SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00087 · ACL · 2020

Revisiting Unsupervised Relation Extraction

Sophia Ananiadou, Thy Tran, Phong Le

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures 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/2005.00087.json · badge: /api/ran/2005.00087.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
diegma/relation-autoencoder canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
before_arg1 Ran
ran on a synthesized input
diegma/relation-autoencoder/definitions/OieFeatures.py
code served (permissive licence) · get_code("23d949eb0421a508")
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 re
import string

sentence = 3

def arg1(info, arg1, arg2):
    return arg1

def before_arg1(info, arg1, arg2):
    before = info[sentence][:info[sentence].find(arg1)]
    beforeSplit = before.lower().strip().split(' ')
    beforeSplit = [word for word in beforeSplit if word not in string.punctuation]
    if len(beforeSplit) > 1:
        return [beforeSplit[-2], beforeSplit[-1]]
    elif len(beforeSplit) == 1:
        if beforeSplit[0] != '':
            return [beforeSplit[-1]]
        else:
            return []
    else:
        return []

ARGS = {
    "info": [
        "sentence zero",
        "sentence one",
        "sentence two",
        "the quick brown fox jumps over lazy dog"
    ],
    "arg1": "jumps",
    "arg2": "unused_param"
}
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
bow Ran
ran on a synthesized input
diegma/relation-autoencoder/definitions/OieFeatures.py
code served (permissive licence) · get_code("a4dbe11872dda513")
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 torch

torch.manual_seed(0)

sentence = 3

info = [
    "hello world test string",
    "another test line here",
    "some data in position two",
    "the quick brown fox jumps over the lazy dog",
    "final string at index four"
]

arg1 = "quick"
arg2 = "lazy"

ARGS = {
    "info": info,
    "arg1": arg1,
    "arg2": arg2
}
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 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

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

Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE. 1

For agents

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

get_harvested_code_for_paper("2005.00087")
get_code_for_paper("2005.00087")
have("2005.00087")

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

curl https://syntology.ai/api/ran/2005.00087.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.00087.svg)](https://syntology.ai/paper/2005.00087)

Connect an agent — have() is free.