Case-based Reasoning for Natural Language Queries over Knowledge Bases

  title={Case-based Reasoning for Natural Language Queries over Knowledge Bases},
  author={Rajarshi Das and Manzil Zaheer and Dung Ngoc Thai and Ameya Godbole and Ethan Perez and Jay Yoon Lee and Lizhen Tan and Lazaros Polymenakos and Andrew McCallum},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
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… 

CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases

This work proposes a case-based reasoning approach, CBR-iKB, for knowledge base question answering (KBQA) with incomplete-KB as the main focus, and ensembles decisions from multiple reasoning chains with a novel nonparametric reasoning algorithm.

Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases

GMT-KBQA is proposed, a Generation-based KBQA method via Multi-Task learning, to better retrieve and utilize auxiliary information and achieves state-of-the-art results on both ComplexWebQuestions and WebQuestionsSP datasets.

Machine Reading Comprehension using Case-based Reasoning

An accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI, and finds CBR-MRC to be robust to these variations while performance using fully-parametric methods drops.

End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion

This framework addresses a fundamental question on whether CBR methodology can be utilized to improve deep learning models and generates more valid, informative, and novel knowledge than the state-of-the-art COMET model for CKBC in both the fully supervised and few-shot settings.

Case-Based Abductive Natural Language Inference

This paper presents Case-Based Abductive Natural Language Inference (CB-ANLI), a model that addresses unseen inference problems by analogical transfer of prior explanations from similar examples that can be effectively integrated with sparse and dense pre-trained encoders to improve multi-hop inference.

Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

CBR-SUBG can answer queries requiring subgraph reasoning patterns and performs competitively with the best models on several KBQA benchmarks and proposes an adaptive subgraph collection strategy to select a query-specific compact subgraph, allowing the model to scale to full Freebase KB containing billions of facts.

Knowledge Base Question Answering via Structured Query Generation using Question domain

A new KBQA framework based on similar question domains is proposed that can handle complex question answering and has a strong reasoning ability and has resulted in new state-of-the-art performance on WebQSP and CWQ datasets.

Complex Knowledge Base Question Answering: A Survey

A review of recent advances on KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations.

Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions

When answering natural language questions over knowledge bases (KBs), incompleteness in the KB can naturally lead to many questions being unanswerable. While answerability has been explored in other

DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases

This work proposed a novel framework DecAF that jointly generates both logical forms and direct answers, and then combines the merits of them to get the final answers, which achieves new state-of-the-art accuracy on WebQSP, FreebaseQA, and GrailQA benchmarks.

Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion

The effectiveness of the case-based reasoning system in an "open-world" setting where new entities arrive in an online fashion is demonstrated, significantly outperforming state-of-the-art approaches and nearly matching the best offline method.

A Simple Approach to Case-Based Reasoning in Knowledge Bases

We present a surprisingly simple yet accurate approach to reasoning in knowledge graphs (KGs) that requires \emph{no training}, and is reminiscent of case-based reasoning in classical artificial

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

A novel model is proposed, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and Knowledge Bases entities and relations that is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting.

The Web as a Knowledge-Base for Answering Complex Questions

This paper proposes to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers, and empirically demonstrates that question decomposition improves performance from 20.8 precision@1 to 27.5 precision @1 on this new dataset.

Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

This paper presents a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision and leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases.

Knowledge Base Question Answering with Topic Units

This paper proposes to perform topic unit linking where topic units cover a wider range of units of a KB, and uses a generation-and-scoring approach to gradually refine the set of topic units.

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

PullNet is described, an integrated framework for learning what to retrieve and reasoning with this heterogeneous information to find the best answer in an open-domain question answering setting.

Reasoning With Neural Tensor Networks for Knowledge Base Completion

An expressive neural tensor network suitable for reasoning over relationships between two entities given a subset of the knowledge base is introduced and performance can be improved when entities are represented as an average of their constituting word vectors.

Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches

An overview of the foundational issues related to case-based reasoning is given, some of the leading methodological approaches within the field are described, and the current state of the field is exemplified through pointers to some systems.

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

It is found that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster, and a new QA-pair retriever, RePAZ, is introduced to complement PAQ.