SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.14674 · NAACL · 2021

AMR Parsing with Action-Pointer Transformer

Jiawei Zhou, Tahira Naseem, Ramón Fernandez, Radu Florian

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2104.14674.json · badge: /api/ran/2104.14674.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ibm/graph_ensemble_learning community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
prepare_data Ran
ran, honoured the contract we drafted
ibm/graph_ensemble_learning/amr_parsing/t5/models/lg.py
code served (permissive licence) · get_code("ef86f857417defe2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family int; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from transformers import TensorType

torch.manual_seed(0)

class MockTokenizer:
    def __init__(self):
        self.pad_token_id = 0
    
    def batch_encode_plus(self, batch_text, padding=True, truncation=False, max_length=None, return_attention_mask=True, return_tensors=None):
        # Return mock encoded output
        batch_size = len(batch_text)
        seq_length = 5
        input_ids = torch.randint(1, 100, (batch_size, seq_length))
        attention_mask = torch.ones((batch_size, seq_length), dtype=torch.long)
        return {
            'input_ids': input_ids,
            'attention_mask': attention_mask
        }

batch_text = ["I like monkey", "How are you"]
tokenizer = MockTokenizer()
max_length = 10
pad_id = 999
return_overflowing_tokens = True

ARGS = {
    'batch_text': batch_text,
    'tokenizer': tokenizer,
    'max_length': max_length,
    'pad_id': pad_id,
    'return_overflowing_tokens': return_overflowing_tokens
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LG Not yet run
unverified (harvested, no recorded run)
ibm/graph_ensemble_learning/amr_parsing/t5/models/lg.py
code served (permissive licence) · get_code("fd285eab3acfada6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Meaning Representation parsing is a sentence-to-graph prediction task where target nodes are not explicitly aligned to sentence tokens. However, since graph nodes are semantically based on one or more sentence tokens, implicit alignments can be derived. Transition-based parsers operate over the sentence from left to right, capturing this inductive bias via alignments at the cost of limited expressiveness. In this work, we propose a transition-based system that combines hard-attention over sentences with a targetside action pointer mechanism to decouple source tokens from node representations and address alignments. We model the transitions as well as the pointer mechanism through straightforward modifications within a single Transformer architecture. Parser state and graph structure information are efficiently encoded using attention heads. We show that our action-pointer approach leads to increased expressiveness and attains large gains (+1.6 points) against the best transition-based AMR parser in very similar conditions. While using no graph re-categorization, our single model yields the second best SMATCH score on AMR 2.0 (81.8), which is further improved to 83.4 with silver data and ensemble decoding.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.14674")
get_code_for_paper("2104.14674")
have("2104.14674")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.14674.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.14674.svg)](https://syntology.ai/paper/2104.14674)

Connect an agent — have() is free.