Scaling Semantic Parsers with On-the-Fly Ontology Matching

By Tom Kwiatkowski, Eunsol Choi, Yoav Artzi, Luke S. Zettlemoyer. 2013

334 citations recorded by the source corpus.

We consider the challenge of learning semantic parsers that scale to large, open-domain problems, such as question answering with Freebase. In such settings, the sentences cover a wide variety of topics and include many phrases whose meaning is difficult to represent in a fixed target ontology. For example, even simple phrases such as ‘daughter’ and ‘number of people living in’ cannot be directly represented in Freebase, whose ontology instead encodes facts about gender, parenthood, and population. In this paper, we introduce a new semantic parsing approach that learns to resolve such ontological mismatches. The parser is learned from question-answer pairs, uses a probabilistic CCG to build linguistically motivated logicalform meaning representations, and includes an ontology matching model that adapts the output logical forms for each target ontology. Experiments demonstrate state-of-the-art performance on two benchmark semantic parsing datasets, including a nine point accuracy improvement on a recent Freebase QA corpus.

Subfields: Artificial Intelligence, Molecular Biology, 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 Molecular Biology

In Natural Language Processing

Citations in the corpus

Latent Retrieval for Weakly Supervised Open Domain Question Answering (2019, background): “…weakly supervised semantic parsing (Clarke et al., 2010; Liang et al., 2013; Artzi and Zettlemoyer, 2013; Fader et al., 2014; Berant et al., 2013; Kwiatkowski et al., 2013), with which we share similar challenges—(1) inference and learning are tightly coupled, (2) latent derivations must be…”
Break It Down: A Question Understanding Benchmark (2020, methodology): “Domain-independent intermediate representations for semantic parsers were proposed by Kwiatkowski et al. (2013) and Reddy et al.”
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering (2019, background): “Question answering over knowledge bases has also been well studied (Berant et al., 2013; Kwiatkowski et al., 2013; Yih et al., 2015), typically without using any external text collections.”
Key-Value Memory Networks for Directly Reading Documents (2016, methodology): “…KBs (Auer et al. , 2007; Bollacker et al. , 2008) have lead to the developement 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.”
Learning to Automatically Solve Algebra Word Problems (2014, background): “Examples include question answering (Clarke et al., 2010; Cai and Yates, 2013a; Cai and Yates, 2013b; Berant et al., 2013; Kwiatkowski et al., 2013), dialog systems (Artzi and Zettlemoyer, 2011), robot instruction (Chen and Mooney, 2011; Chen, 2012; Kim and Mooney, 2012; Matuszek et al.”
The Web as a Knowledge-Base for Answering Complex Questions (2018, background): “Conversely, work on QA through semantic parsing has focused primarily on compositionality: questions are translated to compositional programs that encode a sequence of actions for finding the answer in a knowledge-base (KB) (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Artzi and Zettlemoye”
Learning to Compose Neural Networks for Question Answering (2016, background): “…the set of primitive functions from which these logical forms can be assembled is fixed, but one recent line of work focuses on inducing new predicates functions automatically, either from perceptual features (Krishnamurthy and Kollar, 2013) or the underlying schema (Kwiatkowski et al., 2013).”
Compositional Semantic Parsing on Semi-Structured Tables (2015, methodology): “The increasing number of relations and entities motivates new resources and techniques for improving the accuracy, including the use of ontology matching models (Kwiatkowski et al., 2013), paraphrase models (Fader et al.”
Question Answering with Subgraph Embeddings (2014, background): “Interestingly, recent works (Berant et al., 2013; Kwiatkowski et al., 2013; Berant and Liang, 2014; Fader et al., 2014) have shown that such systems can be efficiently trained under indirect and imperfect su-”
Semantic Parsing via Paraphrasing (2014, background): “( b) Kwiatkowski et al. (2013) map the utter-ance to an underspeciﬁed logical form, and perform ontology matching to handle the mismatch.”
Building a Semantic Parser Overnight (2015, background): “This connection warrants further scrutiny, as the structural mismatch between logic and language is the chief source of difficulty in semantic parsing (Liang et al., 2011; Kwiatkowski et al., 2013; Berant and Liang, 2014).”
Troubling Trends in Machine Learning Scholarship (2018, background): “Understanding can also come from robustness checks (as in [15], which discovers that existing language models handle inflectional morphology poorly) as well as qualitative error analysis [40].”
Open Question Answering with Weakly Supervised Embedding Models (2014, background): “Their system, Paralex, answers questions with more limited semantics than those introduced in [3,12], but does so at a very large scale in an open-domain manner.”
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].”
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, background): “…type of semantic parsing work (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005; Zettlemoyer & Collins, 2007; Wong & Mooney, 2007; Cai & Yates, 2013; Berant et al., 2013; Kwiatkowski et al., 2013; Berant & Liang, 2014) maps NL text into logical forms by supervised or semi-supervised learning.”
Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015, methodology): “For instance, a generic meaning representation may have the ontology matching problem when the logical form uses predicates that differ from those defined in the KB (Kwiatkowski et al., 2013).”