Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

By Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang. 2019

126 citations recorded by the source corpus.

We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets.Under the assumptions that structured data is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge ofKB entities from a question-related KB sub-graph; then reformulates the question in the latent space and reads the text with the accumulated entity knowledge at hand. The evidence from KB and text are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Retrieval Augmentation Reduces Hallucination in Conversation (2021, background): “These recent neural approaches over unstructured text have overtaken prior methods exploiting the graph structure of knowledge sources (such as hyperlinks in Wikipedia) (Min et al., 2019; Asai et al., 2020; Sun et al., 2019; Xiong et al., 2019), and are an attractive alternative for dialogue.”
Unsupervised Commonsense Question Answering with Self-Talk (2020, background): “, 2017), knowledge base embeddings (Chen et al., 2019; Xiong et al., 2019), hand-crafted rules (Lin et al.”
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model (2019, methodology): “et al. (2019) adopt similar ideas and propose entity-level knowledge enhancement training objectives to incorporate knowledge into pretrained models. Other recent studies (Mihaylov & Frank, 2018; Xiong et al., 2019) leverage external knowledge bases to enhance text-based question answering model”
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data (2020, methodology): “More recently, KAReader (Xiong et al., 2019) proposes to reformulate the questions in latent space by reading retrieved text snippets under KB-incomplete cases.”
Open-Domain Question Answering (2020, background): “…data to guide the retriever or reader stage of existing textual QA systems (Asai et al., 2020; Min et al., 2019b), or (2) how to synthesize information from these two heterogeneous sources and build effective QA models on the combined information (Sun et al., 2018, 2019; Xiong et al., 2019).”
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021, background): “Several works study joint representations of external textual knowledge (e.g., Wikipedia articles) and structured knowledge (e.g., KGs) (Riedel et al., 2013; Toutanova et al., 2015; Xiong et al., 2019; Sun et al., 2019; Wang et al., 2019b).”
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (2021, background): “Some works (Berant et al., 2013; Sun et al., 2018, 2019; Xiong et al., 2019) restrict the answer to be entities in the knowledge graph, while our work focus on more general ODQA setting where the answer can be any words or phrases.”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, methodology): “…from the KG using RL agent (Xiong et al., 2017; Qiu et al., 2020a; Lin et al., 2018; Das et al., 2018) or graph nets (Sun et al., 2018a; 2019a; Xiong et al., 2019), however, these methods rely on heuristics, e.g. , shortest paths between topic entities and answers, most of which are spurious…”
Boosting Visual Question Answering with Context-aware Knowledge Aggregation (2020, methodology): “Inspired by recent works on graph neural networks [30] and knowledge-based question answering [29], we utilize a particular type of graph convolution network to aggregate graph knowledge into anchor entities according to a specific contextual query.”