Papers › KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

4 Sep 2019IJCNLP 2019 11arXiv:1909.02151archive 2025-07-28

Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences. The framework first grounds a question-answer pair from the semantic space to the knowledge-based symbolic space as a schema graph, a related sub-graph of external knowledge graphs. It represents schema graphs with a novel knowledge-aware graph network module named KagNet, and finally scores answers with graph representations. Our model is based on graph convolutional networks and LSTMs, with a hierarchical path-based attention mechanism. The intermediate attention scores make it transparent and interpretable, which thus produce trustworthy inferences. Using ConceptNet as the only external resource for Bert-based models, we achieved state-of-the-art performance on the CommonsenseQA, a large-scale dataset for commonsense reasoning.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

INK-USC/KagNet officialmentioned in paperpytorchMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report
INK-USC/MHGRN mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
10ran
1unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from INK-USC/KagNet. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

INK-USC/KagNet official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
baselines/extract_csqa_bert.py ran · honoured contract fingerprinted MIT (permissive) · eb725d5794b15f6b · report fixture: signature out:ndarray/2/float, labels:ndarray/1/int · returned int64 · level recorded 2026-09-22
collate_csqa_paths models/csqa_dataset.py ran MIT (permissive) · 59331830eb0526c2 · report fixture: signature samples:list/1/tuple · returned tuple · level recorded 2026-09-25
convert_examples_to_features in 134 papers baselines/extract_csqa_bert.py ran MIT (permissive) · 324da0e6c0b20893 · report fixture: signature examples:list/1/SimpleExample, tokenizer:SimpleTokenizer/0/?, max_seq_length:int/0/int, is_training:bool/0/bool · returned list · level recorded 2026-09-25
create_hypothesis in 5 papers baselines/run_csqa_bert.py ran fingerprinted MIT (permissive) · f92024b299799ce7 · report fixture: signature fitb:str/0/str, choice:str/0/str · returned str · level recorded 2026-09-25
del_pos in 6 papers conceptnet/extract_cpnet.py ran fingerprinted MIT (permissive) · 5f4eefd99c11e698 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-25
get_fitb_from_question in 6 papers baselines/run_csqa_bert.py ran fingerprinted MIT (permissive) · fea5bb325776f21f · report fixture: signature question_text:str/0/str · returned str · level recorded 2026-09-25
get_fitb_from_question in 6 papers datasets/convert_csqa.py ran fingerprinted MIT (permissive) · 692d601c35015e13 · report fixture: signature question_text:str/0/str · returned str · level recorded 2026-09-25
load_embeddings in 33 papers models/csqa_dataset.py ran MIT (permissive) · 9b0d6be3854d5d6d · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-25
most_frequent in 6 papers baselines/ensemble.py ran fingerprinted MIT (permissive) · 08149da7e3c7cab3 · report fixture: signature List:list/1/int, qid:int/0/int · returned int · level recorded 2026-09-25
read_csqa_examples baselines/extract_csqa_bert.py ran MIT (permissive) · ce2f5b8a15be67db · report fixture: signature input_file:str/0/str, have_answer:bool/0/bool · returned list · level recorded 2026-09-25
replace_wh_word_with_blank baselines/run_csqa_bert.py ran fingerprinted MIT (permissive) · f46246d74e1f7b3e · report fixture: signature question_str:str/0/str · returned str · level recorded 2026-09-25
patch_replication_callback in 18 papers models/parallel.py unverified MIT (permissive) · e50200dbeffa0133 · report

Tasks

Common Sense ReasoningKnowledge Base Question AnsweringKnowledge GraphsNatural Language Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning CommonsenseQA KagNet Accuracy 58.9 #30 of 38 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Convolutional Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections