Papers › AMR Parsing via Graph-Sequence Iterative Inference

AMR Parsing via Graph-Sequence Iterative Inference

12 Apr 2020ACL 2020 6arXiv:2004.05572archive 2025-07-28

Deng Cai, Wai Lam

We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph. At each time step, our model performs multiple rounds of attention, reasoning, and composition that aim to answer two critical questions: (1) which part of the input sequence to abstract; and (2) where in the output graph to construct the new concept. We show that the answers to these two questions are mutually causalities. We design a model based on iterative inference that helps achieve better answers in both perspectives, leading to greatly improved parsing accuracy. Our experimental results significantly outperform all previously reported Smatch scores by large margins. Remarkably, without the help of any large-scale pre-trained language model (e.g., BERT), our model already surpasses previous state-of-the-art using BERT. With the help of BERT, we can push the state-of-the-art results to 80.2% on LDC2017T10 (AMR 2.0) and 75.4% on LDC2014T12 (AMR 1.0).

PaperPDFConference PDFCodeCode 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 31 code samples: 30 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 31: 21 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 24 samples from 1 repository, 16 ran (12 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

jcyk/AMR-gs officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
bjascob/amrlib mentioned on GitHubSyntology: 24 samples, 16 ran (4 instrument-failed) · 8 unverified report
ibm/graph_ensemble_learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AMR Parsing with Action-Pointer Transformer (arXiv:2104.14674; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified) and Ensembling Graph Predictions for AMR Parsing (arXiv:2110.09131; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 21 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 10 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.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
14ran
10unverified

Licence: 1 of the 31 samples is 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 2 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. 1 sample is listed last, in a group without a repository. “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 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

jcyk/AMR-gs official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
ListsToTensor in 6 papers parser/data.py ran MIT (permissive) · 12eb240a8ae9ed12 · report fixture: signature xs:list/1/list, vocab:SimpleVocab/0/?, local_vocabs:list/1/dict, unk_rate:float/0/float · returned ndarray · level recorded 2026-09-25
is_attr_or_abs_form parser/AMRGraph.py ran MIT (permissive) · 5846e0e199be3a49 · report fixture: signature x:str/0/str · returned bool · level recorded 2026-09-25
make_vocab in 5 papers parser/extract.py ran MIT (permissive) · 5d147ec91127fd39 · report fixture: signature batch_seq:list/1/list, char_level:bool/0/bool · returned Counter · level recorded 2026-09-25
need_an_instance parser/AMRGraph.py ran MIT (permissive) · 53445cbd60ba3b37 · report fixture: signature x:str/0/str · returned bool · level recorded 2026-09-25
ArraysToTensor parser/data.py unverified MIT (permissive) · 664642471ed447d0 · report
ListsofStringToTensor parser/data.py unverified MIT (permissive) · b34a3f249614ba45 · report
bjascob/amrlib community (archive-listed) 24 samples, 16 ran (4 instrument-failed) · 8 unverified
AMREmbedding amrlib/models/parse_gsii/modules/parser.py ran · our draft was wrong MIT (permissive) · 9c17ed9b8e45ed75 · report fixture: signature vocab:Vocab/0/?, embedding_dim:int/0/int, pretrained_file:str/0/str, amr:bool/0/bool, dump_file:str/0/str · returned Embedding · level recorded 2026-09-22
Beam in 8 papers amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 9422195a9817c9f0 · report fixture: returned Beam · level recorded 2026-09-22
CNNEncoder amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 2aca3b9ec1e90acc · report fixture: returned CNNEncoder · level recorded 2026-09-22
ConceptEncoder amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 9685d1d7338d51b0 · report fixture: returned ConceptEncoder · level recorded 2026-09-22
Highway in 5 papers amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 9a03fd1280e48fe1 · report fixture: returned Highway · level recorded 2026-09-22
Hypothesis in 5 papers amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 578aaecb450604aa · report fixture: returned Hypothesis · level recorded 2026-09-22
ListsToTensor in 6 papers amrlib/models/parse_gsii/modules/parser.py ran · honoured contract MIT (permissive) · 61216bb6394461a5 · report fixture: signature xs:list/1/list, vocab:SimpleVocab/0/?, local_vocabs:list/1/dict, unk_rate:float/0/float · returned ndarray · level recorded 2026-09-22
RelationGenerator amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · d575ce59062e5687 · report fixture: returned RelationGenerator · level recorded 2026-09-22
SelfAttentionMask amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 2eacf55a75ce3b77 · report fixture: returned SelfAttentionMask · level recorded 2026-09-22
SinusoidalPositionalEmbedding in 10 papers amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 940651e6bf8dc1b0 · report fixture: returned SinusoidalPositionalEmbedding · level recorded 2026-09-22
TransformerLayer in 34 papers amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 8e5d31580fcebd5a · report fixture: returned TransformerLayer · level recorded 2026-09-22
WordEncoder amrlib/models/parse_gsii/modules/parser.py ran MIT (permissive) · 490e608e2f392b83 · report fixture: returned WordEncoder · level recorded 2026-09-22
_is_attr_form amrlib/models/parse_gsii/modules/parser.py ran · violated contract MIT (permissive) · 5fe4e042a974cf92 · report fixture: signature x:str/0/str · returned bool · level recorded 2026-09-22
compute_f_by_tensor amrlib/models/parse_gsii/modules/parser.py ran · our draft was wrong fingerprinted MIT (permissive) · 4166e883cf4ae5a9 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, mask:Tensor/2/float · returned tuple · level recorded 2026-09-22
label_smoothed_nll_loss in 43 papers amrlib/models/parse_gsii/modules/parser.py ran · our draft was wrong MIT (permissive) · 2746494f3bbf25b3 · report fixture: signature log_probs:Tensor/2/float, target:Tensor/1/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
move_to_device in 26 papers amrlib/models/parse_gsii/modules/parser.py ran · our draft was wrong MIT (permissive) · 9d1d752263773f70 · report fixture: signature maybe_tensor:Tensor/2/float, device:str/0/str · returned Tensor · level recorded 2026-09-22
ArcGenerator amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · ff00df88d53cbc0d · report
ConceptGenerator amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · 08e5532ebc24827d · report
DecodeLayer amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · 408d38484408687b · report
ListsofStringToTensor amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · ab457d4ca63f1a01 · report
MultiheadAttention in 44 papers amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · 4b0bd99292baeaff · report
Parser amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · e56d2ab78d40acb7 · report
Transformer in 173 papers amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · f0af88a62479f8da · report
search_by_batch amrlib/models/parse_gsii/modules/parser.py unverified MIT (permissive) · 009b8f7e0b6e1c7a · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
Embedding in 90 papers repository not located ran · our draft was wrong licence of this copy not recorded · 1485dd769dd9cb51 · report fixture: signature num_embeddings:int/0/int, embedding_dim:int/0/int, padding_idx:int/0/int · returned Embedding · level recorded 2026-09-22

