Learning executable semantic parsers for natural language understanding

By Percy Liang. 2016

135 citations recorded by the source corpus.

Semantic parsing is a rich fusion of the logical and the statistical worlds.

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

Measuring and Improving BERT’s Mathematical Abilities by Predicting the Order of Reasoning. (2021, methodology): “Since natural language understanding also involves symbolic manipulation (Liang, 2016), we treat mathematical reasoning as a language understanding and revisit the data-driven paradigm.”
Training Classifiers with Natural Language Explanations (2018, methodology): “Semantic parsing of natural language into logical forms is recognized as a challenging problem and has been studied extensively (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang et al., 2011; Liang, 2016).”
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models (2021, methodology): “Our approach also differs from methods that semantically parse natural language into a formal representation on which a formal reasoner can be applied (Liang, 2016), as we directly reason with language.”
Axiomatic Attribution for Deep Networks (2017, background): “A common approach is to semantically parse the question to its logical form (Liang, 2016; Pasupat & Liang, 2015) using a set of human-authored grammar rules.”
Search-based Neural Structured Learning for Sequential Question Answering (2017, background): “Semantic parsing, which maps natural language text to meaning representations in formal logic, has emerged as a key technical component for building question answering systems (Liang, 2016).”
Program Synthesis and Semantic Parsing with Learned Code Idioms (2019, background): “When an input speciﬁcation is limited to natu-ral language, the resulting problem can be considered semantic parsing [22].”
Learning a Natural Language Interface with Neural Programmer (2016, methodology): “Semantic parsing is a challenging problem that involves deep language understanding and reasoning with discrete operations such as counting and row selection (Liang, 2016).”
Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing (2020, background): “Researchers have also explored models involving logical forms and discourse for language representation [15, 32, 35].”
Learning an Executable Neural Semantic Parser (2017, unknown): “Jia and Liang (2016) achieve better results with synthetic data that expand G EO Q UERY ; we could adopt their approach to improve model performance, however, we leave this to future work.”
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations (2018, background): “The semantic parsing literature has focused on representing language with logical forms (Liang, 2016; Zettlemoyer and Collins, 2012; Kwiatkowski et al., 2010).”
A Survey on Semantic Parsing (2018, methodology): “We refer the reader to [Jia and Liang, 2016] for more details on the grammar induction steps.”
Robust Text-to-SQL Generation with Execution-Guided Decoding (2018, methodology): “ is then used for question answering (Wong and Mooney 2007; Zettlemoyer and Collins 2005; 2007; Berant et al. 2013), robot navigation (Chen and Mooney 2011; Tellex et al. 2011), and many other tasks. Liang (2016) surveys different statistical semantic parsers and categorizes them under a uniﬁed fram”
Leveraging Language to Learn Program Abstractions and Search Heuristics (2021, methodology): “, 2017), semantic parsing (Artzi & Zettlemoyer, 2013; Liang, 2016), structured visual understanding (Johnson et al.”
Complexity-Based Prompting for Multi-Step Reasoning (2022, background): “The procedure of chain of thoughts prompting is conceptually similar to classical semantic parsing where one generates a logical form then executes it upon a knowledge base to reach a ﬁnal answer (Liang, 2016; Cheng et al., 2019).”
An Application-Independent Approach to Building Task-Oriented Chatbots with Interactive Continual Learning (2020, methodology): “As a part of reduction, the variables of C (cid:48) obtained after replacement are also renamed [i.e. from block_set/O1 in C 2 in Figure 1 to block_set/X3 (not shown)] and aliases are recorded, so that in the next iteration, it can be matched with the action SCs [in Lines 5 and 21].”
Why Build an Assistant in Minecraft? (2019, methodology): “In our view, with the assumptions of this program, this is nontrivial but straightforward, for example using techniques as in [100, 101, 53, 52].”
Improving Question Answering by Commonsense-Based Pre-Training (2018, unknown): “We believe that deep question understanding, such as parsing a question based on a predeﬁned grammar and operators in a semantic parsing manner (Liang 2016), is required to handle these questions, which is a very promising direction, and we leave it to future work.”