Graph Sequential Network for Reasoning over Sequences
Recently Graph Neural Network (GNN) has been applied successfully to various NLP tasks that require reasoning, such as multi-hop machine reading comprehension. In this paper, we consider a novel case where reasoning is needed over graphs built from sequences, i.e. graph nodes with sequence data. Existing GNN models fulfill this goal by first summarizing the node sequences into fixed-dimensional vectors, then applying GNN on these vectors. To avoid information loss inherent in the early summarization and make sequential labeling tasks on GNN output feasible, we propose a new type of GNN called Graph Sequential Network (GSN), which features a new message passing algorithm based on co-attention between a node and each of its neighbors. We validate the proposed GSN on two NLP tasks: interpretable multi-hop reading comprehension on HotpotQA and graph based fact verification on FEVER. Both tasks require reasoning over multiple documents or sentences. Our experimental results show that the proposed GSN attains better performance than the standard GNN based methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Fact VerificationGraph Neural NetworkMachine Reading ComprehensionMulti-Hop Reading ComprehensionReading ComprehensionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning
Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs). However, applying LLMs to graphs requires linearizing their structure into sequences, introducing distortion rooted in the…
Prompt EngineeringDynamic Graph Neural Networks for Sequential Recommendation
Modeling user preference from his historical sequences is one of the core problems of sequential recommendation. Existing methods in this field are widely distributed from conventional methods to deep learning methods. H…
Graph AttentionGraph Neural NetworkLink PredictionSequential RecommendationSequential Recommendation with Graph Neural Networks
Sequential recommendation aims to leverage users' historical behaviors to predict their next interaction. Existing works have not yet addressed two main challenges in sequential recommendation. First, user behaviors in t…
Graph Neural NetworkMetric LearningSequential RecommendationMementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static inf…
Language ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelSTEPS: A Benchmark for Order Reasoning in Sequential Tasks
Various human activities can be abstracted into a sequence of actions in natural text, i.e. cooking, repairing, manufacturing, etc. Such action sequences heavily depend on the executing order, while disorder in action se…
In-Context Learning