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 Graph Sequence Iterative Inference (graph method: Graph Sequence Iterative Inference). 25 bricks; individually on a fixture: 17 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. Parser entry · level 0 · unverified · e56d2ab78d40acb7
  2. Beam helper · level 1 · ran · 9422195a9817c9f0
  3. ConceptEncoder helper · level 1 · ran · 9685d1d7338d51b0
  4. DecodeLayer model · level 0 · unverified · 408d38484408687b
  5. Hypothesis helper · level 1 · ran · 578aaecb450604aa
  6. ListsToTensor helper · level 1 · ran · honoured contract · 61216bb6394461a5
  7. ListsofStringToTensor helper · level 0 · unverified · ab457d4ca63f1a01
  8. SelfAttentionMask helper · level 1 · ran · 2eacf55a75ce3b77
  9. SinusoidalPositionalEmbedding helper · level 1 · ran · 940651e6bf8dc1b0
  10. Transformer helper · level 0 · unverified · f0af88a62479f8da
  11. WordEncoder helper · level 1 · ran · 490e608e2f392b83
  12. move_to_device helper · level 1 · ran · our draft was wrong · 9d1d752263773f70
  13. search_by_batch helper · level 0 · unverified · 009b8f7e0b6e1c7a
  14. _is_attr_form helper · level 1 · ran · violated contract · 5fe4e042a974cf92
  15. AMREmbedding helper · level 1 · ran · our draft was wrong · 9c17ed9b8e45ed75
  16. CNNEncoder helper · level 1 · ran · 2aca3b9ec1e90acc
  17. ArcGenerator model · level 0 · unverified · ff00df88d53cbc0d
  18. ConceptGenerator model · level 0 · unverified · 08e5532ebc24827d
  19. RelationGenerator model · level 1 · ran · d575ce59062e5687
  20. TransformerLayer helper · level 1 · ran · 8e5d31580fcebd5a
  21. Embedding helper · level 1 · ran · our draft was wrong · 1485dd769dd9cb51
  22. Highway helper · level 1 · ran · 9a03fd1280e48fe1
  23. MultiheadAttention helper · level 0 · unverified · 4b0bd99292baeaff
  24. compute_f_by_tensor helper · level 1 · ran · our draft was wrong · 4166e883cf4ae5a9
  25. label_smoothed_nll_loss helper · level 1 · ran · our draft was wrong · 2746494f3bbf25b3

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="2004.05572") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AMR ParsingLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
AMR Parsing LDC2014T12 AMR Parsing via Graph-Sequence Iterative Inference F1 Full 75.4 #3 of 12 Archive leaderboard report
AMR Parsing LDC2017T10 Cai and Lam Smatch 80.2 #17 of 27 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 DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight 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