Learning to Learn Semantic Parsers from Natural Language Supervision
By Igor Labutov, Bishan Yang, Tom Michael Mitchell. 2019
16 citations recorded by the source corpus.
As humans, we often rely on language to learn language. For example, when corrected in a conversation, we may learn from that correction, over time improving our language fluency. Inspired by this observation, we propose a learning algorithm for training semantic parsers from supervision (feedback) expressed in natural language. Our algorithm learns a semantic parser from users’ corrections such as “no, what I really meant was before his job, not after”, by also simultaneously learning to parse this natural language feedback in order to leverage it as a form of supervision. Unlike supervision with gold-standard logical forms, our method does not require the user to be familiar with the underlying logical formalism, and unlike supervision from denotation, it does not require the user to know the correct answer to their query. This makes our learning algorithm naturally scalable in settings where existing conversational logs are available and can be leveraged as training data. We construct a novel dataset of natural language feedback in a conversational setting, and show that our method is effective at learning a semantic parser from such natural language supervision.
Subfields: Artificial Intelligence
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
- Gholamreza Haffari
- Lizhen Qu
- Zhuang Li
- Ahmed Elgohary
- Miroslav Dud'ik
- Huan Sun
- Ahmed Hassan Awadallah
- Yu Su
Citations in the corpus
- Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “Feedback semantic parsing interactively collects data from user feedbacks as continuous data streams but does not address the problem of catastrophic forgetting or improve forward transfer (Iyer et al., 2017; Yao et al., 2019; Labutov et al., 2018).”
- Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback (2020, background): “Our work is closest to (Labutov et al., 2018), which also studies correcting semantic parses with natural language feedback, but we (1) focus on text-to-SQL parsing and build on a multi-domain dataset that requires generating complex semantic structures and generalizing to unseen domains (Labutov et”
- Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study (2019, background): “Learning from user feedback is a promising solution for lifelong semantic parser improvement (Iyer et al., 2017; Padmakumar et al., 2017; Labutov et al., 2018).”
- Interactive Learning from Activity Description (2021, background): “…2020), learning to ground language to actions (Chen & Mooney, 2011; Misra et al., 2014; Bisk et al., 2016; Liu et al., 2016; Wang et al., 2016; Li et al., 2017; 2020a;b), or devising EM-based algo-Interactive rithms to parse language into logical forms (Matuszek et al., 2012; Labutov et al., 2018).”