SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_26541 · AAAI · 2023

SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition

Wei Li, Erik Cambria, Rui Mao, Luyao Zhu

Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/aaai_26541.json · badge: /api/ran/aaai_26541.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
senticnet/SKIER canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
config_logger Ran
ran on a synthesized input
senticnet/SKIER/prepare_glove.py
code served (permissive licence) · get_code("04c547199f2b0401")
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 RootLogger. 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 logging
import tempfile
import os

# Create a temporary directory and log file path
temp_dir = tempfile.mkdtemp()
log_path = os.path.join(temp_dir, "test.log")

ARGS = {
    "log_path": log_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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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_train_valid_sampler Ran
ran on a synthesized input
senticnet/SKIER/train_dd.py
code served (permissive licence) · get_code("828716810d62f8c3")
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.

import torch
import torch.nn as nn
from torch.utils.data import Dataset

torch.manual_seed(0)

class DummyDataset(Dataset):
    def __init__(self, size=20):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(4), torch.randint(0, 2, (1,))

trainset = DummyDataset(size=20)

ARGS = {
    "trainset": trainset,
    "valid": 0.1
}
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 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
load_w2v Ran
ran on a synthesized input
senticnet/SKIER/prepare_glove.py
code served (permissive licence) · get_code("8645b4118cbd9bfa")
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.

import numpy as np
import tempfile
import os

# Create a temporary directory and a mock GloVe embedding file
temp_dir = tempfile.mkdtemp()
embedding_file_path = os.path.join(temp_dir, 'glove.6B.100d.txt')

# Create a simple mock GloVe file with a few word embeddings
with open(embedding_file_path, 'w', encoding='latin') as f:
    f.write("300 100\n")  # Mock header
    f.write("the " + " ".join([str(0.1 * i) for i in range(100)]) + "\n")
    f.write("cat " + " ".join([str(0.2 * i) for i in range(100)]) + "\n")
    f.write("dog " + " ".join([str(0.3 * i) for i in range(100)]) + "\n")
    f.write("bird " + " ".join([str(0.4 * i) for i in range(100)]) + "\n")

embedding_dim = 100
embedding_path = temp_dir + "/"
cpt_vocab = [
    "the cat",
    "the dog",
    "bird is flying",
    "unknown_word"
]

ARGS = {
    "embedding_dim": embedding_dim,
    "embedding_path": embedding_path,
    "cpt_vocab": cpt_vocab
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
tokenize Ran
ran on a synthesized input
senticnet/SKIER/dataloader_10.py
code served (permissive licence) · get_code("7cfb7c74fa06cfbc")
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.

import torch
import re

torch.manual_seed(0)

# Create a minimal tokenizer stand-in that mimics HuggingFace tokenizer behavior
class MinimalTokenizer:
    def __call__(self, text, padding=None, return_tensors=None):
        # Simulate tokenization by creating dummy token IDs
        # Return dict with required keys: input_ids, attention_mask, token_type_ids
        tokens = text.split()
        num_tokens = min(len(tokens) + 2, 50)  # Keep it small, add special tokens
        
        input_ids = torch.randint(0, 1000, (1, num_tokens))
        attention_mask = torch.ones((1, num_tokens), dtype=torch.long)
        token_type_ids = torch.zeros((1, num_tokens), dtype=torch.long)
        
        return {
            'input_ids': input_ids,
            'attention_mask': attention_mask,
            'token_type_ids': token_type_ids
        }

# Create sample data dictionary with short text entries
data = {
    'dialogue_1': 'Hello how are you doing today',
    'dialogue_2': 'This is a test conversation'
}

ARGS = {
    'data': data,
    'tokenizer': MinimalTokenizer(),
    'MAX_L': 20,
    'model_type': 'albert'
}
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 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
tokenize_emory Ran
ran on a synthesized input
senticnet/SKIER/dataloader_10.py
code served (permissive licence) · get_code("aca795ddb218a2a2")
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.

import torch
import re

torch.manual_seed(0)

class MockTokenizer:
    def __call__(self, text, padding=None, return_tensors=None):
        # Simulate tokenizer output with small tensors
        batch_size = 1
        seq_length = 10
        vocab_size = 100
        
        result = {
            'input_ids': torch.randint(0, vocab_size, (batch_size, seq_length)),
            'attention_mask': torch.ones((batch_size, seq_length), dtype=torch.long),
            'token_type_ids': torch.zeros((batch_size, seq_length), dtype=torch.long),
        }
        return result

# Create sample data dictionary with short dialogues
data = {
    'dial_1': 'Hello how are you today?',
    'dial_2': 'I am doing well thank you for asking.',
}

# Create a mock tokenizer
tokenizer = MockTokenizer()

# Set parameters
MAX_L = 20
model_type = 'albert'

ARGS = {
    'data': data,
    'tokenizer': tokenizer,
    'MAX_L': MAX_L,
    'model_type': model_type,
}
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 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
tokenize_glove Ran
ran on a synthesized input
senticnet/SKIER/prepare_glove.py
code served (permissive licence) · get_code("d670f55b990e8b78")
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)

# Construct word_idx: a dictionary mapping words to token IDs
word_idx = {
    'hello': 0,
    'world': 1,
    'python': 2,
    'code': 3,
    'unk': 4  # unknown token ID
}

# Construct str_input: a string of space-separated words
str_input = "hello world python unknown code"

ARGS = {
    'word_idx': word_idx,
    'str_input': str_input
}
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 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
get_train_valid_sampler 2 other papers
2 dated earlier
2002.08267 (2020-02)
Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
2203.02385 (2022-03)
MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations

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

Emotion recognition in conversation (ERC) has received increasing attention from the research community. However, the ERC task is challenging, largely due to the complex and unstructured properties of multi-party conversations. Besides, the majority of daily dialogues take place in a specific context or circumstance, which requires rich external knowledge to understand the background of a certain dialogue. In this paper, we address these challenges by explicitly modeling the discourse relations between utterances and incorporating symbolic knowledge into multi-party conversations. We first introduce a dialogue parsing algorithm into ERC and further improve the algorithm through a transfer learning method. Moreover, we leverage different symbolic knowledge graph relations to learn knowledge-enhanced features for the ERC task. Extensive experiments on three benchmarks demonstrate that both dialogue structure graphs and symbolic knowledge are beneficial to the model performance on the task. Additionally, experimental results indicate that the proposed model surpasses baseline models on several indices.

For agents

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

get_harvested_code_for_paper("aaai_26541")
get_code_for_paper("aaai_26541")
have("aaai_26541")

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

curl https://syntology.ai/api/ran/aaai_26541.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_26541.svg)](https://syntology.ai/paper/aaai_26541)

Connect an agent — have() is free.