Papers › Multilingual Constituency Parsing with Self-Attention and Pre-Training

Multilingual Constituency Parsing with Self-Attention and Pre-Training

31 Dec 2018ACL 2019 7arXiv:1812.11760archive 2025-07-28

Nikita Kitaev, Steven Cao, Dan Klein

We show that constituency parsing benefits from unsupervised pre-training across a variety of languages and a range of pre-training conditions. We first compare the benefits of no pre-training, fastText, ELMo, and BERT for English and find that BERT outperforms ELMo, in large part due to increased model capacity, whereas ELMo in turn outperforms the non-contextual fastText embeddings. We also find that pre-training is beneficial across all 11 languages tested; however, large model sizes (more than 100 million parameters) make it computationally expensive to train separate models for each language. To address this shortcoming, we show that joint multilingual pre-training and fine-tuning allows sharing all but a small number of parameters between ten languages in the final model. The 10x reduction in model size compared to fine-tuning one model per language causes only a 3.2% relative error increase in aggregate. We further explore the idea of joint fine-tuning and show that it gives low-resource languages a way to benefit from the larger datasets of other languages. Finally, we demonstrate new state-of-the-art results for 11 languages, including English (95.8 F1) and Chinese (91.8 F1).

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

Syntology 28 code samples harvested from 4 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 18 samples from 3 repositories, 14 ran (11 with no instrument failure; 3 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nikitakit/self-attentive-parser officialmentioned in papermentioned on GitHubtfMITSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report
dpfried/rnng-bert mentioned on GitHubtfSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
ghazalkhalighinejad/approximating-cky mentioned on GitHubpytorchMITSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 unverified report
thomaslu2000/incremental-parsing-representations mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 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

28 samples harvested: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 3 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.

