Multi-Hop Reasoning

AbstractOur goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and …...

AbstractLarge scale knowledge graphs (KGs) such as Freebase are generally incomplete. Reasoning over multi-hop (mh) KG paths is thus an important capability that is needed for question answering or other …...

AbstractState-of-the-art models for knowledge graph completion aim at learning a fixed embedding representation of entities in a multi-relational graph which can generalize to infer unseen entity relationships at test time. …...

AbstractIn this paper, we propose a novel graph neural network with generated parameters (GP-GNNs). The parameters in the propagation module, i.e. the transition matrices used in message passing procedure, are …...

AbstractRule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to …...

AbstractAdversarial evaluation stress-tests a model’s understanding of natural language. Because past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human- in-the-loop adversarial …...

AbstractLearning multi-hop reasoning has been a key challenge for reading comprehension models, leading to the design of datasets that explicitly focus on it. Ideally, a model should not be able …...

AbstractMulti-hop reasoning has been widely studied in recent years to seek an effective and interpretable method for knowledge graph (KG) completion. Most previous reasoning methods are designed for dense KGs …...

AbstractEnd-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how to effectively incorporate external knowledge bases …...

AbstractIn this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes …...

AbstractRecently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we …...

AbstractMulti-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships. We extend existing works to consider a …...

AbstractQuestion generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence to sequence neural …...

AbstractKnowledge graphs are essential for numerous downstream natural language processing applications, but are typically incomplete with many facts missing. This results in research efforts on multi-hop reasoning task, which can …...

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 …...

AbstractRecent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. However, the quality of most existing models’ generated response is still limited, …...

AbstractMulti-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, …...

Multi-hop reasoning is an effective and ex- plainable approach to predicting missing facts in Knowledge Graphs (KGs). It usually adopts the Reinforcement Learning (RL) framework and searches over the KG …...

AbstractMultihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, requires …...

AbstractOne of the key challenges of knowledge base question answering (KBQA) is the multi-hop reasoning. Since in different hops, one attends to different parts of question, it is important to …...

AbstractDespite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex …...

AbstractMulti-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable …...

AbstractGenerative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving relevant evidence (the open-book setting). Generative …...

AbstractEntities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a pan is hot) …...

AbstractMulti-hop reasoning, a prevalent approach for query answering, aims at inferring new facts along reasonable paths over a knowledge graph. Reinforcement learning methods can be adopted by formulating the problem …...