Manzil Zaheer, Ethan Perez, Andrew Mccallum, Rajarshi Das, Ameya Godbole, Jay-Yoon Lee, Dung Thai, Lizhen Tan, Lazaros Polymenakos
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions -a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach (CBR-KBQA) for question answering over large knowledge bases. CBR-KBQA consists of a nonparametric memory that stores cases (question and logical forms) and a parametric model that can generate a logical form for a new question by retrieving cases that are relevant to it. On several KBQA datasets that contain complex questions, CBR-KBQA achieves competitive performance. For example, on the COMPLEXWEBQUESTIONS dataset, CBR-KBQA outperforms the current state of the art by 11% on accuracy. Furthermore, we show that CBR-KBQA is capable of using new cases without any further training: by incorporating a few human-labeled examples in the case memory, CBR-KBQA is able to successfully generate logical forms containing unseen KB entities as well as relations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.08762")
get_code_for_paper("2104.08762")
have("2104.08762")
Connect an agent — have() is free.