Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots

Zhao, Wenting; Liu, Ye; Wan, Yao; Yu, Philip S.

doi:10.18653/v1/2021.findings-emnlp.347

Cited by 5 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As language models have advanced (Devlin et al, 2019;Raffel et al, 2020;Zhao et al, 2023;Dong et al, 2023;Zhao et al, 2021;, numerous efforts have emerged to enhance the performance of MRC-based NER. incorporated different domain knowledge into MRCbased NER task to improve model generalization ability.…”

Section: Related Workmentioning

confidence: 99%

Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

Wang,

Zhao,

Wan

et al. 2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

Named Entity Recognition (NER) aims to extract and classify entity mentions in the text into pre-defined types (e.g., organization or person name). Recently, many works have been proposed to shape the NER as a machine reading comprehension problem (also termed MRC-based NER), in which entity recognition is achieved by answering the formulated questions related to pre-defined entity types through MRC, based on the contexts. However, these works ignore the label dependencies among entity types, which are critical for precisely recognizing named entities. In this paper, we propose to incorporate the label dependencies among entity types into a multi-task learning framework for better MRC-based NER. We decompose MRC-based NER into multiple tasks and use a self-attention module to capture label dependencies. Comprehensive experiments on both nested NER and flat NER datasets are conducted to validate the effectiveness of the proposed Multi-NER. Experimental results show that Multi-NER can achieve better performance on all datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

Wang,

Zhao,

Wan

et al. 2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

show abstract

“…However, the input text is insufficient to provide knowledge to generate decent output due to the lack of commonsense, factual events, and semantic information. Knowledge-grounded text generation incorporating external knowledge such as linguistic features (Liu et al, 2021c), knowledge graph (Liu et al, 2021b;Li et al, 2021a), knowledge base (Eric and Manning, 2017;Liu et al, 2022b), and textual knowledge (Liu et al, 2021a;Zhao et al, 2021) help to generate a more logical and informative answer.…”

Section: Related Workmentioning

confidence: 99%

Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables

Zhao,

Liu,

Wan

et al. 2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

Question answering on tabular data (a.k.a TableQA), which aims at generating answers to questions grounded on a provided table, has gained significant attention recently. Prior work primarily produces concise factual responses through information extraction from individual or limited table cells, lacking the ability to reason across diverse table cells. Yet, the realm of free-form TableQA, which demands intricate strategies for selecting relevant table cells and the sophisticated integration and inference of discrete data fragments, remains mostly unexplored. To this end, this paper proposes a generalized three-stage approach: Table-to-Graph conversion and cell localizing, external knowledge retrieval, and the fusion of table and text (called TAG-QA), to address the challenge of inferring long free-form answers in generative TableQA. In particular, TAG-QA (1) locates relevant table cells using a graph neural network to gather intersecting cells between relevant rows and columns, (2) leverages external knowledge from Wikipedia, and (3) generates answers by integrating both tabular data and natural linguistic information. Experiments showcase the superior capabilities of TAG-QA in generating sentences that are both faithful and coherent, particularly when compared to several state-of-the-art baselines. Notably, TAG-QA surpasses the robust pipelinebased baseline TAPAS by 17% and 14% in terms of BLEU-4 and PARENT F-score, respectively. Furthermore, TAG-QA outperforms the end-to-end model T5 by 16% and 12% on BLEU-4 and PARENT F-score, respectively. 1

show abstract

“…Recently, few-shot data-to-text generation [20][21][22][23] has attracted increasing attention. Some incorporate memory module [26,27], while some exploit data augmentation based on existing training set [28,29]. Kasner and Dusek [30] explored a zero-shot setting that utilizes a handcrafted template to transform triples into textual facts and uses neural modules to plan and form the final text.…”

Section: Related Work 21 Data-to-text Generationmentioning

confidence: 99%

Quality Control for Distantly-Supervised Data-to-Text Generation via Meta Learning

2023

View full text Add to dashboard Cite

Data-to-text generation plays an important role in natural language processing by processing structured data and helping people understand those data by generating user-friendly descriptive text. It can be applied to news generation, financial report generation, customer service, etc. However, in practice, it needs to adapt to different domains that may lack an annotated training corpus. To alleviate this dataset scarcity problem, distantly-supervised data-to-text generation has emerged, which constructs a training corpus automatically and is more practical to apply to new domains when well-aligned data is expensive to obtain. However, this distant supervision method of training induces an over-generation problem since the automatically aligned text includes hallucination. These expressions cannot be inferred from the data, misguiding the model to produce unfaithful text. To exploit the noisy dataset while maintaining faithfulness, we empower the neural data-to-text model by dynamically increasing the weights of those well-aligned training instances and reducing the weights of the low-quality ones via meta learning. To our best knowledge, we are the first to alleviate the noise in distantly-supervised data-to-text generation via meta learning. In addition, we rewrite those low-quality texts to provide better training instances. Finally, we construct a new distantly-supervised dataset, DIST-ToTTo (abbreviation for Distantly-supervised Table-To-Text), and conduct experiments on both the benchmark WITA (abbreviation for the data source Wikipedia and Wikidata) and DIST-ToTTo datasets. The evaluation results show that our model can improve the state-of-the-art DSG (abbreviation for Distant Supervision Generation) model across all automatic evaluation metrics, with an improvement of 3.72% on the WITA dataset and 3.82% on the DIST-ToTTo dataset in terms of the widely used metric BLEU (abbreviation for BiLingual Evaluation Understudy). Furthermore, based on human evaluation, our model can generate more grammatically correct and more faithful text compared to the state-of-the-art DSG model.

show abstract

Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots

Cited by 5 publications

References 40 publications

Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables

Quality Control for Distantly-Supervised Data-to-Text Generation via Meta Learning

Contact Info

Product

Resources

About