A Survey on Multi-hop Question Answering and Generation

Mavi, Vaibhav; Jangra, Anubhav; Jatowt, Adam

doi:10.48550/arxiv.2204.09140

Cited by 4 publications

(4 citation statements)

References 143 publications

(368 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the high performance of recent pretrained language models on question-answering (QA) tasks, solving questions that require multi-hop reasoning is still challenging (Mavi et al, 2022). In this paper, we focus on spatial reasoning over text which can be described as inferring the implicit 1 spatial relations from explicit relations 2 described in the text.…”

Section: Introductionmentioning

confidence: 99%

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning

Mirzaee¹,

Faghihi²,

Ning³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.

show abstract

Section: Introductionmentioning

confidence: 99%

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning

Mirzaee¹,

Faghihi²,

Ning³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…The embedding-based multi-hop question [5] answering algorithm mainly relies on the semantic similarity between the question and the relationships in the knowledge graph, and uses the scoring function of the knowledge graph embedding model's triple to construct the answer scoring function. The specific operation methods based on embedding can be divided into two types: semantic analysis-based and graph neural network-based multi-hop question answering inference algorithms.…”

Section: The Embedding-based Multi-hop Knowledge Question Answering (...mentioning

confidence: 99%

Research on multi-hop question answering algorithm based on knowledge graph

Zhao,

Wu,

Tang

et al. 2023

Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023)

View full text Add to dashboard Cite

With the continuous increase of Internet information, the traditional single-hop query is not enough to meet the needs of users. For complex problems, multi-hop KGQA requires reasoning at multiple edges of the KG to arrive at the correct answer. KGS often lack many links, which poses additional challenges for KGQAs especially multi-jump KGQAs. In this paper, the main multi-hop question answering algorithms are divided into two categories: embedded-based multi-hop knowledge question answering reasoning and linked multi-hop knowledge question answering reasoning. The results show that the EmbedKGQA model performs better in prediction reasoning under the knowledge map with missing links by analyzing and comparing the performance of the subgraph matching and embedding prediction models on the Meta and WebQestionSP data sets. Finally, in view of the absence of knowledge graph data in practical application, we propose the development prospect of knowledge graph multi-hop algorithm from the two directions of combining pre-training with knowledge graph and using multi-modal model to expand the data in knowledge graph from multiple dimensions of the same entity.

show abstract

“…The Transformer model, proposed by Vaswani et al [15], has revolutionized natural language processing with its self-attention mechanism, which allows the model to capture long-range dependencies and contextual information efficiently. Transformers have been successfully applied to a variety of NLP tasks, such as machine translation, text summarization [29], and question-answering [30]. Recently, researchers have started exploring the application of Transformer-based models in the knowledge graph domain.…”

Section: Transformer Attention Mechanism and Its Applications In Know...mentioning

confidence: 99%

Efficient Medical Knowledge Graph Embedding: Leveraging Adaptive Hierarchical Transformers and Model Compression

Han-sheng

Yang

et al. 2023

Electronics

View full text Add to dashboard Cite

Medical knowledge graphs have emerged as essential tools for representing complex relationships among medical entities. However, existing methods for learning embeddings from medical knowledge graphs, such as DistMult, RotatE, ConvE, InteractE, JointE, and ConvKB, may not adequately capture the unique challenges posed by the domain, including the heterogeneity of medical entities, rich hierarchical structures, large-scale, high-dimensionality, and noisy and incomplete data. In this study, we propose an Adaptive Hierarchical Transformer with Memory (AHTM) model, coupled with a teacher–student model compression approach, to effectively address these challenges and learn embeddings from a rich medical knowledge dataset containing diverse entities and relationship sets. We evaluate the AHTM model on this newly constructed “Med-Dis” dataset and demonstrate its superiority over baseline methods. The AHTM model achieves substantial improvements in Mean Rank (MR) and Hits@10 values, with the highest MR value increasing by nearly 56% and Hits@10 increasing by 39%. Furthermore, we observe similar performance enhancements on the “FB15K-237” and “WN18RR” datasets. Our model compression approach, incorporating knowledge distillation and weight quantization, effectively reduces the model’s storage and computational requirements, making it suitable for resource-constrained environments. Overall, the proposed AHTM model and compression techniques offer a novel and effective solution for learning embeddings from medical knowledge graphs and enhancing our understanding of complex relationships among medical entities, while addressing the inadequacies of existing approaches.

show abstract

A Survey on Multi-hop Question Answering and Generation

Cited by 4 publications

References 143 publications

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning

Research on multi-hop question answering algorithm based on knowledge graph

Efficient Medical Knowledge Graph Embedding: Leveraging Adaptive Hierarchical Transformers and Model Compression

Contact Info

Product

Resources

About