[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273689-105":59,"doc-detail-273689-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","sabet-qa-temporal-knowledge-graph-question-answering","SABET-QA - Temporal Knowledge Graph Question Answering","","Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet embedding-based pipelines often fail on multi-step queries because they process evidence in a single pass. SABET-QA addresses this by iteratively refining reasoning states across multiple hops, using bidirectional entity–temporal scoring and a slot-aware contextualization module that matches question semantics with temporal KG embeddings. Differentiable working memory supports progressive hypothesis refinement, and auxiliary temporal boundaries provide coarse supervision. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions show consistent gains over strong baselines, especially for complex temporal queries.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/sabet-qa-temporal-knowledge-graph-question-answering/273689/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/sabet-qa-temporal-knowledge-graph-question-answering/273689.png","ImageObject",300,407,{"name":92,"@type":93},"River Wang","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why do existing embedding-based TKGQA methods struggle with complex multi-step questions?","Question",{"text":113,"@type":114},"They rely on single-pass reasoning pipelines, which cannot revisit or correct intermediate errors when multi-hop temporal evidence is needed.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What are the three gaps identified in prior TKGQA approaches?",{"text":118,"@type":114},"Single-shot reasoning for complex queries, ambiguous relation directionality (head vs tail), and context-dependent ambiguity where the same mention can refer to different entity types.",{"name":120,"@type":111,"acceptedAnswer":121},"How does SABET-QA improve temporal KG question answering?",{"text":122,"@type":114},"It uses slot-aware contextualization, bidirectional entity–temporal scoring to handle directionality, and iterative multi-hop reasoning with differentiable working memory for progressive hypothesis refinement.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},273689,1789472500,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},1099514067438,"https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542","SABET-QA: Temporal Knowledge Graph Question Answering  \nBrahim Touayouch1,2,* Mirette Moawad1,* Dmitry Akulov1,*  \n1 QuickSort Research, Paris, France  \n2ENS Paris-Saclay, École Polytechnique, France  \nContact: [brahim.touayouch.2022@polytechnique.org](brahim.touayouch.2022@polytechnique.org)  \narXiv : 2608 .20083v 1 [cs .CL] 20 Aug 2026  \nAbstract  \nQuestion Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning overtime-sensitive facts, yet existing embeddingbased methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries.  \n1 Introduction  \nThe proliferation of large-scale Knowledge Graphs (KGs) such as Wikidata (Vrandei and Krötzsch, 2014), Freebase (Bollacker et al., 2008) and YAGO (Suchanek et al., 2007) has made Question Answering over KGs (KGQA) a crucial interface for accessing structured knowledge. However, realworld facts evolve over time, motivating Temporal Knowledge Graphs (TKGs) where a fact is represented as a quintuple (s, r, o,[ts, te]) . Temporal KGQA (TKGQA), the task of answering questions over such dynamic graphs, is essential for reasoning about a changing world.  \nDespite progress in static KGQA (Jiang et al., 2023 ; Saxena et al., 2020), TKGQA presents unique challenges. Natural language questions contain explicit temporal constraints (e.g.,“Who  \n*  \nWork conducted at QuickSort Research, Paris, France ([https://www.quicksort.fr](https://www.quicksort.fr)). Correspondence to:  \nmohamed@quicksort.fr or personal emails.  \nwas the president in 2008?”) or implicit compositional ones (e.g., “Who was the president after Obama?”) . Embedding-based approaches like CronKGQA (Saxena et al., 2021) reduce simple queries to link prediction, but struggle with complex reasoning. Later work such as TempoQR (Mavromatis et al., 2021) enriches question representations with contextualized time and entity information, yet these methods still process questions in a single forward pass, lacking iterative refinement and effective aggregation of distributed temporal evidence.  \nWe identify three specific gaps in existing TKGQA methods:  \n1. Single-Shot Reasoning: Complex questions require sequential deduction (e.g., finding an entity, locating its tenure, then identifying the successor) . Single-pass models cannot revisit or correct intermediate errors.  \n2. Ambiguous Directionality: Questions mention entities without specifying their grammatical role (head or tail) in the relation. Existing models often assume a fixed direction, leading to incorrect scoring.  \n3. Context-Dependent Ambiguity: Entities like“Washington” may refer to a person, a city, or a state depending on context. Lexical matching or fixed entity linking fails when the same mention carries different meanings.  \nTo address these gaps, we propose SABETQA, a temporal KGQA framework combining slot-aware contextualization, bidirectional entity– temporal scoring, and iterative multi-hop reasoning.  \nWhen coarse temporal hints are available, SABETQA exploits them as additional supervision. A full architectural description is provided in Section 3.3. Our contributions are summarized as follows:  \n• We propose SABET-QA, an iterative temporal KGQA framework that progressively refines predictions through a working-memory-based multi-  \nhop reasoning process.  \n• We introduce bidirectional entity–temporal scoring to address head–tail ambiguity and imp","cbCaik3FPsLbmMwv","https://ap.wps.com/l/cbCaik3FPsLbmMwv","pdf",566061,17,"English","# Introduction\n## Gaps in existing TKGQA methods\n# Related Work\n## Temporal Knowledge Graph Representations\n## Knowledge Graph Question Answering","[{\"question\":\"Why do existing embedding-based TKGQA methods struggle with complex multi-step questions?\",\"answer\":\"They rely on single-pass reasoning pipelines, which cannot revisit or correct intermediate errors when multi-hop temporal evidence is needed.\"},{\"question\":\"What are the three gaps identified in prior TKGQA approaches?\",\"answer\":\"Single-shot reasoning for complex queries, ambiguous relation directionality (head vs tail), and context-dependent ambiguity where the same mention can refer to different entity types.\"},{\"question\":\"How does SABET-QA improve temporal KG question answering?\",\"answer\":\"It uses slot-aware contextualization, bidirectional entity–temporal scoring to handle directionality, and iterative multi-hop reasoning with differentiable working memory for progressive hypothesis refinement.\"}]","SABET-QA - Temporal Knowledge Graph Question Answering | PDF",43]