Related papers: Conversational Question Answering over Knowledge G…

Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and…

The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge…

Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data and have been widely studied for link prediction and node classification. One challenge raised by GraphSAGE is how to smartly…

Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings.…

Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words,…

In this paper, we are interested in developing semantic parsers which understand natural language questions embedded in a conversation with a user and ground them to formal queries over definitions in a general purpose knowledge graph (KG)…

The integration of Large Language Models (LLMs) with Graph Neural Networks (GNNs) has recently been explored to enhance the capabilities of Text Attribute Graphs (TAGs). Most existing methods feed textual descriptions of the graph structure…

Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we…

We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jointly learning and…

Users interacting with voice assistants today need to phrase their requests in a very specific manner to elicit an appropriate response. This limits the user experience, and is partly due to the lack of reasoning capabilities of dialogue…

Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few…

This study aims to optimize the existing retrieval-augmented generation model (RAG) by introducing a graph structure to improve the performance of the model in dealing with complex knowledge reasoning tasks. The traditional RAG model has…

Scene graph representations, which form a graph of visual object nodes together with their attributes and relations, have proved useful across a variety of vision and language applications. Recent work in the area has used Natural Language…

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…

Knowledge graph question answering is an important technology in intelligent human-robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge graph. For the multi-relation…

Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs…

Retrieval Augmented Generation (RAG) is an important aspect of conversing with Large Language Models (LLMs) when factually correct information is important. LLMs may provide answers that appear correct, but could contain hallucinated…

Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful…

In this work, we investigate the use of Large Language Models (LLMs) within a graph-based Retrieval Augmented Generation (RAG) architecture for Energy Efficiency (EE) Question Answering. First, the system automatically extracts a Knowledge…

Semantic parsing, as an important approach to question answering over knowledge bases (KBQA), transforms a question into the complete query graph for further generating the correct logical query. Existing semantic parsing approaches mainly…