Papers › Structural Embedding of Syntactic Trees for Machine Comprehension

Structural Embedding of Syntactic Trees for Machine Comprehension

2 Mar 2017EMNLP 2017 9arXiv:1703.00572archive 2025-07-28

Rui Liu, Junjie Hu, Wei Wei, Zi Yang, Eric Nyberg

Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we propose structural embedding of syntactic trees (SEST), an algorithm framework to utilize structured information and encode them into vector representations that can boost the performance of algorithms for the machine comprehension. We evaluate our approach using a state-of-the-art neural attention model on the SQuAD dataset. Experimental results demonstrate that our model can accurately identify the syntactic boundaries of the sentences and extract answers that are syntactically coherent over the baseline methods.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

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 Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQuAD1.1 SEDT (ensemble model) EM 74.090 #131 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT (ensemble model) F1 81.761 #131 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT+BiDAF (ensemble) EM 73.723 #135 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT+BiDAF (ensemble) F1 81.530 #135 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT+BiDAF (single model) EM 68.478 #165 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT+BiDAF (single model) F1 77.971 #165 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT (single model) EM 68.163 #168 of 213 Archive leaderboard report
Question Answering SQuAD1.1 SEDT (single model) F1 77.527 #168 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev SEDT-LSTM EM 67.89 #40 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev SEDT-LSTM F1 77.42 #40 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev SECT-LSTM EM 67.65 #42 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev SECT-LSTM F1 77.19 #42 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