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

09/09/2019
by   Bailin Wang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2017

Weakly-supervised Semantic Parsing with Abstract Examples

Semantic parsers translate language utterances to programs, but are ofte...
research
08/23/2018

Weakly-supervised Neural Semantic Parsing with a Generative Ranker

Weakly-supervised semantic parsers are trained on utterance-denotation p...
research
04/12/2021

Learning from Executions for Semantic Parsing

Semantic parsing aims at translating natural language (NL) utterances on...
research
04/25/2017

From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood

Our goal is to learn a semantic parser that maps natural language uttera...
research
07/13/2021

Enforcing Consistency in Weakly Supervised Semantic Parsing

The predominant challenge in weakly supervised semantic parsing is that ...
research
10/14/2021

LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing

Semantic parsing is the task of producing a structured meaning represent...
research
05/25/2022

Active Programming by Example with a Natural Language Prior

We introduce APEL, a new framework that enables non-programmers to indir...

Please sign up or login with your details

Forgot password? Click here to reset