Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs

By Bailin Wang, Ivan Titov, Mirella Lapata. 2019

51 citations recorded by the source corpus.

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained on utterance-denotation pairs treating programs as latent. The task is challenging due to the large search space and spuriousness of programs which may execute to the correct answer but do not generalize to unseen examples. Our goal is to instill an inductive bias in the parser to help it distinguish between spurious and correct programs. We capitalize on the intuition that correct programs would likely respect certain structural constraints were they to be aligned to the question (e.g., program fragments are unlikely to align to overlapping text spans) and propose to model alignments as structured latent variables. In order to make the latent-alignment framework tractable, we decompose the parsing task into (1) predicting a partial “abstract program” and (2) refining it while modeling structured alignments with differential dynamic programming. We obtain state-of-the-art performance on the WikiTableQuestions and WikiSQL datasets. When compared to a standard attention baseline, we observe that the proposed structured-alignment mechanism is highly beneficial.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

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 Natural Language Processing

In Information Extraction

Citations in the corpus

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing (2020, methodology): “This suggests that inductive biases injected in pre-trained representation of G RAPPA can signiﬁcantly help combat the issue of spurious programs introduced by learning from denotations Pasupat & Liang (2015); Wang et al. (2019) when gold programs are not available.”
TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021, methodology): “For TableQA, previous works almost formulate it as a weakly semantic parsing task (Liang et al., 2018; Wang et al., 2019a; Guo et al., 2021), which always employ reinforcement learning to optimize semantic parsers over tables.”
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries (2020, background): “Wang et al. (2019) argue that structured alignment is crucial to text-to-SQL models and they induce latent alignments in a weakly-supervised setting.”
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data (2020, methodology): “Global–GNN (Bogin et al., 2019a) 52.7 EditSQL + B ERT (Zhang et al., 2019a) 57.6 RatSQL (Wang et al., 2019a) 60.9 IRNet + B ERT (Guo et al., 2019) 60.3 + Memory + Coarse-to-Fine 61.9 IRNet V2 + B ERT 63.9 RyanSQL + B ERT (Choi et al., 2020) 66.6 Our System based on TranX (Yin and Neubig, 2018…”