Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
By Apoorv Saxena, Aditay Tripathi, Partha P. Talukdar. 2020
644 citations recorded by the source corpus.
Knowledge Graphs (KG) are multi-relational graphs consisting of entities as nodes and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) task is to answer natural language queries posed over the KG. Multi-hop KGQA requires reasoning over multiple edges of the KG to arrive at the right answer. KGs are often incomplete with many missing links, posing additional challenges for KGQA, especially for multi-hop KGQA. Recent research on multi-hop KGQA has attempted to handle KG sparsity using relevant external text, which isn’t always readily available. In a separate line of research, KG embedding methods have been proposed to reduce KG sparsity by performing missing link prediction. Such KG embedding methods, even though highly relevant, have not been explored for multi-hop KGQA so far. We fill this gap in this paper and propose EmbedKGQA. EmbedKGQA is particularly effective in performing multi-hop KGQA over sparse KGs. EmbedKGQA also relaxes the requirement of answer selection from a pre-specified neighborhood, a sub-optimal constraint enforced by previous multi-hop KGQA methods. Through extensive experiments on multiple benchmark datasets, we demonstrate EmbedKGQA’s effectiveness over other state-of-the-art baselines.
Subfields: Artificial Intelligence, Question Answering & Reading Comprehension, Knowledge Graphs & Representation
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
- Percy Liang
- Luke S. Zettlemoyer
- Jianfeng Gao
- Caiming Xiong
- Mohit Bansal
- Graham Neubig
- Richard Socher
- Noah A. Smith
In Question Answering & Reading Comprehension
- Soumen Chakrabarti
- Partha P. Talukdar
- Apoorv Saxena
- Haitian Sun
- Caiming Xiong
- Xiaodong Liu
- Ji-rong Wen
- Jure Leskovec
In Knowledge Graphs & Representation
- Soumen Chakrabarti
- Partha P. Talukdar
- Apoorv Saxena
- Noah A. Smith
- Bo Dai
- Jure Leskovec
- Xindong Wu
- Jianfeng Gao
Citations in the corpus
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, methodology): “Structured knowledge encoding has been widely explored (Bogin et al., 2019; Lin et al., 2019; Agar-wal et al., 2020; Saxena et al., 2020; Yasunaga and Liang, 2020; Yasunaga et al., 2022; and others detailed in Section 2).”
- ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering (2021, result): “We compare our model with previous state-of-the-art models on GrailQA (Lan and Jiang, 2020; Gu et al., 2021) and WebQSP (Liang et al., 2017; Sun et al., 2019; Saxena et al., 2020; Lan and Jiang, 2020).”
- Question Answering Over Temporal Knowledge Graphs (2021, methodology): “…between test/train entities and test/train question paraphrases, leading to suspiciously high performance on baseline methods even with partial KG data (Saxena et al., 2020), which suggests that models that apparently perform well are not necessarily performing the desired reasoning over the KG.”
- Graph Retrieval-Augmented Generation: A Survey (2024, positive): “Some approaches unify retrievers and generators into a single model, typically LLMs, and train them with both retrieval and generation objectives simultaneously [102].”
- LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, methodology): “Compared with non-parsing methods (Sun et al., 2019a; Saxena et al., 2020), these models achieve better empirical results and interpretability since the underlying structured query captures the reasoning process.”
- Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “EmbedKGQA selects the entity with the highest score as the answer.”
- Simulations approaching data: cortical slow waves in inferred models of the whole hemisphere of mouse (2021, neutral): “the dynamic organization of functional cortical modules in different cognitive processes [52, 53].”
- Knowledge Graphs: Opportunities and Challenges (2023, background): “Saxena et al. (2020) proposed EmbedKGQA to achieve multi-hop question answering over sparse knowledge graphs (such as knowledge graphs with missing edges).”
- Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, background): “Knowledge graph question answering (KGQA) aims to find answers to natural language questions based on the structured facts stored in knowledge graphs [233], [234].”
- HittER: Hierarchical Transformers for Knowledge Graph Embeddings (2020, methodology): “Such KGE methods are conceptually simple and can be applied to tasks like factoid question answering (Saxena et al., 2020) and language modeling (Peters et al., 2019).”
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (2023, methodology): “EmbedKGQA (Saxena et al., 2020) and NSM (He et al., 2021) utilize the sequential model to mimic the multi-hop reasoning process.”
- RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (2021, methodology): “, 2018), or iteratively built using learned models (Sun et al., 2019; Shi et al., 2021; Cohen et al., 2020; Saxena et al., 2020).”
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data (2023, methodology): “For KGQA, we select KV-Mem (Miller et al., 2016), GragtNet (Sun et al., 2018), EmbedKGQA (Saxena et al., 2020), NSM (He et al., 2021), and UniKGQA (Jiang et al., 2023).”
- Exploiting Reasoning Chains for Multi-hop Science Question Answering (2021, methodology): “…explore the effectiveness of KG by either automatically constructing the graph using named entity or semantic role labeling (Qiu et al., 2019; Bosselut et al., 2019; Fang et al., 2020; Chen et al., 2019) or resorting to existing KG (Saxena et al., 2020; Zhang et al., 2020; Yasunaga et al., 2021).”