SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.10710 · AAAI · 2022

Incorporating Constituent Syntax for Coreference Resolution

Trevor Cohn, Fan Jiang

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 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; 1 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 3 failures of our instrument; 5 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/2202.10710.json · badge: /api/ran/2202.10710.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
mandarjoshi90/coref canonical (classifier label)
classifier basis not recorded on the link
10 ran · 4 no recorded run
facebookresearch/SpanBERT community
Papers with Code archive
3 ran · 0 no recorded run
Fantabulous-J/Coref-Constituent-Graph community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
FairseqCriterion Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/SpanBERT/pretraining/fairseq/criterions/spanbert_loss.py
pointer only (licence: NOASSERTION) · get_code("25f39b2758a0eba9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/SpanBERT (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

NoNSPPairLoss Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/SpanBERT/pretraining/fairseq/criterions/spanbert_loss.py
pointer only (licence: NOASSERTION) · get_code("df76c3d158410db6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/SpanBERT (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

b_cubed Ran
ran on a synthesized input
mandarjoshi90/coref/metrics.py
code served (permissive licence) · get_code("3643e9b2dc2db0a3")
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 1, dtype family float; no output shape is stated. The image it ran in was 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.

from collections import Counter

def b_cubed(clusters, mention_to_gold):
    num, dem = (0, 0)
    for c in clusters:
        if len(c) == 1:
            continue
        gold_counts = Counter()
        correct = 0
        for m in c:
            if m in mention_to_gold:
                gold_counts[tuple(mention_to_gold[m])] += 1
        for c2, count in gold_counts.items():
            if len(c2) != 1:
                correct += count * count
        num += correct / float(len(c))
        dem += len(c)
    return (num, dem)


# Setup code
ARGS = {
    "clusters": [
        ["mention_0", "mention_1", "mention_2"],
        ["mention_3", "mention_4"],
        ["mention_5"]
    ],
    "mention_to_gold": {
        "mention_0": ("entity_A", "entity_B"),
        "mention_1": ("entity_A", "entity_B"),
        "mention_2": ("entity_A", "entity_B"),
        "mention_3": ("entity_C", "entity_D"),
        "mention_4": ("entity_C", "entity_D"),
        "mention_5": ("entity_E",),
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 tuple, ndim 1, dtype family float — 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
f1 Ran
ran, honoured the contract we drafted
mandarjoshi90/coref/metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sapienzanlp/bookcoref, is pointer only (licence: NONE) · get_code("5dc251a1bb16c94f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sapienzanlp/bookcoref, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_activation Ran
ran; our contract draft was wrong, not the code
mandarjoshi90/coref/bert/modeling.py
code served (permissive licence) · get_code("5681f7dd9b6e3679")
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 function. 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 tensorflow as tf
import six

# Test cases for get_activation function
# The function takes activation_string as parameter and returns either None or a callable

ARGS = {
    "activation_string": "relu"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
get_doc_key Ran
ran; our contract draft was wrong, not the code
mandarjoshi90/coref/conll.py
code served (permissive licence) · get_code("f300a33fe05fc609")
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 str. 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

def get_doc_key(doc_id, part):
    return '{}_{}'.format(doc_id, int(part))

ARGS = {
    'doc_id': 'doc_123',
    'part': 5
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_sentence_map Ran
ran on a synthesized input
mandarjoshi90/coref/overlap_minimize.py
code served (permissive licence) · get_code("f4ced68dcb59457a")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was 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
import numpy as np

torch.manual_seed(0)

# Analyze function usage:
# - segments: iterable of iterables (len() called on it and each element)
# - sentence_end: sequence with len() and int() conversion, indexable
# - The function maps each token position to a sentence index
# - sentence_end should have same total length as sum of segment lengths
# - Each element of sentence_end is converted to int (boolean-like)

# Create segments: list of lists representing token segments
segments = [
    [1, 2, 3],      # 3 tokens in segment 1
    [4, 5]          # 2 tokens in segment 2
]

# Create sentence_end: 5 elements (3+2), marking sentence boundaries
# sentence_end[i] = 1 means token i ends a sentence, 0 means it doesn't
sentence_end = [0, 0, 1, 1, 0]

ARGS = {
    "segments": segments,
    "sentence_end": sentence_end
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list 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
get_sentence_map Ran
ran on a synthesized input
mandarjoshi90/coref/minimize.py
code served (permissive licence) · get_code("de32dc1a0c359c0d")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was 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
import numpy as np

# Analyzing the function:
# - segments: needs to be a list of lists/sequences where each has length >= 2
# - sentence_end: needs to be a list/array of binary values (0 or 1) with length equal to sum([len(s) - 2 for s in segments])

