Semantic Parsing for Single-Relation Question Answering

By Wen-tau Yih, Xiaodong He, Christopher Meek. 2014

420 citations recorded by the source corpus.

We develop a semantic parsing framework based on semantic similarity for open domain question answering (QA). We focus on single-relation questions and decompose each question into an entity mention and a relation pattern. Using convolutional neural network models, we measure the similarity of entity mentions with entities in the knowledge base (KB) and the similarity of relation patterns and relations in the KB. We score relational triples in the KB using these measures and select the top scoring relational triple to answer the question. When evaluated on an open-domain QA task, our method achieves higher precision across different recall points compared to the previous approach, and can improve F1 by 7 points.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Memory Networks (2014, background): “The difficulty of the task is that multiple sentences have to be used to do inference when asking where an object is, e.g. to answer where is the milk in Figure 1 one has to understand the meaning of the actions “picked up” and “left” and the influence of their relative order.”
Convolutional Neural Networks for Sentence Classification (2014, background): “…for computer vision, CNN models have subsequently been shown to be effective for NLP and have achieved excellent results in semantic parsing (Yih et al., 2014), search query retrieval (Shen et al., 2014), sentence modeling (Kalch-brenner et al., 2014), and other traditional NLP tasks…”
Stacked Attention Networks for Image Question Answering (2015, background): “Unlike pure language based QA systems that have been studied extensively in the NLP community [28, 14, 4, 31, 3, 32], image QA systems are designed to automatically answer natural language questions according to the content of a reference image.”
Neural Variational Inference for Text Processing (2015, background): “One of the popular streams is mapping factoid questions with answer triples in the knowledge base (Bordes et al., 2014a;b; Yih et al., 2014).”
Natural Language Processing for EHR-Based Computational Phenotyping (2018, methodology): “Deep learning has been applied on various NLP applications, including semantic representation [146], semantic analysis [147, 148], information retrieval [149, 150], entity recognition [151, 152], relation extraction [153-156], and event detection [157, 158].”
Deep Learning for Answer Sentence Selection (2014, methodology): “[23], who constructed models for single-relation question answering with a knowl edge base of triples.”
Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering (2016, background): “…such abilities, including neural tensor networks (Socher et al., 2013), recursive networks (Iyyer et al., 2014), convolution neural networks (Yih et al., 2014; Dong et al., 2015; Yin et al., 2015), attention models (Hermann et al., 2015; Yin et al., 2015; Santos et al., 2016), and memories…”
Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, methodology): “This general framework for relationship modeling also applies to the recent deep-structured semantic model (Huang et al., 2013; Shen et al., 2014a;b; Gao et al., 2014; Yih et al., 2014), which learns the relevance or a single relation between a pair of word sequences.”
Question Answering over Freebase with Multi-Column Convolutional Neural Networks (2015, methodology): “Yih et al. (2014) used convolutional neural networks to answer single-relation questions on R E V ERB (Fader et al., 2011).”
Improved Neural Relation Detection for Knowledge Base Question Answering (2017, methodology): “…KBQA system: (a) a single-relation question, which can be answered with a single < head-entity, relation, tail-entity > KB tuple (Fader et al., 2013; Yih et al., 2014; Bordes et al., 2015); and (b) a more complex case, where some constraints need to be handled for multiple entities in the question.”
Learning What is Essential in Questions (2017, methodology): “Inference based QA systems operating on (semi-)structured knowledge formalisms have also demonstrated complementary strengths, by using optimization formalisms such as Semantic Parsing (Yih et al., 2014), Integer Linear Program (ILP) (Khashabi et al.”
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).”
SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach (2018, methodology): “Microsoft’s search query logs (Yih et al., 2014) and WikiAnswers web questions (Fader et al.”
SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models (2022, background): “…is the transformation of input ut-terance into formal language, such as SQL query (Zelle and Mooney, 1996), and plays a critical role in NLP applications, such as question answering (Yih et al., 2014), dialogue system (Gupta et al., 2018), and information extraction (Yao and Van Durme, 2014).”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, positive): “Yih et al. (2014) solve the single-relation question by completing two tasks: linking the mention in the question to an entity in KGs as the topic entity, and mapping the relation pattern described by the question to a relation in KGs.”