Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base
By Wen-tau Yih, Ming-Wei Chang, Xiaodong He, Jianfeng Gao. 2015
835 citations recorded by the source corpus.
We propose a novel semantic parsing framework for question answering using a knowledge base. We define a query graph that resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Semantic parsing is reduced to query graph generation, formulated as a staged search problem. Unlike traditional approaches, our method leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem. By applying an advanced entity linking system and a deep convolutional neural network model that matches questions and predicate sequences, our system outperforms previous methods substantially, and achieves an F1 measure of 52.5% on the WEBQUESTIONS dataset.
Subfields: Artificial Intelligence, Natural Language Processing, Question Answering & Reading Comprehension
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
- Mohit Bansal
- Percy Liang
- Jianfeng Gao
- Luke S. Zettlemoyer
- Caiming Xiong
- Yoshua Bengio
- Graham Neubig
- Richard Socher
In Natural Language Processing
- Mohit Bansal
- Percy Liang
- Luke S. Zettlemoyer
- Caiming Xiong
- Hannaneh Hajishirzi
- Jianfeng Gao
- Jonathan Berant
- Wen-tau Yih
In Question Answering & Reading Comprehension
- Anton van den Hengel
- Damien Teney
- Mo Yu
- Ming-Wei Chang
- Haitian Sun
- Xiaodong He
- William W. Cohen
- Qi Wu
Citations in the corpus
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, background): “(2) KB-QA systems (Bast & Haussmann, 2015; Yih et al., 2015; Xu et al., 2016) sometimes use text evidence to enhance answer re-ranking, where the features are also extracted on the pair of question and a single-passage but ignored the union information among multiple passages.”
- Key-Value Memory Networks for Directly Reading Documents (2016, methodology): “, 2008) have led to the development of a new class of QA methods based on semantic parsing (Berant et al., 2013; Kwiatkowski et al., 2013; Fader et al., 2014; Yih et al., 2015) that can return precise answers to complicated compositional questions.”
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (2019, background): “Knowledge-based question answering has received much more attention in the NLP community (e.g., [5, 50, 49, 6, 40, 28, 7]).”
- Neural Approaches to Conversational AI (2018, neutral): “Question Answering (QA), deep semantics and dialogue with intelligent agents. Recent years have seen the rise of a small industry of tutorials and survey papers on deep learning and dialogue systems. Yih et al. (2015b, 2016); Gao (2017) reviewed deep learning approaches for a wide range of IR and NL”
- Sentence Embedding Alignment for Lifelong Relation Extraction (2019, methodology): “, 2013) and question answering (Yih et al., 2015; Yu et al., 2017).”
- Search-based Neural Structured Learning for Sequential Question Answering (2017, methodology): “DynSP is inspired by STAGG, a search-based semantic parser (Yih et al., 2015), as well as the dynamic neural module network (DNMN) of Andreas et al. (2016).”
- Neural Semantic Parsing with Type Constraints for Semi-Structured Tables (2017, background): “Second, they do not address entity linking, which is a critical subproblem of semantic parsing (Yih et al., 2015).”
- Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge (2020, methodology): “, 2019) and WebQuestionsSP (Yih et al., 2015) (See table 1 for data statistics).”
- Learning executable semantic parsers for natural language understanding (2016, background): “Due to their empirical success, there has been a recent surge of interest in using recurrent neural networks and their extensions for solving NLP tasks such as machine translation and question answering [35, 31].”
- The Value of Semantic Parse Labeling for Knowledge Base Question Answering (2016, methodology): “in (Yih et al., 2015).”
- Improved Neural Relation Detection for Knowledge Base Question Answering (2017, methodology): “Knowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples (Berant et al., 2013; Yao et al., 2014; Bordes et al., 2015; Bast and Haussmann, 2015; Yih et al., 2015; Xu et al., 2016).”
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data (2020, methodology): “These methods adopts KB-only datasets (Berant et al., 2013; Yih et al., 2015; Talmor and Berant, 2018) to simulate a hybrid setting by randomly masking KB triples and replace them with text corpus.”
- QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships (2018, background): “In prior semantic parsing work, entity linking is relatively straightforward: simple string-matching heuristics are often sufficient (Jia and Liang 2016; Dong and Lapata 2016), or an external entity linking system can be used (Yih et al. 2015; Xu et al. 2016).”
- Natural Language to Structured Query Generation via Meta-Learning (2018, background): “…studied in natu-ral language processing research (Zettlemoyer and Collins, 2005; Giordani and Moschitti, 2010; Artzi and Zettlemoyer, 2011; Berant et al., 2013; Vla-chos and Clark, 2014; Yih et al., 2014, 2015; Wang et al., 2015; Golub and He, 2016; Iyer et al., 2017; Krishnamurthy et al., 2017).”
- Collective Entity Disambiguation with Structured Gradient Tree Boosting (2018, background): “…role in the language understanding pipeline, underlying a variety of downstream applications such as relation extraction (Mintz et al., 2009; Riedel et al., 2010), knowledge base population (Ji and Grishman, 2011; Dredze et al., 2010), and question answering (Berant et al., 2013; Yih et al., 2015).”