Многошаговый QA
Related Papers
Repurposing Entailment for Multi-Hop Question Answering Tasks
AbstractQuestion Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple …...
Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
AbstractMulti-hop QA requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. The recently proposed HotpotQA (Yang et al., 2018) dataset is …...
SRLGRN: Semantic Role Labeling Graph Reasoning Network
AbstractThis work deals with the challenge of learning and reasoning over multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to …...
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering
AbstractMulti-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first …...
Latent Reasoning for Low-Resource Question Generation
Multi-hop question generation requires com- plex reasoning and coherent language realiza- tion. Learning a generation model for the problem requires extensive multi-hop question answering (QA) data, which are limited due …...
ReadOnce Transformers: Reusable Representations of Text for Transformers
AbstractWe present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. The resulting representation is reusable across …...
Unsupervised Multi-hop Question Answering by Question Generation
AbstractObtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive. We explore the possibility to train a well-performed multi-hop QA model without referencing any human-labeled multi-hop question-answer pairs, …...
Weakly Supervised Pre-Training for Multi-Hop Retriever
In multi-hop QA, answering complex ques- tions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question detection, document retrieval …...
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
AbstractThis paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization. Specifically, Diff- Explainer allows for the fine-tuning …...
Modeling Multi-hop Question Answering as Single Sequence Prediction
AbstractFusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop …...
VIMQA: A Vietnamese Dataset for Advanced Reasoning and Explainable Multi-hop Question Answering
AbstractVietnamese is the native language of over 98 million people in the world. However, existing Vietnamese Question Answering (QA) datasets do not explore the model’s ability to perform advanced reasoning …...
Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning
AbstractMulti-hop QA requires reasoning over multiple supporting facts to answer the question. However, the existing QA models always rely on shortcuts, e.g., providing the true answer by only one fact, …...
Few-shot Reranking for Multi-hop QA via Language Model Prompting
AbstractWe study few-shot reranking for multi-hop QA (MQA) with open-domain questions. To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which …...