Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs
Recent years have seen increasingly complex question-answering on knowledge bases (KBQA) involving logical, quantitative, and comparative reasoning over KB subgraphs. Neural Program Induction (NPI) is a pragmatic approach toward modularizing the reasoning process by translating a complex natural language query into a multi-step executable program. While NPI has been commonly trained with the {}{}gold{'}{'} program or its sketch, for realistic KBQA applications such gold programs are expensive to obtain. There, practically only natural language queries and the corresponding answers can be provided for training. The resulting combinatorial explosion in program space, along with extremely sparse rewards, makes NPI for KBQA ambitious and challenging. We present Complex Imperative Program Induction from Terminal Rewards (CIPITR), an advanced neural programmer that mitigates reward sparsity with auxiliary rewards, and restricts the program space to semantically correct programs using high-level constraints, KB schema, and inferred answer type. CIPITR solves complex KBQA considerably more accurately than key-value memory networks and neural symbolic machines (NSM). For moderately complex queries requiring 2- to 5-step programs, CIPITR scores at least 3{\mbox{$\times$}} higher F1 than the competing systems. On one of the hardest class of programs (comparative reasoning) with 5{--}10 steps, CIPITR outperforms NSM by a factor of 89 and memory networks by 9 times.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language QueriesProgram inductionQuestion AnsweringSimilar Papers 제목 키워드 기반
Program Transfer for Answering Complex Questions over Knowledge Bases
Program induction for answering complex questions over knowledge bases (KBs) aims to decompose a question into a multi-step program, whose execution against the KB produces the final answer. Learning to induce programs …
Program inductionProgram Transfer for Answering Complex Questions over Knowledge Bases
Program induction for answering complex questions over knowledge bases (KBs) aims to decompose a question into a multi-step program, whose execution against the KB produces the final answer. Learning to induce programs r…
Program inductionSemantic ParsingQuerying in the Age of Graph Databases and Knowledge Graphs
Graphs have become the best way we know of representing knowledge. The computing community has investigated and developed the support for managing graphs by means of digital technology. Graph databases and knowledge grap…
Knowledge GraphsManagementKB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases
Program induction (PI) has become a promising paradigm for using knowledge bases (KBs) to help large language models (LLMs) answer complex knowledge-intensive questions. Nonetheless, PI typically relies on a large number…
Program inductionSelf-Supervised LearningCost-Based Semantics for Querying Inconsistent Weighted Knowledge Bases
In this paper, we explore a quantitative approach to querying inconsistent description logic knowledge bases. We consider weighted knowledge bases in which both axioms and assertions have (possibly infinite) weights, whi…