A Survey on Semantic Parsing

By Aishwarya Kamath, Rajarshi Das. 2018

139 citations recorded by the source corpus.

A significant amount of information in today's world is stored in structured and semi-structured knowledge bases. Efficient and simple methods to query them are essential and must not be restricted to only those who have expertise in formal query languages. The field of semantic parsing deals with converting natural language utterances to logical forms that can be easily executed on a knowledge base. In this survey, we examine the various components of a semantic parsing system and discuss prominent work ranging from the initial rule based methods to the current neural approaches to program synthesis. We also discuss methods that operate using varying levels of supervision and highlight the key challenges involved in the learning of such systems.

Subfields: Information Extraction, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Extraction

1. Mohit Bansal
2. Lizhen Qu
3. Shuo Huang
4. Gholamreza Haffari
5. Oyvind Tafjord
6. Peter Clark
7. Zhuang Li

In Computational Linguistics & Semantics

1. Mohit Bansal
2. Lizhen Qu
3. Gholamreza Haffari
4. Oyvind Tafjord
5. Bhavana Dalvi
6. Peter Clark
7. Zhuang Li

Citations in the corpus

• Injecting Numerical Reasoning Skills into Language Models (2020, neutral): “This approach is a particular case of semantic parsing (Kamath and Das, 2019), and was common in early NRoT datasets (Koncel-Kedziorski et al., 2015; Roy and Roth, 2015; Hosseini et al., 2014).”
• Transformers as Soft Reasoners over Language (2020, neutral): “Our approach contrasts with prior efforts that attempt to semantically parse language into a formal form, so that a formal reasoner can then be applied [ Kamath and Das, 2019 ] .”
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “Semantic Parsing The recent surveys (Kamath and Das, 2018; Zhu et al., 2019; Li et al., 2020) cover an ample of work in semantic parsing.”
• ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language (2020, background): “Unlike other approaches to reasoning such as parsing to a formal language (Kamath and Das, 2019), imple-”
• PRover: Proof Generation for Interpretable Reasoning over Rules (2020, background): “…and Neural Theorem Proving: Semantic parsing (Zettlemoyer and Collins, 2005; Berant et al., 2013; Berant and Liang, 2014) of multi-sentence texts into logical forms has proved to be challenging, restricting the application of semantic parsers to formal reasoning systems (Kamath and Das, 2019).”
• Context Dependent Semantic Parsing: A Survey (2020, methodology): “Most research work on semantic parsing treats each NL utterance as an independent input, ignoring the text surrounding them (Kamath and Das, 2018), such as interaction histories in dialogues.”
• Few-Shot Semantic Parsing for New Predicates (2021, background): “The recent surveys (Kamath and Das, 2018; Zhu et al., 2019) cover a wide range of work in this area.”