Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence

By Xiaoyu Shen, Ernie Chang, Hui Su, Jie Zhou, Dietrich Klakow. 2020

51 citations recorded by the source corpus.

The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and “hallucination”. Due to the black-box nature of the neural attention architecture, avoiding these problems in a systematic way is non-trivial. To address this concern, we propose to explicitly segment target text into fragment units and align them with their data correspondences. The segmentation and correspondence are jointly learned as latent variables without any human annotations. We further impose a soft statistical constraint to regularize the segmental granularity. The resulting architecture maintains the same expressive power as neural attention models, while being able to generate fully interpretable outputs with several times less computational cost. On both E2E and WebNLG benchmarks, we show the proposed model consistently outperforms its neural attention counterparts.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Natural Language Generation

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 Computer Vision and Pattern Recognition

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Data-to-text datasets take different formats, including slot-value pairs, Abstract Meaning Representation (AMR) (Flanigan et al., 2016; Ferreira et al., 2017; Song et al., 2017; Zhu et al., 2019a; Ribeiro et al., 2019; Damonte and Cohen, 2019; Wang et al., 2020a; Zhao et al., 2020b; Shen et al., 202”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “2020b), template-like (Liu et al. 2017; Wiseman, Shieber, and Rush 2018; Shen et al. 2020; Li and Rush 2020; Ye et al. 2020) or controllable generation (Peng et al.”
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation (2021, background): “text sequences which specify the narrative ordering, and implicit plans (Wiseman et al., 2018; Ye et al., 2020; Shen et al., 2020; Li and Rush, 2020), e.”
Controlling hallucinations at word level in data-to-text generation (2021, background): “In this direction, Shen et al. [61] were able to obtain good results at increasing the coverage of neural outputs, by constraining the decoder to focus its attention exclusively on each table cell sequentially until the whole table was realized.”
Neural Data-to-Text Generation with LM-based Text Augmentation (2021, methodology): “For future works, we hope to apply the techniques to annotation scenarios (Hong et al., 2019; de Souza et al., 2018; Zhuang and Chang, 2017; Chang et al., 2020a; Wiehr et al., 2020; Shen et al., 2020; Chang et al., 2020b; Su et al., 2020a; Chang et al., 2021a,b; Crook et al., 2018).”
AggGen: Ordering and Aggregating while Generating (2021, methodology): “…2017 (seen) and E2E dataset, i.e. T5 (Kale and Rastogi, 2020), PlanEnc (Zhao et al., 2020), ADAPT (Gardent et al., 2017b), and TGen (Dušek and Jurčı́ček, 2016); (2) models with explicit planning, i.e. TILB-PIPE (Gardent et al., 2017b), NTemp+AR (Wiseman et al., 2018) and Shen et al. (2020).”
Sequence-to-Sequence Learning with Latent Neural Grammars (2021, unknown): “…with the use of neural networks over embedding parameterizations, which makes it easy to share parameters and additionally condition the generative model on side information such as auxiliary latent variables [52, 64], images [130, 60, 55], video and audio [129], and source-side context [113, 99].”