Incomplete Utterance Rewriting as Semantic Segmentation

Liu, Qian; Chen, Bei; Lou, Jian–Guang; Zhou, Bin; Zhang, Dongmei

doi:10.18653/v1/2020.emnlp-main.227

Cited by 30 publications

(19 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the rewrite task, we compared the pretrained BART with state-of-the-art rewrite models: L-Ptr-Gen (See et al, 2017), GECOR (Quan et al, 2019), and RUN (Liu et al, 2020b). Table 1 shows the experimental results on TASK and CANARD datasets.…”

Section: Bart As Rewrite Modelmentioning

confidence: 99%

“…The split and recombine models are both learned from the well-designed reward function by the policy gradient method. Borrowing the idea from image segmentation, Liu et al (2020b) formulate the utterance rewrite as the semantic segmentation task, where the rewrite model is implemented with UNet (Ronneberger et al, 2015). For the downstream task, the utterance rewrite has been successfully used in dialogue state tracking (DST) tasks (Rastogi et al, 2019;Han et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

“…The experimental results on rewrite datasets TASK (left) and CANARD (right). †: results from(Quan et al, 2019); ‡: results from(Liu et al, 2020b).…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Chen¹,

Chen²,

Li³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

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 endto-end models on both SParC and CoSQL datasets.

show abstract

Section: Bart As Rewrite Modelmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

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

Chen¹,

Chen²,

Li³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…Neighboring distribution divergence (Peng et al, 2021) is initially proposed to detect semantic changes caused by editions like compression (Xu and Durrett, 2019) or rewriting (Liu et al, 2020). Their experiments on syntactic tree pruning and semantic predicate detection also show NDD to be aware of syntax and semantics.…”

Section: Neighboring Distribution Divergencementioning

confidence: 99%

Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence

Peng

Zhao

2021

Preprint

View full text Add to dashboard Cite

Unsupervised constituency parsing has been explored much but is still far from being solved. Conventional unsupervised constituency parser is only able to capture the unlabeled structure of sentences. Towards unsupervised full constituency parsing, we propose an unsupervised and training-free labeling procedure by exploiting the property of a recently introduced metric, Neighboring Distribution Divergence (NDD), which evaluates semantic similarity between sentences before and after editions. For implementation, we develop NDD into Dual POS-NDD (DP-NDD) and build "molds" to detect constituents and their labels in sentences. We show that DP-NDD not only labels constituents precisely but also inducts more accurate unlabeled constituency trees than all previous unsupervised methods with simpler rules. With two frameworks for labeled constituency trees inference, we set both the new state-of-the-art for unlabeled F1 and strong baselines for labeled F1. In contrast with the conventional predictingand-evaluating scenario, our method acts as an plausible example to inversely apply evaluating metrics for prediction.

show abstract

“…Turn Utterance (Translation) Previous works [7,8,9,10,11,12] formulate the conversational context understanding as a query rewriting problem, transforming a user utterance with anaphora or ellipsis into a new utterance where the left-out or referred expressions are automatically generated from the dialogue context. Usually an end-to-end sequence-to-sequence model with copy mechanism is applied for this task.…”

Section: Introductionmentioning

confidence: 99%

Conversational Query Rewriting with Self-Supervised Learning

Liu

Chen

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Context modeling plays a critical role in building multi-turn dialogue systems. Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational query into a self-contained utterance. However, existing approaches rely on massive supervised training data, which is labor-intensive to annotate. And the detection of the omitted important information from context can be further improved. Besides, intent consistency constraint between contextual query and rewritten query is also ignored. To tackle these issues, we first propose to construct a large-scale CQR dataset automatically via self-supervised learning, which does not need human annotation. Then we introduce a novel CQR model Teresa based on Transformer, which is enhanced by self-attentive keywords detection and intent consistency constraint. Finally, we conduct extensive experiments on two public datasets. Experimental results demonstrate that our proposed model outperforms existing CQR baselines significantly, and also prove the effectiveness of self-supervised learning on improving the CQR performance.

show abstract

Incomplete Utterance Rewriting as Semantic Segmentation

Cited by 30 publications

References 37 publications

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

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

Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence

Conversational Query Rewriting with Self-Supervised Learning

Contact Info

Product

Resources

About