Survey on trends and methods of an intelligent answering system

Yogish, Deepa; Manjunath, T N; Hegadi, Ravindra S.

doi:10.1109/iceeccot.2017.8284526

Cited by 9 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In textual QA [13], the knowledge resource is unstructured text such as Wikipedia pages or news articles. Textual QA extracts a sentence or answer snippet from a supporting document that responds directly to a query, which is the main form of the current QA system [49].…”

mentioning

confidence: 99%

ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks

Wang¹,

Yao²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the sentence-level answer, i.e., answer selection, or phrase-level answer, i.e., machine reading comprehension. How to produce compositional answers has not been throughout investigated. In compositional question answering, the systems should assemble several supporting evidence from the document to generate the final answer, which is more difficult than sentence-level or phrase-level QA. In this paper, we present a largescale compositional question answering dataset containing more than 120k human-labeled questions. The answer in this dataset is composed of discontiguous sentences in the corresponding document. To tackle the ComQA problem, we proposed a hierarchical graph neural networks, which represent the document from the low-level word to the high-level sentence. We also devise a question selection and node selection task for pre-training. Our proposed model achieves a significant improvement over previous machine reading comprehension methods and pre-training methods. Codes, dataset can be found at https://github.com/benywon/ComQA.

show abstract

mentioning

confidence: 99%