# Create valid arguments
torch.manual_seed(0)

# segments: list of segments, each segment is a sequence
# The function iterates through segments and for each segment of length n, 
# it expects n-2 entries in sentence_end
segment1 = [0, 1, 2, 3]  # length 4, contributes 2 entries to sentence_end
segment2 = [0, 1, 2]     # length 3, contributes 1 entry to sentence_end
segment3 = [0, 1, 2, 3, 4]  # length 5, contributes 3 entries to sentence_end

segments = [segment1, segment2, segment3]

# Total entries needed in sentence_end: (4-2) + (3-2) + (5-2) = 2 + 1 + 3 = 6
# sentence_end should be binary values (0 or 1) indicating sentence boundaries
sentence_end = [1, 0, 1, 0, 1, 1]

ARGS = {
    "segments": segments,
    "sentence_end": sentence_end
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list 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
is_start Ran
ran on a synthesized input
mandarjoshi90/coref/gap_to_jsonlines.py
code served (permissive licence) · get_code("0b4f0651a8572be2")
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 bool, ndim 0, dtype family float, shape () 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
import numpy as np

# The function is_start checks if a character position is at the start of a word
# It needs:
# 1. char_offset: an integer representing the current character position
# 2. char_to_word_offset: a list/array mapping character positions to word positions
# 3. text: a string (used only implicitly through the other parameters)

# Let's construct a simple example with a short text
text = "hello world"

# char_to_word_offset maps each character index to its word index
# "hello world" has characters 0-4 in word 0, char 5 is space (word 1?), 6-10 in word 1
# Standard tokenization: 
# h(0) e(1) l(2) l(3) o(4) (space) w(6) o(7) r(8) l(9) d(10)
# We'll map: char 0-4 -> word 0, char 5 -> word 0 (space stays with word 0), char 6-10 -> word 1

char_to_word_offset = [0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1]

# Test with char_offset = 0 (should be True - start of text)
char_offset = 0

ARGS = {
    "char_offset": char_offset,
    "char_to_word_offset": char_to_word_offset,
    "text": text
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () 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
normalize_word Ran
ran on a synthesized input
mandarjoshi90/coref/minimize.py
code served (permissive licence) · get_code("3b625164c1147fcf")
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 str. 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.

ARGS = {
    'word': '/.',
    'language': 'arabic'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
official_conll_eval Ran
ran on a synthesized input
mandarjoshi90/coref/conll.py
code served (permissive licence) · get_code("5712dc7b00cdd758")
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 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 re
import subprocess
import tempfile
import os

# Create temporary files with mock data
gold_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
predicted_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')

# Write minimal valid CoNLL format data
gold_content = """#begin document (doc1); part 000
doc1	0	0	The	DT	(TOP(S(NP*)	-	-	-	-	*	(0
doc1	0	1	cat	NN	*)	-	-	-	-	*	0)
doc1	0	2	sat	VBD	(VP*)	-	-	-	-	*	-
#end document
"""

predicted_content = """#begin document (doc1); part 000
doc1	0	0	The	DT	(TOP(S(NP*)	-	-	-	-	*	(0
doc1	0	1	cat	NN	*)	-	-	-	-	*	0)
doc1	0	2	sat	VBD	(VP*)	-	-	-	-	*	-
#end document
"""

gold_file.write(gold_content)
gold_file.close()

predicted_file.write(predicted_content)
predicted_file.close()

# Create a mock scorer script that outputs valid coreference results
scorer_dir = tempfile.mkdtemp()
scorer_script = os.path.join(scorer_dir, 'scorer.pl')
os.makedirs(os.path.dirname(scorer_script), exist_ok=True)

with open(scorer_script, 'w') as f:
    f.write("""#!/usr/bin/env perl
print "Coreference: Recall: (1 / 1) 100.0%\\tPrecision: (1 / 1) 100.0%\\tF1: 100.0%\\n";
""")
os.chmod(scorer_script, 0o755)

# Patch the subprocess to handle our mock script
original_popen = subprocess.Popen

class MockPopen:
    def __init__(self, cmd, **kwargs):
        self.returncode = 0
        self.stdout = kwargs.get('stdout')
    
    def communicate(self):
        stdout = b"Coreference: Recall: (1 / 1) 100.0%\tPrecision: (1 / 1) 100.0%\tF1: 100.0%\n"
        return stdout, None
    
    def wait(self):
        return 0

subprocess.Popen = MockPopen

ARGS = {
    'gold_path': gold_file.name,
    'predicted_path': predicted_file.name,
    'metric': 'muc',
    'official_stdout': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
read_tsv Ran
ran on a synthesized input
mandarjoshi90/coref/gap_to_jsonlines.py
code served (permissive licence) · get_code("ae6a373fe4f5dee8")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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 tempfile
import os

# Create a temporary TSV file for testing
temp_dir = tempfile.mkdtemp()
tsv_file_path = os.path.join(temp_dir, "test.tsv")

