Knowledge Base Question Answering

46 papers with code • 5 benchmarks • 9 datasets

Knowledge Base Q&A is the task of answering questions from a knowledge base.

( Image credit: Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering )

Most implemented papers

Neural Machine Translation for Query Construction and Composition

LiberAI/NSpM 27 Jun 2018

Research on question answering with knowledge base has recently seen an increasing use of deep architectures.

Knowledge Base Question Answering via Encoding of Complex Query Graphs

lkq1992yeah/CompQA EMNLP 2018

Answering complex questions that involve multiple entities and multiple relations using a standard knowledge base is an open and challenging task.

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering

wudapeng268/KBQA-Adapter ACL 2019

However, one critical problem is that current approaches only get high accuracy for questions whose relations have been seen in the training data.

Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering

siat-nlp/TransDG 16 Dec 2019

In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation.

RuBQ: A Russian Dataset for Question Answering over Wikidata

vladislavneon/RuBQ 21 May 2020

The paper presents RuBQ, the first Russian knowledge base question answering (KBQA) dataset.

Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

DevinJake/MRL-CQA EMNLP 2020

Our method achieves state-of-the-art performance on the CQA dataset (Saha et al., 2018) while using only five trial trajectories for the top-5 retrieved questions in each support set, and metatraining on tasks constructed from only 1% of the training set.

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

DevinJake/MARL 29 Oct 2020

However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive.

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

dki-lab/GrailQA 16 Nov 2020

To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64, 331 questions, GrailQA, and provide evaluation settings for all three levels of generalization.