Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs

Abstract

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× 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. 1

TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph

“…For the label form, which is also known as "KBQA" or "KGQA", existing methods fall into two categories: information retrieval (Miller et al, 2016;Xu et al, 2019;Zhao et al, 2019b;Saxena et al, 2020) and semantic parsing (Berant et al, 2013;Yih et al, 2015;Liang et al, 2017;Guo et al, 2018;Saha et al, 2019). The former retrieves answer from KG by learning representations of question and graph, while the latter queries answer by parsing the question into logical form.…”

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

“…Knowledge-guided generation. There is a growing interest in exploiting external knowledge to generate informative responses for applications such as dialog systems (He et al, 2017; and question answering (Das et al, 2017;Saha et al, 2019). Previous approaches inject knowl-edge through topic phrases , structured knowledge graphs and unstructured texts (Dinan et al, 2019;Hua et al, 2019).…”

Sensitivity Analysis for Causal Mediation through Text: an Application to Political Polarization

“…Much of the prior work on text in causal settings has focused on text as a confounder, e.g. Saha et al (2019) andRoberts et al (2020). See Keith et al (2020) for a full overview of the text-as-confounder literature.…”