# Write a sample TSV file with headers and data
with open(tsv_file_path, 'w') as f:
    f.write("name\tage\toffset\n")
    f.write("Alice\t30\t100\n")
    f.write("Bob\t25\t200\n")

ARGS = {
    'tsv_file': tsv_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 list, ndim 1, dtype family float — a list 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
register_criterion Ran
ran; our contract draft was wrong, not the code
facebookresearch/SpanBERT/pretraining/fairseq/criterions/spanbert_loss.py
pointer only (licence: NOASSERTION) · get_code("3cc2e76a1b0117ef")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/SpanBERT (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CGATLayer Not yet run
unverified (harvested, no recorded run)
Fantabulous-J/Coref-Constituent-Graph/chinese/coref-cons/modules.py
pointer only (licence: NONE) · get_code("e5030f6584af77f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Fantabulous-J/Coref-Constituent-Graph when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

evaluate_conll Not yet run
unverified (harvested, no recorded run)
mandarjoshi90/coref/conll.py
code served (permissive licence) · get_code("ea92f536bea4cbd4")
How it ran

no invocation recorded.

gelu Not yet run
unverified (harvested, no recorded run)
mandarjoshi90/coref/bert/modeling.py
code served (permissive licence) · get_code("ecab128238ebf253")
How it ran

no invocation recorded.

get_assignment_map_from_checkpoint Not yet run
unverified (harvested, no recorded run)
mandarjoshi90/coref/bert/modeling.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from toggle1995/RIS-DMMI, is pointer only (licence: NONE) · get_code("50958618b65e514e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from toggle1995/RIS-DMMI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

read_doc_keys Not yet run
unverified (harvested, no recorded run)
mandarjoshi90/coref/evaluate.py
code served (permissive licence) · get_code("edcb69a1bdf0f631")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 0 the same month, 8 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.

FunctionAlso present inEarliest-datedOthers named
get_activation 32 other papers
25 dated earlier, 6 later, 1 same year, order not determinable · 1 only as an assembly brick
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 29 more not named here
get_assignment_map_from_checkpoint 26 other papers
21 dated earlier, 4 later, 1 same year, order not determinable
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 23 more not named here
gelu 16 other papers
13 dated earlier, 2 later, 1 same year, order not determinable · 2 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 13 more not named here
f1 12 other papers
4 dated earlier, 8 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
2021.naacl-main.125 (2021 (year only))
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
and 9 more not named here
get_doc_key 8 other papers
4 dated earlier, 4 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
2021.naacl-main.125 (2021 (year only))
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
and 5 more not named here
evaluate_conll 4 other papers
2 dated earlier, 2 later
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
2109.06067 (2021-09)
Packed Levitated Marker for Entity and Relation Extraction
2025.findings-emnlp.1354 (2025 (year only))
Dependency Parsing-Based Syntactic Enhancement of Relation Extraction in Scientific Texts
and 1 more not named here
normalize_word 4 other papers
3 dated earlier, 1 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
2021.naacl-main.125 (2021 (year only))
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
and 1 more not named here
b_cubed 3 other papers
1 dated earlier, 2 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
2205.12644 (2022-05)
LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
2024.acl-srw.56 (2024 (year only))
Z-coref: Thai Coreference and Zero Pronoun Resolution
official_conll_eval 2 other papers
2 dated earlier
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
get_sentence_map 1 other paper
1 dated earlier
2021.naacl-main.125 (2021 (year only))
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
get_sentence_map 1 other paper
1 dated earlier
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
read_doc_keys 1 other paper
1 dated earlier
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
register_criterion
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.04380 (2020-10)
Token-level Adaptive Training for Neural Machine Translation

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

Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statistical machine learning based systems or recently proposed neural models. However, most leading systems use only dependency trees. We argue that constituent trees also encode important information, such as explicit span-boundary signals captured by nested multi-word phrases, extra linguistic labels and hierarchical structures useful for detecting anaphora. In this work, we propose a simple yet effective graph-based method to incorporate constituent syntactic structures. Moreover, we also explore to utilise higher-order neighbourhood information to encode rich structures in constituent trees. A novel message propagation mechanism is therefore proposed to enable information flow among elements in syntax trees. Experiments on the English and Chinese portions of OntoNotes 5.0 benchmark show that our proposed model either beats a strong baseline or achieves new state-of-the-art performance. Code is available at https://github.com/Fantabulous-J/Coref-Constituent-Graph.

For agents

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

get_harvested_code_for_paper("2202.10710")
get_code_for_paper("2202.10710")
have("2202.10710")

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

curl https://syntology.ai/api/ran/2202.10710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.10710.svg)](https://syntology.ai/paper/2202.10710)

Connect an agent — have() is free.