Information Extraction over Structured Data: Question Answering with Freebase
By Xuchen Yao, Benjamin Van Durme. 2014
487 citations recorded by the source corpus.
Answering natural language questions using the Freebase knowledge base has recently been explored as a platform for advancing the state of the art in open domain semantic parsing. Those efforts map questions to sophisticated meaning representations that are then attempted to be matched against viable answer candidates in the knowledge base. Here we show that relatively modest information extraction techniques, when paired with a webscale corpus, can outperform these sophisticated approaches by roughly 34% relative gain.
Subfields: Artificial Intelligence, Question Answering & Reading Comprehension, Information Extraction
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
- Jianfeng Gao
- Luke S. Zettlemoyer
- Percy Liang
- Yejin Choi
- Caiming Xiong
- Graham Neubig
- Christopher D. Manning
In Question Answering & Reading Comprehension
- Anton van den Hengel
- Wen-tau Yih
- Xiaodong He
- Ashish Sabharwal
- Peter Clark
- Xiaohan Zou
- Jianfeng Gao
- Qi Wu
In Information Extraction
- Wen-tau Yih
- Dan Roth
- Ming-Wei Chang
- Siva Reddy
- Tom Kwiatkowski
- Luke S. Zettlemoyer
- Mirella Lapata
- Eunsol Choi
Citations in the corpus
- 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): “We take the example used in Yih et al. (2015a) to illustrate the QA process.”
- Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions (2016, methodology): “Answering questions using an ensemble has been shown to be effective in numerous previous cases, (e.g., Töscher, Jahrer, and Bell (2009)), most famously in IBM’s highly successful Watson system (Ferrucci et al. 2010).”
- Modeling Relational Data with Graph Convolutional Networks (2017, background): “Knowledge bases organize and store factual knowledge, enabling a multitude of applications including question answering (Yao and Van Durme 2014; Bao et al. 2014; Seyler, Yahya, and Berberich 2015; Hixon, Clark, and Hajishirzi 2015; Bordes et al. 2015; Dong et al. 2015) and information retrieval (Kot”
- Explicit Knowledge-based Reasoning for Visual Question Answering (2015, background): “The advances in structured KBs, have driven an increasing interest in the NLP and AI communities in the problem of natural language question answering using structured KBs (refer to as KBQA) [4, 7, 8, 16, 23, 25, 41, 26, 38].”
- Question Answering via Integer Programming over Semi-Structured Knowledge (2016, methodology): “…the capital of France?”) using document collections or databases (e.g., Freebase [Bollacker et al. , 2008], NELL [Carlson et al. , 2010]), for example [Brill et al. , 2002; Fader et al. , 2014; Ferrucci et al. , 2010; Ko et al. , 2007; Yih et al. , 2014; Yao and Van Durme, 2014; Zou et al. , 2014].”
- Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015, methodology): “Inspired by (Yao and Van Durme, 2014; Bao et al., 2014), we propose a semantic parsing framework that leverages the knowledge base more tightly when forming the parse for an input question.”
- Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths (2015, methodology): “Zelenko et al. (2003) compute the similarity of two trees by utilizing their common subtrees.”
- FVQA: Fact-Based Visual Question Answering (2016, background): “KB-QA approaches can be divided into two categories: semantic parsing methods [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47] that try to translate questions into accurate logical expressions and then map to KB queries, and information retrieval methods [48], [49], [50], [51], [52],”
- Question Answering over Freebase with Multi-Column Convolutional Neural Networks (2015, methodology): “This entity resolution method was also used in (Yao and Van Durme, 2014).”
- Measuring Compositional Generalization: A Comprehensive Method on Realistic Data (2019, methodology): “This means that CFQ can be used for semantic parsing (Be-rant et al., 2013; Yao & Van Durme, 2014), which is the task that we focus on in this paper.”
- Improved Neural Relation Detection for Knowledge Base Question Answering (2017, background): “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).”
- Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification (2016, background): “Relation classification is the task of finding semantic relations between pairs of nominals, which is useful for many NLP applications, such as information extraction (Wu and Weld, 2010), question answering (Yao and Van Durme, 2014).”
- Large-scale Semantic Parsing without Question-Answer Pairs (2014, background): “Indeed, methods which learn from question-answer pairs have been gaining momentum as a means of scaling semantic parsers to large, open-domain problems (Kwiatkowski et al., 2013; Berant et al., 2013; Berant and Liang, 2014; Yao and Van Durme, 2014).”
- Learning to Paraphrase for Question Answering (2017, unknown): “G RAPH Q W EB Q S EMPRE (Berant et al., 2013) 10.8 35.7 J ACANA (Yao and Van Durme, 2014) 5.1 33.0 P ARA S EMP (Berant and Liang, 2014) 12.8 39.9 S UB G RAPH (Bordes et al., 2014a) - 40.4 MCCNN (Dong et al., 2015) - 40.8 Y AO 15 (Yao, 2015) - 44.3 A GENDA IL (Berant and Liang, 2015) - 49.7 STAGG…”