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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1909.02151")

Code

Syntology Ran 1 of 12 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 12 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

INK-USC/KagNet officialmentioned in paperpytorchMIT report
INK-USC/MHGRN mentioned on GitHubpytorch 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; 1 ran; 1 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
11unverified

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

accuracy INK-USC/KagNet/baselines/extract_csqa_bert.py official repository ran · honoured contract fingerprinted MIT (permissive) · eb725d5794b15f6b · report
collate_csqa_paths INK-USC/KagNet/models/csqa_dataset.py official repository unverified MIT (permissive) · 59331830eb0526c2 · report
convert_examples_to_features INK-USC/KagNet/baselines/extract_csqa_bert.py official repository unverified MIT (permissive) · 324da0e6c0b20893 · report
create_hypothesis INK-USC/KagNet/baselines/run_csqa_bert.py official repository unverified MIT (permissive) · f92024b299799ce7 · report
del_pos INK-USC/KagNet/conceptnet/extract_cpnet.py official repository unverified MIT (permissive) · 5f4eefd99c11e698 · report
get_fitb_from_question INK-USC/KagNet/baselines/run_csqa_bert.py official repository unverified MIT (permissive) · fea5bb325776f21f · report
get_fitb_from_question INK-USC/KagNet/datasets/convert_csqa.py official repository unverified MIT (permissive) · 692d601c35015e13 · report
load_embeddings INK-USC/KagNet/models/csqa_dataset.py official repository unverified MIT (permissive) · 9b0d6be3854d5d6d · report
most_frequent INK-USC/KagNet/baselines/ensemble.py official repository unverified MIT (permissive) · 08149da7e3c7cab3 · report
patch_replication_callback INK-USC/KagNet/models/parallel.py official repository unverified MIT (permissive) · e50200dbeffa0133 · report
read_csqa_examples INK-USC/KagNet/baselines/extract_csqa_bert.py official repository unverified MIT (permissive) · ce2f5b8a15be67db · report
replace_wh_word_with_blank INK-USC/KagNet/baselines/run_csqa_bert.py official repository unverified MIT (permissive) · f46246d74e1f7b3e · 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