Papers › Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

7 Sep 2018arXiv:1809.02286archive 2025-07-28

Taeuk Kim, Jihun Choi, Daniel Edmiston, Sanghwan Bae, Sang-goo Lee

Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic compositionality by considering comprehensive syntactic information derived from both the structure and linguistic tags. Specifically, we introduce a structure-aware tag representation constructed by a separate tag-level tree-LSTM. With this, we can control the composition function of the existing word-level tree-LSTM by augmenting the representation as a supplementary input to the gate functions of the tree-LSTM. In extensive experiments, we show that models built upon the proposed architecture obtain superior or competitive performance on several sentence-level tasks such as sentiment analysis and natural language inference when compared against previous tree-structured models and other sophisticated neural models.

PaperPDFCode

Code

galsang/SATA-Tree-LSTM officialmentioned in papermentioned on GitHubpytorch report
galsang/galsang mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Natural Language InferenceSentenceSentiment AnalysisTAG

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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