Published on Fri Jun 04 2021

Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL

Zhi Chen, Lu Chen Hanqi Li, Ruisheng Cao, Da Ma, Mengyue Wu, Kai Yu

The proposed method can achieve excellent performance without any annotated in-domain data. With just a few annotated rewrite cases, the decoupled method outperforms the state-of-the-art end-to-end models on both SParC and CoSQL datasets.

8
0
6
Abstract

Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user input of the current turn is parsed into the corresponding SQL query of the appropriate database, given all previous dialogue history. Current approaches mostly employ end-to-end models and consequently face two challenges. First, dialogue history modeling and Text-to-SQL parsing are implicitly combined, hence it is hard to carry out interpretable analysis and obtain targeted improvement. Second, SQL annotation of multi-turn dialogue is very expensive, leading to training data sparsity. In this paper, we propose a novel decoupled multi-turn Text-to-SQL framework, where an utterance rewrite model first explicitly solves completion of dialogue context, and then a single-turn Text-to-SQL parser follows. A dual learning approach is also proposed for the utterance rewrite model to address the data sparsity problem. Compared with end-to-end approaches, the proposed decoupled method can achieve excellent performance without any annotated in-domain data. With just a few annotated rewrite cases, the decoupled method outperforms the released state-of-the-art end-to-end models on both SParC and CoSQL datasets.

Mon Sep 02 2019
NLP
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
We focus on the cross-domain context-dependent text-to-SQL generation task. We employ an utterance-table encoder and a table-aware decoder. We evaluate our approach on the SParC dataset and demonstrate the benefit of editing.
0
0
0
Fri Jun 14 2019
Artificial Intelligence
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Current models are still far from satisfactory for multi-turn dialgoue modelling. Each utterance is first rewritten to recover coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance.
0
0
0
Tue Mar 12 2019
NLP
Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns. We develop our model for query reforming using a pointer-generator network and a novel multi-task learning setup.
0
0
0
Fri Sep 25 2020
Artificial Intelligence
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Minimalist Transfer Learning (MinTL) is a simple yet effective transfer learning framework. Unlike previous approaches, which use a copy mechanism to"carryover" the old dialogue states to the new one, we introduce Levenshtein belief spans.
0
0
0
Mon Sep 28 2020
Machine Learning
Incomplete Utterance Rewriting as Semantic Segmentation
We present a novel and extensive approach, which formulates it as asemantic segmentation task. Instead of generating from scratch, such aformulation introduces edit operations and shapes the problem as prediction of word-level edit matrix. Our approach is four times faster than the standard approach in inference.
0
0
0
Tue Feb 09 2021
NLP
Conversational Query Rewriting with Self-supervised Learning
Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem. Existing approaches rely on massive supervised training data, which is labor-intensive to annotate.
0
0
0
Mon Jun 12 2017
NLP
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms. Experiments on two machine translation tasks show these models to be superior in
50
215
883
Fri Oct 23 2020
NLP
SmBoP: Semi-autoregressive Bottom-up Semantic Parsing
The de-facto standard decoding method for semantic parsing in recent years has been to autoregressively decode the abstract syntax tree of the target program using a top-down depth-first traversal. In this work, we propose an alternative approach: a Semi-autoregressive Bottom-up
2
2
10
Thu Jul 21 2016
Machine Learning
Layer Normalization
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch.
1
0
2
Tue Oct 29 2019
Machine Learning
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
BART is a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by corrupting text with an arbitrary noising function and learning a model to reconstruct the original text. BART achieves new state-of-the-art results on a range of
0
0
0
Tue Sep 22 2020
NLP
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status. Taking advantage of the structured state representation, we can further fine-tune the pre-trained model (by supervised learning)
0
0
0
Mon May 18 2015
Computer Vision
U-Net: Convolutional Networks for Biomedical Image Segmentation
The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. Segmentation of a 512x512 image takes less than a second on a recent GPU.
1
0
0