SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.11702 · 2022

BERT-ASC: Auxiliary-Sentence Construction for Implicit Aspect Learning in Sentiment Analysis

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 4 have no contract verdict; 1 failure of our instrument; 2 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/2203.11702.json · badge: /api/ran/2203.11702.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
amurtadha/bert-asc canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
FunctionStatusWhere it lives
cleaning Ran
ran on a synthesized input
amurtadha/bert-asc/L-LDA/preprocessing.py
code served (permissive licence) · get_code("26b8f06bf5cdf325")
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 csv
import re

def cleaning(text):
    words_to_repere = ["it's", "don't", "'", "isn't", "you've", "'s"]
    for w in words_to_repere:
        text = text.replace(w, ' ' + w + ' ')
    text = re.sub('[^\\w\\s]', '', text)
    return text

ARGS = {
    "text": "Hello, it's a test! Don't worry, you've got this. Isn't it great?"
}
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
get_parse Ran
ran on a synthesized input
amurtadha/bert-asc/ASC_generating/opinion_words_extracting.py
code served (permissive licence) · get_code("5ed8e61d5251692a")
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 2, 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.

class Token:
    def __init__(self, word, token_end_index):
        self.word = word
        self.tokenEndIndex = token_end_index

class Edge:
    def __init__(self, source, target, dep):
        self.source = source
        self.target = target
        self.dep = dep

class DependencyParse:
    def __init__(self, edges):
        self.edge = edges

class Sentence:
    def __init__(self, tokens, dependency_parse):
        self.token = tokens
        self.enhancedDependencies = dependency_parse

class Annotation:
    def __init__(self, sentence):
        self.sentence = [sentence]

# Create token objects with tokenEndIndex as keys
tokens = [
    Token("The", 3),
    Token("quick", 9),
    Token("brown", 15),
    Token("fox", 19)
]

# Create edges with source/target matching tokenEndIndex values
edges = [
    Edge(3, 9, "det"),
    Edge(9, 15, "amod"),
    Edge(15, 19, "nsubj")
]

dependency_parse = DependencyParse(edges)
sentence = Sentence(tokens, dependency_parse)
ann = Annotation(sentence)

ARGS = {
    "ann": ann
}
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 2, 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
sentihood_macro_F1 Ran
ran on a synthesized input
amurtadha/bert-asc/code/evaluation.py
code served (permissive licence) · get_code("e9ca51d345b01ef2")
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 float, 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

torch.manual_seed(0)

# Analyzing the function:
# - y_true: list or array-like, indexed with integers, compared to 0
# - y_pred: list or array-like, indexed with integers, compared to 0
# - len(y_pred) must be divisible by 4
# - Elements are compared with != 0 and == 0
# - The function processes groups of 4 elements at a time

# Create test data: 2 groups of 4 elements each (8 total)
# y_pred: predictions (0 or non-zero values)
# y_true: ground truth (0 or non-zero values)

y_pred = [0, 1, 0, 2,    # First group: aspects 1, 3 predicted
          1, 0, 2, 0]    # Second group: aspects 0, 2 predicted

y_true = [0, 1, 1, 0,    # First group: aspects 1, 2 are true
          1, 1, 0, 0]    # Second group: aspects 0, 1 are true

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred
}
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 float, 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
sentihood_strict_acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amurtadha/bert-asc/code/evaluation.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from anshulwadhawan/ABSA, is pointer only (licence: NONE) · get_code("367e923376717b34")
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 anshulwadhawan/ABSA, 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.

sort_auxiliary Ran
ran on a synthesized input
amurtadha/bert-asc/ASC_generating/opinion_words_extracting.py
code served (permissive licence) · get_code("754f8945fbeec6ec")
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

# Construct arguments for sort_auxiliary function
# The function takes two string parameters: text_a and text_b
# text_a is split into words and used as a reference list
# text_b is used to look up indices or collect words not in text_a

text_a = "apple banana cherry date"
text_b = "cherry apple elderberry banana"

ARGS = {
    "text_a": text_a,
    "text_b": text_b
}
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
parseSentence Not yet run
unverified (harvested, no recorded run)
amurtadha/bert-asc/ASC_generating/preprocessing.py
code served (permissive licence) · get_code("cbfa53ba605a4b5d")
How it ran

no invocation recorded.

sentihood_AUC_Acc Not yet run
unverified (harvested, no recorded run)
amurtadha/bert-asc/code/evaluation.py
code served (permissive licence) · get_code("771e468728b122a4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 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.

FunctionAlso present inEarliest-datedOthers named
sentihood_strict_acc 2 other papers
2 dated earlier
1903.09588 (2019-03)
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
aaai_17659 (2021 (year only))
Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis
sentihood_AUC_Acc 1 other paper
1 dated earlier
aaai_17659 (2021 (year only))
Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

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

Aspect-based sentiment analysis (ABSA) aims to associate a text with a set of aspects and infer their respective sentimental polarities. State-of-the-art approaches are built on fine-tuning pre-trained language models, focusing on learning aspect-specific representations from the corpus. However, aspects are often expressed implicitly, making implicit mapping challenging without sufficient labeled examples, which may be scarce in real-world scenarios. This paper proposes a unified framework to address aspect categorization and aspect-based sentiment subtasks. We introduce a mechanism to construct an auxiliary-sentence for the implicit aspect using the corpus's semantic information. We then encourage BERT to learn aspect-specific representation in response to this auxiliary-sentence, not the aspect itself. We evaluate our approach on real benchmark datasets for both ABSA and Targeted-ABSA tasks. Our experiments show that it consistently achieves state-of-the-art performance in aspect categorization and aspect-based sentiment across all datasets, with considerable improvement margins. The BERT-ASC code is available at https://github.com/amurtadha/BERT-ASC.

For agents

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

get_harvested_code_for_paper("2203.11702")
get_code_for_paper("2203.11702")
have("2203.11702")

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

curl https://syntology.ai/api/ran/2203.11702.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.11702.svg)](https://syntology.ai/paper/2203.11702)

Connect an agent — have() is free.