3ran · our draft was wrong
19ran
6unverified

Licence: 3 of the 28 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

nikitakit/self-attentive-parser official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
arabic src/transliterate.py ran fingerprinted MIT (permissive) · c6fbc9f36f128a4d · report fixture: signature inp:str/0/str · returned str · level recorded 2026-09-25
collapse_unary_strip_pos src/benepar/decode_chart.py ran MIT (permissive) · bd029ebdc4c2a411 · report fixture: signature tree:Tree/1/Tree, strip_top:bool/0/bool · returned Tree · level recorded 2026-09-25
format_elapsed src/export.py ran fingerprinted MIT (permissive) · d568621c7cfd96cc · report fixture: signature start_time:float/0/float · returned str · level recorded 2026-09-25
get_labeled_spans src/benepar/decode_chart.py ran MIT (permissive) · 3f9e76811bf1f815 · report fixture: signature tree:Tree/1/Tree · returned list · level recorded 2026-09-25
guess_space_after src/benepar/ptb_unescape.py ran MIT (permissive) · 9c0f1355ed00c9d1 · report fixture: signature escaped_words:list/1/str, for_english:bool/0/bool · returned list · level recorded 2026-09-25
guess_space_after_non_english src/benepar/ptb_unescape.py ran MIT (permissive) · 2da31f9e8d6c6497 · report fixture: signature escaped_words:list/1/str · returned list · level recorded 2026-09-25
hebrew src/transliterate.py ran fingerprinted MIT (permissive) · 98db1b220dd2ecb7 · report fixture: signature inp:str/0/str · returned str · level recorded 2026-09-25
pad_charts src/benepar/decode_chart.py ran MIT (permissive) · 5fa1c233f4e619bb · report fixture: signature charts:list/1/Tensor, padding_value:int/0/int · returned Tensor · level recorded 2026-09-25
evalb src/evaluate.py unverified MIT (permissive) · f800c1f3fd0d012a · report
ptb_unescape src/benepar/ptb_unescape.py unverified MIT (permissive) · 8aedd0d17836b284 · report
dpfried/rnng-bert community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
get_graph in 15 papers scripts/bert_parse.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 4289934e599d98d1 · report fixture: signature language:str/0/str, bert_large:bool/0/bool · returned str · level recorded 2026-09-22
make_command scripts/bert_parse.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · bf01d3fec3465c34 · report fixture: signature model_dir:str/0/str, bert_graph_path:str/0/str, bert_large:bool/0/bool, inorder:bool/0/bool, beam_size:int/0/int · returned list · level recorded 2026-09-22
parse in 85 papers scripts/bert_parse.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · d73ae4737d0072dc · report fixture: returned dict · level recorded 2026-09-22
ghazalkhalighinejad/approximating-cky community (archive-listed) 12 samples, 8 ran (0 instrument-failed) · 4 unverified
UniversalTransformerRandomLayerEncoderWithLayer models/ndr.py ran MIT (permissive) · 5304ef0f453a56ad · report fixture: signature layer:callable/0/? · returned function · level recorded 2026-09-26
chartscores_from_2hids models/all_models.py ran MIT (permissive) · 1248ec1004d55757 · report fixture: signature hids1:Tensor/3/float, hids2:Tensor/3/float, decoder:callable/0/?, cat:bool/0/bool · returned Tensor · level recorded 2026-09-26
chartscores_from_hids models/all_models.py ran MIT (permissive) · 6707b9653e35add5 · report fixture: signature hids:Tensor/3/float, decoder:callable/0/? · returned Tensor · level recorded 2026-09-26
extract_parse my_utils.py ran MIT (permissive) · 1e2e209296c87494 · report fixture: signature span:Tensor/3/float, length:int/0/int · returned tuple · level recorded 2026-09-26
inner_score2 models/all_models.py ran MIT (permissive) · 321467c6959866dd · report fixture: signature model:callable/0/?, inp:Tensor/2/int, inputs_embeds:Tensor/3/float, firsts:Tensor/2/int, lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-26
make_voc get_data/get_pcfg.py ran MIT (permissive) · 782a5dffeb3d6b35 · report fixture: signature cntr:dict/0/?, thresh:int/0/int, add_pad:bool/0/bool · returned tuple · level recorded 2026-09-26
make_voc get_data/make_data.py ran fingerprinted MIT (permissive) · d501ca5164d5e1b1 · report fixture: signature types:list/1/str · returned tuple · level recorded 2026-09-26
sinusoidal_pos_embedding models/ndr.py ran MIT (permissive) · 1189a8b722298cac · report fixture: signature d_model:int/0/int, max_len:int/0/int, pos_offset:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-26
get_potentials_and_trees get_data/get_pcfg.py unverified MIT (permissive) · ec1bd125cee0d5c8 · report
get_trees_and_vocs get_data/get_pcfg.py unverified MIT (permissive) · aa0d9a3ff9c7e9c0 · report
stupid_extract_parse2 my_utils.py unverified MIT (permissive) · 801802f2f39d3775 · report
tree_from_span my_utils.py unverified MIT (permissive) · a7368615fa47e4fe · report
thomaslu2000/incremental-parsing-representations community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
collapse_unlabel_binarize src/tree_transforms.py ran MIT (permissive) · ad00821962c48d10 · report fixture: signature tree:Tree/1/Tree, default_label:str/0/str · returned Tree · level recorded 2026-09-26
cub_traverse src/tree_transforms.py ran MIT (permissive) · 29605c9c3042ed16 · report fixture: signature tree:Tree/1/Tree, default_label:str/0/str · returned Tree · level recorded 2026-09-26
random_subspan src/tree_transforms.py ran MIT (permissive) · 8ec94d08b3904eba · report fixture: signature tree:list/1/list · returned list · level recorded 2026-09-26

Tasks

Constituency ParsingUnsupervised Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Parsing CTB5 Kitaev etal. 2019 F1 score 91.75 #6 of 9 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

AdamAttentionAttention DropoutBERTBiLSTMDense ConnectionsDropoutELMoLSTMLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiecefastText

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