SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.14568 · NeurIPS · 2020

Strongly Incremental Constituency Parsing with Graph Neural Networks

Jia Deng, Kaiyu Yang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 3 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/2010.14568.json · badge: /api/ran/2010.14568.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
princeton-vl/attach-juxtapose-parser canonical (classifier label)
classifier basis: classifier_2025
2 ran · 3 no recorded run
FunctionStatusWhere it lives
Action Ran
ran on a synthesized input · constructed an object; no result was computed
princeton-vl/attach-juxtapose-parser/transition_systems.py
code served (permissive licence) · get_code("3bc16c8163ecf854")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Action: the class was constructed and called, and the call returned an instance of its own class. The image it ran in was not recorded. If your copy returns the same type 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.

from typing import NamedTuple, Union, List, Tuple, Optional

Label = Tuple[str, ...]

class Action(NamedTuple):
    """An action in the attach-juxtatapose transition system"""
    action_type: str
    target_node: int
    parent_label: Label
    new_label: Label

    def normalize(self) -> 'Action':
        return Action(self.action_type, self.target_node, tuple(self.parent_label), tuple(self.new_label))


INIT_ARGS = {
    'action_type': 'attach',
    'target_node': 2,
    'parent_label': ('NP', 'VP'),
    'new_label': ('S', 'NP', 'VP'),
}

ARGS = {}

METHOD = 'normalize'

# Construct and call
action = Action(**INIT_ARGS)
result = action.normalize()
print(f"Original: {action}")
print(f"Normalized: {result}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Action — the call returned an instance of its own class, which has no array shape; none is stated
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
form_batch Ran
ran; our contract draft was wrong, not the code
princeton-vl/attach-juxtapose-parser/parse.py
code served (permissive licence) · get_code("7f34d7551bfc0a53")
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) and returned dict. The image it ran in was not recorded. If your copy returns the same type 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
import numpy as np

torch.manual_seed(0)

# Construct example dictionaries that match what form_batch expects
examples = [
    {
        'tokens_idx': [1, 2, 3],
        'tags_idx': [10, 11],
        'word_end_mask': [True, False, True],
        'tokens_word': ['hello', 'world', 'test'],
        'tags': ['NOUN', 'VERB']
    },
    {
        'tokens_idx': [4, 5],
        'tags_idx': [12],
        'word_end_mask': [False, True],
        'tokens_word': ['foo', 'bar'],
        'tags': ['ADJ']
    }
]

ARGS = {
    'examples': examples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
AttachJuxtapose Not yet run
unverified (harvested, no recorded run)
princeton-vl/attach-juxtapose-parser/transition_systems.py
code served (permissive licence) · get_code("d2470ae17c475ca6")
How it ran

no invocation recorded.

LeafParseNode Not yet run
unverified (harvested, no recorded run)
princeton-vl/attach-juxtapose-parser/transition_systems.py
code served (permissive licence) · get_code("84d1ced2714a4c8d")
How it ran

no invocation recorded.

ParseNode Not yet run
unverified (harvested, no recorded run)
princeton-vl/attach-juxtapose-parser/transition_systems.py
code served (permissive licence) · get_code("4260e3807fd0d4f6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to predict actions based on partial trees. However, existing transition-based parsers are predominantly based on the shift-reduce transition system, which does not align with how humans are known to parse sentences. Psycholinguistic research suggests that human parsing is strongly incremental-humans grow a single parse tree by adding exactly one token at each step. In this paper, we propose a novel transition system called attach-juxtapose. It is strongly incremental; it represents a partial sentence using a single tree; each action adds exactly one token into the partial tree. Based on our transition system, we develop a strongly incremental parser. At each step, it encodes the partial tree using a graph neural network and predicts an action. We evaluate our parser on Penn Treebank (PTB) and Chinese Treebank (CTB). On PTB, it outperforms existing parsers trained with only constituency trees; and it performs on par with state-of-the-art parsers that use dependency trees as additional training data. On CTB, our parser establishes a new state of the art. Code is available at https://github.com/princeton-vl/ attach-juxtapose-parser.

For agents

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

get_harvested_code_for_paper("2010.14568")
get_code_for_paper("2010.14568")
have("2010.14568")

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

curl https://syntology.ai/api/ran/2010.14568.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.14568.svg)](https://syntology.ai/paper/2010.14568)

Connect an agent — have() is free.