SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.03736 · IJCAI · 2020

Fast and Accurate Neural CRF Constituency Parsing

Yu Zhang, Zhenghua Li, Houquan Zhou

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 0 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/2008.03736.json · badge: /api/ran/2008.03736.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
jiesutd/NCRFpp community
Papers with Code archive
2 ran · 0 no recorded run
yzhangcs/crfpar marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Biaffine Ran
ran on a synthesized input · constructed an object; no result was computed
yzhangcs/crfpar/parser/modules/biaffine.py
code served (permissive licence) · get_code("aba5ec2610fcf76f")
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 an instance of its own class, Biaffine: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

class Biaffine(nn.Module):

    def __init__(self, n_in, n_out=1, bias_x=True, bias_y=True):
        super(Biaffine, self).__init__()
        self.n_in = n_in
        self.n_out = n_out
        self.bias_x = bias_x
        self.bias_y = bias_y
        self.weight = nn.Parameter(torch.Tensor(n_out, n_in + bias_x, n_in + bias_y))
        self.reset_parameters()

    def extra_repr(self):
        s = f'n_in={self.n_in}, n_out={self.n_out}'
        if self.bias_x:
            s += f', bias_x={self.bias_x}'
        if self.bias_y:
            s += f', bias_y={self.bias_y}'
        return s

    def reset_parameters(self):
        nn.init.zeros_(self.weight)

    def forward(self, x, y):
        if self.bias_x:
            x = torch.cat((x, torch.ones_like(x[..., :1])), -1)
        if self.bias_y:
            y = torch.cat((y, torch.ones_like(y[..., :1])), -1)
        s = torch.einsum('bxi,oij,byj->boxy', x, self.weight, y)
        s = s.squeeze(1)
        return s

ARGS = {
    'n_in': 4,
    'n_out': 3,
    'bias_x': True,
    'bias_y': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Biaffine — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Biaffine 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
CRF Ran
ran on a synthesized input · constructed an object; no result was computed
jiesutd/NCRFpp/model/crf.py
code served (permissive licence) · get_code("392fc2ded9b35850")
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 an instance of its own class, CRF: the run constructed the object and did not call it, so no result was computed. 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 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "tagset_size": 5,
    "gpu": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CRF — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CRF 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
log_sum_exp Ran
ran; our contract draft was wrong, not the code
jiesutd/NCRFpp/model/crf.py
code served (permissive licence) · get_code("8e960fbb64668568")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Construct arguments for log_sum_exp
# Parameters: vec (batch_size, vanishing_dim, hidden_dim), m_size (hidden_dim)

batch_size = 2
vanishing_dim = 3
hidden_dim = 4

# Create a random tensor of shape (batch_size, vanishing_dim, hidden_dim)
vec = torch.randn(batch_size, vanishing_dim, hidden_dim)

# m_size should be the hidden_dim
m_size = hidden_dim

ARGS = {
    "vec": vec,
    "m_size": m_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
log_sum_exp
brick of this paper's assembly: helper
10 other papers
7 dated earlier, 3 later
1505.08075 (2015-05)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
1806.05626 (2018-06)
NCRF++: An Open-source Neural Sequence Labeling Toolkit
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 7 more not named here

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

Estimating probability distribution is one of the core issues in the NLP field. However, in both deep learning (DL) and pre-DL eras, unlike the vast applications of linear-chain CRF in sequence labeling tasks, very few works have applied tree-structure CRF to constituency parsing, mainly due to the complexity and inefficiency of the inside-outside algorithm. This work presents a fast and accurate neural CRF constituency parser. The key idea is to batchify the inside algorithm for loss computation by direct large tensor operations on GPU, and meanwhile avoid the outside algorithm for gradient computation via efficient back-propagation. We also propose a simple two-stage bracketing-thenlabeling parsing approach to improve efficiency further. To improve the parsing performance, inspired by recent progress in dependency parsing, we introduce a new scoring architecture based on boundary representation and biaffine attention, and a beneficial dropout strategy. Experiments on PTB, CTB5.1, and CTB7 show that our two-stage CRF parser achieves new state-of-the-art performance on both settings of w/o and w/ BERT, and can parse over 1,000 sentences per second. We release our code at https://github.com/yzhangcs/crfpar.

For agents

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

get_harvested_code_for_paper("2008.03736")
get_code_for_paper("2008.03736")
have("2008.03736")

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

curl https://syntology.ai/api/ran/2008.03736.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.03736.svg)](https://syntology.ai/paper/2008.03736)

Connect an agent — have() is free.