Weakly-supervised Neural Semantic Parsing with a Generative Ranker

Abstract

Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.

arXiv commentIn EMNLP-CoNLL 2018

References in corpus (12)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Question Answering with Subgraph Embeddings
• Language to Logical Form with Neural Attention
• A Joint Model of Language and Perception for Grounded Attribute Learning
• Learning Dependency-Based Compositional Semantics
• Universal Semantic Parsing
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• Inferring Logical Forms From Denotations
• A Generative Parser with a Discriminative Recognition Algorithm
• Evaluating Induced CCG Parsers on Grounded Semantic Parsing