Large-Scale Simple Question Generation by Template-Based Seq2seq Learning

Li, Tianyu; Wei, Bingzhen; Chang, Baobao; Sui, Zhifang

doi:10.1007/978-3-319-73618-1_7

Cited by 17 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, due to the rareness of the word 'kiev', our model is able to cover the related information. Similarly, the generated description for WB-filter covers the information from 'Organization' and ' Birthplace' with the help of pro-seq2seq seq2seq+Force-attention struct-aware [Liu et al 2017 Fig 6(right) shows the effects of λ in Eq 6.…”

Section: Analysis Of Experimental Resultsmentioning

confidence: 99%

“…Androutsopoulos et al (2013) and Duma and Klein (2013) focused on generating descriptive language for Ontologies and RDF triples. Most recent work utilize neural networks on data-to-text generation (Mahapatra et al, 2016;Wiseman et al, 2017;Kaffee et al, 2018;Freitag and Roy, 2018;Qader et al, 2018;Dou et al, 2018;Yeh et al, 2018;Jhamtani et al, 2018;Liu et al, 2017bLiu et al, , 2019Peng et al, 2019;Dušek et al, 2019). Some closely relevant work also focused on the table-to-text generation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards Comprehensive Description Generation from Factual Attribute-value Tables

Li¹,

Luo²,

Yang³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

The comprehensive descriptions for factual attribute-value tables, which should be accurate, informative and loyal, can be very helpful for end users to understand the structured data in this form. However previous neural generators might suffer from key attributes missing, less informative and groundless information problems, which impede the generation of high-quality comprehensive descriptions for tables. To relieve these problems, we first propose force attention (FA) method to encourage the generator to pay more attention to the uncovered attributes to avoid potential key attributes missing. Furthermore, we propose reinforcement learning for information richness to generate more informative as well as more loyal descriptions for tables. In our experiments, we utilize the widely used WIKIBIO dataset as a benchmark. Additionally we create WB-filter based on WIKIBIO to test our model in the simulated user-oriented scenarios, in which the generated descriptions should accord with particular user interests. Experimental results show that our model outperforms the state-of-the-art baselines on both automatic and human evaluation.

show abstract

Section: Analysis Of Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Towards Comprehensive Description Generation from Factual Attribute-value Tables

Li¹,

Luo²,

Yang³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…To reduce hallucinations in the reference-based setting, researchers have applied iterative training (Nie et al, 2019), post editing (Dong et al, 2020), soft constraints, e.g. attention manipulation (Kiddon et al, 2016;Hua and Wang, 2019;Tian et al, 2019; or optimal transport (Wang et al, 2020b), and template/scaffold guided schema (Liu et al, 2017;Wiseman et al, 2018;Moryossef et al, 2019;Ye et al, 2020;Shen et al, 2020;Li and Rush, 2020;Balakrishnan et al, 2019;Liu et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

Li¹,

Zhang²,

Brockett³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications. Existing work usually attempts to detect these hallucinations based on a corresponding oracle reference at a sentence or document level. However ground-truth references may not be readily available for many free-form text generation applications, and sentence-or document-level detection may fail to provide the fine-grained signals that would prevent fallacious content in real time. As a first step to addressing these issues, we propose a novel token-level, reference-free hallucination detection task and an associated annotated dataset named HADES (HAllucination DEtection dataSet) 1 . To create this dataset, we first perturb a large number of text segments extracted from English language Wikipedia, and then verify these with crowd-sourced annotations. To mitigate label imbalance during annotation, we utilize an iterative model-inloop strategy. We conduct comprehensive data analyses and create multiple baseline models.

show abstract

“…(Liang, Jordan, and Klein 2009;Angeli, Liang, and Klein 2010) extend the work of Barzilay and Lapata to soccer and weather domains by learning the alignment between data and text using hidden variable models. Most recent work treated natural language generation in an end-to-end fashion (Mei, Bansal, and Walter 2016;Lebret, Grangier, and Auli 2016;Wiseman, Shieber, and Rush 2017;Xu et al 2018;Lin et al 2018;Luo et al 2018;Liu et al 2017b;Wang et al 2017) with the help of attention mechanism (Bahdanau, Cho, and Bengio 2014;Luong, Pham, and Manning 2015;Luo et al 2018;Wu et al 2018).…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Encoder with Auxiliary Supervision for Neural Table-to-Text Generation: Learning Better Representation for Tables

Luo

Qin

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

Generating natural language descriptions for the structured tables which consist of multiple attribute-value tuples is a convenient way to help people to understand the tables. Most neural table-to-text models are based on the encoder-decoder framework. However, it is hard for a vanilla encoder to learn the accurate semantic representation of a complex table. The challenges are two-fold: firstly, the table-to-text datasets often contain large number of attributes across different domains, thus it is hard for the encoder to incorporate these heterogeneous resources. Secondly, the single encoder also has difficulties in modeling the complex attribute-value structure of the tables. To this end, we first propose a two-level hierarchical encoder with coarse-to-fine attention to handle the attribute-value structure of the tables. Furthermore, to capture the accurate semantic representations of the tables, we propose 3 joint tasks apart from the prime encoder-decoder learning, namely auxiliary sequence labeling task, text autoencoder and multi-labeling classification, as the auxiliary supervisions for the table encoder. We test our models on the widely used dataset WIKIBIO which contains Wikipedia infoboxes and related descriptions. The dataset contains complex tables as well as large number of attributes across different domains. We achieve the state-of-the-art performance on both automatic and human evaluation metrics.

show abstract

Large-Scale Simple Question Generation by Template-Based Seq2seq Learning

Cited by 17 publications

References 12 publications

Towards Comprehensive Description Generation from Factual Attribute-value Tables

Towards Comprehensive Description Generation from Factual Attribute-value Tables

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

Hierarchical Encoder with Auxiliary Supervision for Neural Table-to-Text Generation: Learning Better Representation for Tables

Contact Info

Product

Resources

About