Value-Agnostic Conversational Semantic Parsing
By Emmanouil Antonios Platanios, Adam Pauls, Subhro Roy, Alexander Kyte, Alan Guo, Sam Thomson, Jayant Krishnamurthy, Jason Andrew Wolfe, Jacob Andreas, Daniel Klein. 2021
21 citations recorded by the source corpus.
Conversational semantic parsers map user utterances to executable programs given dialogue histories composed of previous utterances, programs, and system responses. Existing parsers typically condition on rich representations of history that include the complete set of values and computations previously discussed. We propose a model that abstracts over values to focus prediction on type- and function-level context. This approach provides a compact encoding of dialogue histories and predicted programs, improving generalization and computational efficiency. Our model incorporates several other components, including an atomic span copy operation and structural enforcement of well-formedness constraints on predicted programs, that are particularly advantageous in the low-data regime. Trained on the SMCalFlow and TreeDST datasets, our model outperforms prior work by 7.3% and 10.6% respectively in terms of absolute accuracy. Trained on only a thousand examples from each dataset, it outperforms strong baselines by 12.4% and 6.4%. These results indicate that simple representations are key to effective generalization in conversational semantic parsing.
Subfields: Artificial Intelligence, 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
- Mohit Bansal
- Percy Liang
- Sergey Levine
- Luke S. Zettlemoyer
- Jianfeng Gao
- Yejin Choi
- Quoc V. Le
- Jacob Andreas
In Natural Language Processing
- Jonathan Herzig
- Mohit Bansal
- Panupong Pasupat
- Percy Liang
- Jacob Andreas
- Jonathan Berant
- Luke S. Zettlemoyer
- Peter Shaw
Citations in the corpus
- Pre-Trained Language Models for Interactive Decision-Making (2022, background): “In recent years, word and sentence representations from pre-trained LMs [29, 9, 33] have become ubiquitous in natural language processing [49, 30].”
- Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing (2022, methodology): “We use LISPRESS (Platanios et al., 2021), which is a LISPlike serialization format, for programs.”