Question Answering on Freebase via Relation Extraction and Textual Evidence

By Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, Dongyan Zhao. 2016

303 citations recorded by the source corpus.

Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, 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 Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, background): “the features were all extracted from single-passages thus did not utilize the information of union/co-occurrence of multiple passages. (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 al”
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, methodology): “…of products and services, it is very hard, if not impossible, to pre-compile an up-to-date and reliable knowledge base to cover a wide assortment of questions that customers may ask, such as in factoid-based KB-QA (Xu et al., 2016; Fader et al., 2014; Kwok et al., 2001; Yin 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).”
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).”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, methodology): “Answering complex natural language questions with multi-hop reasoning steps on incomplete knowledge graphs (KGs) is a fundamental, yet challenging task (KGQA) (Sun et al., 2019a; Saxena et al., 2020; Bordes et al., 2014; Xu et al., 2016; Yu et al., 2017; Liang et al., 2017).”
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples (2018, methodology): “…the gap between Natural Language and structured knowledge bases (KB) has been the concern of many research tasks such as: Relation Extraction [Mintz et al.2009], KB Population [Ji and Grishman2011], KB-driven Natural Language Generation [Lebret et al.2016] and Question Answering [Xu et al.2016].”
Context-Aware Representations for Knowledge Base Relation Extraction (2017, background): “Relation extraction is a fundamental task that enables a wide range of semantic applications from question answering (Xu et al., 2016) to fact checking (Vlachos and Riedel, 2014).”
Memory Grounded Conversational Reasoning (2019, background): “QA Systems : Structured QA systems have been very popular due to the popularity of the fact-retrieval assistant products, which solve fact-retrieval QA queries with large-scale common fact knowledge graphs (Bordes et al., 2015; Xu et al., 2016; Dubey et al., 2018).”
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017, methodology): “ence on the KB using text based features (Krishnamurthy and Mitchell, 2012; Reddy et al., 2014; Joshi et al., 2014; Yao and Van Durme, 2014; Yih et al., 2015; Neelakantan et al., 2015b; Guu et al., 2015; Xu et al., 2016b; Choi et al., 2015; Savenkov and Agichtein, 2016) or improves the inference on ”
A Multi-Channel Deep Neural Network for Relation Extraction (2020, methodology): “[38] used a model to combine syntactic features (the shortest path in a dependency tree) and semantic features (word embeddings) for recognizing relations.”
An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge (2017, methodology): “Xu et al. (2016a; 2016b) proposed integrated systems to address KB-QA problems incorporating Wikipedia free text, in which they used multichannel CNNs to extract relations.”
Learning to Paraphrase for Question Answering (2017, unknown): “…MCCNN (Dong et al., 2015) - 40.8 Y AO 15 (Yao, 2015) - 44.3 A GENDA IL (Berant and Liang, 2015) - 49.7 STAGG (Yih et al., 2015) - 48.4 (52.5) MCNN (Xu et al., 2016) - 47.0 (53.3) T YPE R ERANK (Yavuz et al., 2016) - 51.6 (52.6) B I L AYERED (Narayan et al., 2016) - 47.2 UD EP L AMBDA (Reddy et…”
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task (2020, unknown): “This makes RE a key part of many information extraction systems, and its performance determines the quality of extracted facts for knowledge base population (Ji and Grishman, 2011), or the quality of answers in question answering systems (Xu et al., 2016).”
Learning an Executable Neural Semantic Parser (2017, unknown): “Xu et al. (2016) represent the state of the art on WEBQUESTIONS .”
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals (2021, unknown): “Retrieval-based methods [5, 24, 30, 31, 34] directly retrieve answers from the KB in light of the information conveyed in the questions.”
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers (2019, background): “, 2016), knowledge base question answering (Yih et al., 2015; Xu et al., 2016; Yu et al., 2017), and symbolic approaches for visual question answering (Mao et al.”
Semantic Parsing to Probabilistic Programs for Situated Question Answering (2016, unknown): “Semantic parsing translates natural language questions into executable logical forms and has been used in applications such as question answering against a knowledge base (Zelle and Mooney, 1993; Zettlemoyer and Collins, 2005; Liang et al., 2011; Kwiatkowski et al., 2013; Berant et al., 2013; Reddy ”
ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters (2018, background): “Very recent work demonstrated that the two variants are complementary, and a combination of the two results in the best answering performance (Savenkov and Agichtein, 2016; Sun et al., 2018; Xu et al., 2016).”