This research can also be applied to other fields such as finance, e-commerce, and so on.

show abstract

Deep Learning Approaches for Question Answering System

Cited by 52 publications

References 4 publications

Ensemble Approach for Natural Language Question Answering Problem

Ensemble Approach for Natural Language Question Answering Problem

A review of Chinese named entity recognition

BERT+vnKG: Using Deep Learning and Knowledge Graph to Improve Vietnamese Question Answering System

Contact Info

Product

Resources

About