Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning
Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different types, harboring inherently different characteristics, e.g., difficulty level. This paper proposes a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions. Our method quickly and effectively adapts the meta-learned programmer to new questions based on the most similar questions retrieved from the training data. The meta-learned policy is then used to learn a good programming policy, utilizing the trial trajectories and their rewards for similar questions in the support set. 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. We have released our code at https://github.com/DevinJake/MRL-CQA.
Code (1)
Tasks
Knowledge Base Question AnsweringMeta Reinforcement LearningProgram inductionQuestion Answeringreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the …
Question AnsweringLogical ReasoningKnowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering
Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge migh…
Graph Question AnsweringLanguage ModelingLanguage ModellingQuestion AnsweringPrompting-based Synthetic Data Generation for Few-Shot Question Answering
Although language models (LMs) have boosted the performance of Question Answering, they still need plenty of data. Data annotation, in contrast, is a time-consuming process. This especially applies to Question Answering,…
Question AnsweringSynthetic Data GenerationMulti-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering
Commonsense question answering (QA) research requires machines to answer questions based on commonsense knowledge. However, this research requires expensive labor costs to annotate data as the basis of research, and mode…
Contrastive LearningKnowledge GraphsQuestion AnsweringZero-Shot Complex Question-Answering on Long Scientific Documents
With the rapid development in Transformer-based language models, the reading comprehension tasks on short documents and simple questions have been largely addressed. Long documents, specifically the scientific documents …
Answer Generationdocument understandingQuestion AnsweringReading Comprehension