{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sequence-to-sequence-knowledge-graph-1","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","arxiv_id":"2203.10321","date":"2022-03-19","proceeding":"ACL 2022 5","authors":["Apoorv Saxena","Adrian Kochsiek","Rainer Gemulla"],"abstract":"Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each entity in the graph, which results in large model sizes on real-world graphs with millions of entities. For downstream tasks these atomic entity representations often need to be integrated into a multi stage pipeline, limiting their utility. We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model obtaining state-of-the-art results for KG link prediction and incomplete KG question answering. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding. Such a simple but powerful method reduces the model size up to 98% compared to conventional KGE models while keeping inference time tractable. After finetuning this model on the task of KGQA over incomplete KGs, our approach outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.","url_abs":"https://arxiv.org/abs/2203.10321v1","url_pdf":"https://arxiv.org/pdf/2203.10321v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sequence-to-sequence-knowledge-graph-1","repo_url":"https://github.com/apoorvumang/kgt5","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-wikidata5m","task":"Link Prediction","dataset":"Wikidata5M","model":"KGT5 ComplEx Ensemble","rank_in_archive_order":6,"of":14,"metrics":{"Hits@1":"0.282","Hits@10":"0.426","Hits@3":"0.362","MRR":"0.336"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wikidata5m","task":"Link Prediction","dataset":"Wikidata5M","model":"KGT5","rank_in_archive_order":8,"of":14,"metrics":{"Hits@1":"0.267","Hits@10":"0.365","Hits@3":"0.318","MRR":"0.300"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.10321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10321"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/apoorvumang/kgt5","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3e6ba40bc8b3abdd","entry":"eval","repo":"apoorvumang/kgt5","repo_kind":"official","path":"eval_accelerate.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/eval_accelerate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e6ba40bc8b3abdd"}},{"code_sha256_prefix":"18abe939ed3719ed","entry":"getGreedyOutput","repo":"apoorvumang/kgt5","repo_kind":"official","path":"eval_accelerate.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/eval_accelerate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"18abe939ed3719ed"}},{"code_sha256_prefix":"0e293c88fb992f3c","entry":"load_accelerator_model","repo":"apoorvumang/kgt5","repo_kind":"official","path":"utils_accelerate.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/utils_accelerate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e293c88fb992f3c"}},{"code_sha256_prefix":"10dc27d79a090adc","entry":"removeModuleFromKeys","repo":"apoorvumang/kgt5","repo_kind":"official","path":"utils_accelerate.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/utils_accelerate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10dc27d79a090adc"}},{"code_sha256_prefix":"2c9a7c494e855d9d","entry":"removePadding","repo":"apoorvumang/kgt5","repo_kind":"official","path":"eval_models.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/eval_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c9a7c494e855d9d"}},{"code_sha256_prefix":"69d92df11258fee4","entry":"split_example","repo":"apoorvumang/kgt5","repo_kind":"official","path":"make_dataset.py","file_url":"https://github.com/apoorvumang/kgt5/blob/HEAD/make_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69d92df11258fee4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}