Papers › Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

28 Feb 2015IJCNLP 2015 7arXiv:1503.00075archive 2025-07-28

Kai Sheng Tai, Richard Socher, Christopher D. Manning

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences (SemEval 2014, Task 1) and sentiment classification (Stanford Sentiment Treebank).

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1503.00075")

Code

Syntology Ran 6 of 15 code samples harvested from 5 repositories linked to this paper; 9 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 15 samples from 5 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

16 repositories listed; official and paper-mentioned ones first.

stanfordnlp/treelstm officialmentioned in papermentioned on GitHubtorchGPL-2.0 report
EmilReinert/DeepLearningPipelines mentioned on GitHubpytorch report
Vivswan/Sentiment-Analysis-TreeLSTM mentioned on GitHubpytorch report
dasguptar/treelstm.pytorch mentioned on GitHubpytorchMIT report
inyukwo1/tree-lstm mentioned on GitHubpytorchGPL-3.0 report
jayanti-prasad/TreeLSTM mentioned on GitHubpytorch report
munashe5/SemanticTreeLSTM mentioned on GitHubtf report
rohitguptacs/ReVal mentioned on GitHubtorchGPL-2.0 report
tensorflow/fold mentioned on GitHubtf report
tomekkorbak/treehopper mentioned on GitHubpytorchApache-2.0 report
ttpro1995/TreeLSTMSentiment mentioned on GitHubpytorchMIT report
vastsak/tree_structured_gru mentioned on GitHubtf report
zxk19981227/LSTM-SST mentioned on GitHubpytorch report
dmlc/dgl pytorch report
dmlc/dgl pytorch 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

15 samples harvested; 6 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
2ran · fixture could not drive it
9unverified

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

load_constituency_tree Vivswan/Sentiment-Analysis-TreeLSTM/scripts/preprocess-sst.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · fd3e77b45ce34195 · report
load_dependency_tree Vivswan/Sentiment-Analysis-TreeLSTM/scripts/preprocess-sst.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · 48a87dac90a7d495 · report
load_trees Vivswan/Sentiment-Analysis-TreeLSTM/scripts/preprocess-sst.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 8817e369ca9baf24 · report
parse_data EmilReinert/DeepLearningPipelines/workspace/pipelines/defect_prediction.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 55a0de7b0b6428f0 · report
read_file EmilReinert/DeepLearningPipelines/workspace/pipelines/defect_prediction.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 33e96662baea2bc4 · report
tidy EmilReinert/DeepLearningPipelines/workspace/pipelines/defect_prediction.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 8041e074f5f2c31b · report
choose_optimizer tomekkorbak/treehopper/treehopper/model/training.py community (archive-listed) unverified Apache-2.0 (permissive) · 0f1a6ead94a1ebe2 · report
load_word_vectors dasguptar/treelstm.pytorch/treelstm/utils.py community (archive-listed) unverified MIT (permissive) · bc4891355c566a35 · report
map_label_to_target dasguptar/treelstm.pytorch/treelstm/utils.py community (archive-listed) unverified MIT (permissive) · 04bd7091604bee59 · report
map_label_to_target ttpro1995/TreeLSTMSentiment/utils.py community (archive-listed) unverified MIT (permissive) · f55e0209ce694729 · report
map_label_to_target_sentiment ttpro1995/TreeLSTMSentiment/utils.py community (archive-listed) unverified MIT (permissive) · 2c8d4f6f1b8eb9a3 · report
parse_args ttpro1995/TreeLSTMSentiment/config.py community (archive-listed) unverified MIT (permissive) · 816c1241731833a0 · report
parse_args_train tomekkorbak/treehopper/treehopper/config.py community (archive-listed) unverified Apache-2.0 (permissive) · bcabec498122625d · report
set_arguments tomekkorbak/treehopper/treehopper/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 83e2ff5af6039f69 · report
zoneout tomekkorbak/treehopper/treehopper/model/zoneout.py community (archive-listed) unverified Apache-2.0 (permissive) · d4a62a05dc3b8ff4 · report

Tasks

General ClassificationSemantic SimilaritySentiment AnalysisSentiment Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Similarity SICK Dependency Tree-LSTM (Tai et al., 2015) MSE 0.2532 #1 of 5 Archive leaderboard report
Semantic Similarity SICK Dependency Tree-LSTM (Tai et al., 2015) Pearson Correlation 0.8676 #1 of 5 Archive leaderboard report
Semantic Similarity SICK Dependency Tree-LSTM (Tai et al., 2015) Spearman Correlation 0.8083 #1 of 5 Archive leaderboard report
Semantic Similarity SICK Bidirectional LSTM (Tai et al., 2015) MSE 0.2736 #3 of 5 Archive leaderboard report
Semantic Similarity SICK Bidirectional LSTM (Tai et al., 2015) Pearson Correlation 0.8567 #3 of 5 Archive leaderboard report
Semantic Similarity SICK Bidirectional LSTM (Tai et al., 2015) Spearman Correlation 0.7966 #3 of 5 Archive leaderboard report
Semantic Similarity SICK LSTM (Tai et al., 2015) MSE 0.2831 #4 of 5 Archive leaderboard report
Semantic Similarity SICK LSTM (Tai et al., 2015) Pearson Correlation 0.8528 #4 of 5 Archive leaderboard report
Semantic Similarity SICK LSTM (Tai et al., 2015) Spearman Correlation 0.7911 #4 of 5 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification Consistency Tree LSTM with tuned Glove vectors [tai2015improved] Accuracy 88.0 #68 of 87 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification 2-layer LSTM [tai2015improved] Accuracy 86.3 #77 of 87 Archive leaderboard report
Sentiment Analysis SST-5 Fine-grained classification Constituency Tree-LSTM Accuracy 51.0 #17 of 31 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.

Methods

LSTMSigmoid ActivationTanh Activation

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