Papers › Smarnet: Teaching Machines to Read and Comprehend Like Human

Smarnet: Teaching Machines to Read and Comprehend Like Human

8 Oct 2017arXiv:1710.02772archive 2025-07-28

Zheqian Chen, Rongqin Yang, Bin Cao, Zhou Zhao, Deng Cai, Xiaofei He

Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question. Many existing approaches on MC task are suffering the inefficiency in some bottlenecks, such as insufficient lexical understanding, complex question-passage interaction, incorrect answer extraction and so on. In this paper, we address these problems from the viewpoint of how humans deal with reading tests in a scientific way. Specifically, we first propose a novel lexical gating mechanism to dynamically combine the words and characters representations. We then guide the machines to read in an interactive way with attention mechanism and memory network. Finally we add a checking layer to refine the answer for insurance. The extensive experiments on two popular datasets SQuAD and TriviaQA show that our method exceeds considerable performance than most state-of-the-art solutions at the time of submission.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringReading ComprehensionTriviaQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQuAD1.1 smarnet (single model) EM 71.415 #149 of 213 Archive leaderboard report
Question Answering SQuAD1.1 smarnet (single model) F1 80.160 #149 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev Smarnet EM 71.362 #33 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev Smarnet F1 80.183 #33 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections