Papers › Ensemble Distillation for Unsupervised Constituency Parsing

Ensemble Distillation for Unsupervised Constituency Parsing

3 Oct 2023arXiv:2310.01717archive 2025-07-28

Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu, Jackie C. K. Cheung, Lili Mou

We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture differing aspects of parsing structures, which can be leveraged to enhance unsupervised parsing performance. To this end, we propose a notion of "tree averaging," based on which we further propose a novel ensemble method for unsupervised parsing. To improve inference efficiency, we further distill the ensemble knowledge into a student model; such an ensemble-then-distill process is an effective approach to mitigate the over-smoothing problem existing in common multi-teacher distilling methods. Experiments show that our method surpasses all previous approaches, consistently demonstrating its effectiveness and robustness across various runs, with different ensemble components, and under domain-shift conditions.

PaperPDFCodeCode Syntology ranMethod as code

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

Syntology 22 code samples harvested from 1 repository linked to this paper: 16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 16 ran (4 with no instrument failure; 12 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

manga-uofa/ed4ucp officialmentioned in paperSyntology: 22 samples, 16 ran (12 instrument-failed) · 6 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

22 samples harvested: 16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 6 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 · honoured contract
8ran · our draft was wrong
4ran; the contract check could not run
2ran
6unverified

Licence: 22 of the 22 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 manga-uofa/ed4ucp. “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.

manga-uofa/ed4ucp official repository 22 samples, 16 ran (12 instrument-failed) · 6 unverified
Node in 32 papers library/ensemble.py ran no licence file found · pointer only · d6e1aa4c953f9558 · report fixture: returned Node · level recorded 2026-09-22
Stack library/ensemble.py ran no licence file found · pointer only · a985842eb4760a57 · report fixture: returned Stack · level recorded 2026-09-22
add_words_to_str_tree library/ensemble.py ran · our draft was wrong no licence file found · pointer only · 22b36bfe9dedd4e5 · report fixture: signature str_tree:str/0/str, words:list/1/str · returned str · level recorded 2026-09-22
build_sub_tree library/ensemble.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 6764b3121e89eef4 · report fixture: signature root_span:tuple/1/int, spans:list/1/tuple · returned Node · level recorded 2026-09-22
cyk_variant library/ensemble.py ran · our draft was wrong no licence file found · pointer only · 4f7d2bf7bb64878d · report fixture: signature span_scores:dict/0/?, length:int/0/int · returned list · level recorded 2026-09-22
extract_words_from_str_tree library/ensemble.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 231a87f1f865e419 · report fixture: signature line:str/0/str · returned list · level recorded 2026-09-22
filter_by_start library/ensemble.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 3ea301f9efa5cada · report fixture: signature spans:list/1/tuple, start:int/0/int · returned list · level recorded 2026-09-22
filter_includeds library/ensemble.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 9dbfbe670c04af83 · report fixture: signature spans:list/1/tuple, ref:tuple/1/int · returned list · level recorded 2026-09-22
find_average_tree library/ensemble.py ran · our draft was wrong no licence file found · pointer only · ede8bd781f29b492 · report fixture: signature teacher_trees:list/1/Tree, weights:list/1/float, vote_ignoring_level:int/0/int · returned list · level recorded 2026-09-22
find_median_tree library/ensemble.py ran · our draft was wrong no licence file found · pointer only · e72081d216073a83 · report fixture: signature teacher_trees:list/1/Tree · returned Tree · level recorded 2026-09-22
forest_to_tree library/ensemble.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a0ba9e2e3043c815 · report fixture: signature forest:list/1/int · returned str · level recorded 2026-09-22
get_largest_span library/ensemble.py ran · honoured contract no licence file found · pointer only · 1ec46ad3b50cbe0f · report fixture: signature spans:list/1/tuple · returned tuple · level recorded 2026-09-22
node2forest library/ensemble.py ran · our draft was wrong no licence file found · pointer only · 2a9af10330595f30 · report fixture: signature root:Node/0/? · returned list · level recorded 2026-09-22
same_span library/ensemble.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · e0bb2143d57caccf · report fixture: signature span1:tuple/1/int, span2:tuple/1/int · returned bool · level recorded 2026-09-22
spans_except library/ensemble.py ran · honoured contract no licence file found · pointer only · 6007dcb86b995d93 · report fixture: signature spans:list/1/tuple, exceptions:list/1/tuple · returned list · level recorded 2026-09-22
sum_span_scores library/ensemble.py ran · our draft was wrong no licence file found · pointer only · 39e48f05c732688f · report fixture: signature spans:list/1/tuple, key_function:callable/0/? · returned defaultdict · level recorded 2026-09-22
Tree in 10 papers library/ensemble.py unverified no licence file found · pointer only · abbe0a517c586d0b · report
ensemble in 7 papers library/ensemble.py unverified no licence file found · pointer only · ca29ff79958717b6 · report
right_tree library/ensemble.py unverified no licence file found · pointer only · 283d86ad8198dcd7 · report
select in 22 papers library/ensemble.py unverified no licence file found · pointer only · d6c04107f4203972 · report
span_set_to_tree library/ensemble.py unverified no licence file found · pointer only · fc198a2940fed048 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for ENSEMBLE DISTILLATION (graph method: ENSEMBLE DISTILLATION). 22 bricks; individually on a fixture: 16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. ensemble entry · level 0 · unverified · ca29ff79958717b6
  2. Tree helper · level 0 · unverified · abbe0a517c586d0b
  3. extract_words_from_str_tree helper · level 1 · ran · our draft was wrong · 231a87f1f865e419
  4. generate helper · level 0 · unverified · b205273797568982
  5. right_tree helper · level 0 · unverified · 283d86ad8198dcd7
  6. select helper · level 0 · unverified · d6c04107f4203972
  7. Node helper · level 1 · ran · d6e1aa4c953f9558
  8. Stack helper · level 1 · ran · a985842eb4760a57
  9. find_average_tree helper · level 1 · ran · our draft was wrong · ede8bd781f29b492
  10. span_set_to_tree helper · level 0 · unverified · fc198a2940fed048
  11. add_words_to_str_tree helper · level 1 · ran · our draft was wrong · 22b36bfe9dedd4e5
  12. find_median_tree helper · level 1 · ran · our draft was wrong · e72081d216073a83
  13. cyk_variant helper · level 1 · ran · our draft was wrong · 4f7d2bf7bb64878d
  14. sum_span_scores helper · level 1 · ran · our draft was wrong · 39e48f05c732688f
  15. build_sub_tree helper · level 1 · ran; the contract check could not run (RAISES) · 6764b3121e89eef4
  16. forest_to_tree helper · level 1 · ran · our draft was wrong · a0ba9e2e3043c815
  17. node2forest helper · level 1 · ran · our draft was wrong · 2a9af10330595f30
  18. filter_by_start helper · level 1 · ran; the contract check could not run (RAISES) · 3ea301f9efa5cada
  19. filter_includeds helper · level 1 · ran; the contract check could not run (RAISES) · 9dbfbe670c04af83
  20. get_largest_span helper · level 1 · ran · honoured contract · 1ec46ad3b50cbe0f
  21. spans_except helper · level 1 · ran · honoured contract · 6007dcb86b995d93
  22. same_span helper · level 1 · ran; the contract check could not run (RAISES) · e0bb2143d57caccf

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2310.01717") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Constituency Grammar InductionConstituency ParsingSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Grammar Induction PTB Diagnostic ECG Database Ensemble (Generative MBR) Max F1 (WSJ) 71.9 #1 of 24 Archive leaderboard report
Constituency Grammar Induction PTB Diagnostic ECG Database Ensemble (Generative MBR) Mean F1 (WSJ) 70.4 #1 of 24 Archive leaderboard report
Constituency Grammar Induction PTB Diagnostic ECG Database Ensemble (Selective MBR) Mean F1 (WSJ) 66.2 #5 of 24 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