Papers › Tree Transformer: Integrating Tree Structures into Self-Attention

Tree Transformer: Integrating Tree Structures into Self-Attention

14 Sep 2019IJCNLP 2019 11arXiv:1909.06639archive 2025-07-28

Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by attention heads seems not to match human intuitions about hierarchical structures. This paper proposes Tree Transformer, which adds an extra constraint to attention heads of the bidirectional Transformer encoder in order to encourage the attention heads to follow tree structures. The tree structures can be automatically induced from raw texts by our proposed "Constituent Attention" module, which is simply implemented by self-attention between two adjacent words. With the same training procedure identical to BERT, the experiments demonstrate the effectiveness of Tree Transformer in terms of inducing tree structures, better language modeling, and further learning more explainable attention scores.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (yaushian/Tree-Transformer) was not harvested; the 10 samples below come from 1 community repository.

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yaushian/Tree-Transformer officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
iceraionly/Tree-Transformer mentioned on GitHubpytorchSyntology: not harvested report
itzpankajpanwar/Tree-transform mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 9 ran (2 instrument-failed) · 1 unverified 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

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
7ran
1unverified

Licence: 2 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from itzpankajpanwar/Tree-transform. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

itzpankajpanwar/Tree-transform community (archive-listed) 10 samples, 9 ran (2 instrument-failed) · 1 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
attention.py ran Apache-2.0 (permissive) · 30ac4034117b7c76 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/3/bool, dropout:callable/0/?, group_prob:Tensor/2/float, no_cuda:bool/0/bool · returned tuple · level recorded 2026-09-24
build_tree in 14 papers parse.py ran Apache-2.0 (permissive) · a940e63fb38eb615 · report fixture: signature break_probs:ndarray/2/float, layer:int/0/int, start:int/0/int, end:int/0/int, threshold:float/0/float · returned set · level recorded 2026-09-24
cc utils.py ran Apache-2.0 (permissive) · 4fdb28c59aa02f3c · report fixture: signature arr:ndarray/2/float, no_cuda:bool/0/bool · returned Tensor · level recorded 2026-09-24
clones in 92 papers modules.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · b1bec2c4b1c9b491 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
dump_tree parse.py ran Apache-2.0 (permissive) · 60427abde198d7f8 · report fixture: signature break_probs:ndarray/2/float, layer:int/0/int, start:int/0/int, end:int/0/int, text:list/1/str, threshold:float/0/float · returned Tree · level recorded 2026-09-24
make_save_dir utils.py ran Apache-2.0 (permissive) · 215c1b4a8625c6f5 · report fixture: signature save_dir:str/0/str · returned str · level recorded 2026-09-24
read_json in 250 papers utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · c204acb9ea9e761d · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
subsequent_mask in 38 papers modules.py ran Apache-2.0 (permissive) · 79e53d4ea458987d · report fixture: signature size:int/0/int · returned Tensor · level recorded 2026-09-25
word2tree parse.py ran Apache-2.0 (permissive) · 7832e4cac7a9683c · report fixture: signature start:int/0/int, end:int/0/int, text:list/1/str · returned Tree · level recorded 2026-09-24
get_std_opt in 6 papers modules.py unverified Apache-2.0 (permissive) · 009d3f80a8ce3436 · report

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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