Papers › Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
Junbei Zhang, Xiaodan Zhu, Qian Chen, Li-Rong Dai, Si Wei, Hui Jiang
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural network framework. We first introduce syntactic information to help encode questions. We then view and model different types of questions and the information shared among them as an adaptation task and proposed adaptation models for them. On the Stanford Question Answering Dataset (SQuAD), we show that these approaches can help attain better results over a competitive baseline.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | SQuAD1.1 | jNet (ensemble) | EM | 73.010 | #139 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | jNet (ensemble) | F1 | 81.517 | #139 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | jNet (single model) | EM | 70.607 | #160 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | jNet (single model) | F1 | 79.821 | #160 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 dev | jNet (TreeLSTM adaptation, QTLa, K=100) | EM | 69.10 | #39 of 55 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 dev | jNet (TreeLSTM adaptation, QTLa, K=100) | F1 | 78.38 | #39 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