Enhancing Neural Data-To-Text Generation Models with External Background Knowledge

Chen, Shuang; Wang, Jinpeng; Feng, Xiaocheng; Jiang, Feng; Qin, Bing; Lin, Chin-Yew

doi:10.18653/v1/d19-1299

Cited by 24 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WikiBio Dataset We list WikiBio's experimental results in Table 6 and compare with models like Table2Seq (Bao et al, 2018), Order Planning , Field Gating , Background-KB Attention (Chen et al, 2019), Hybrid Hierarchical Model (Liu et al, 2019a) trained with multiple auxiliary loss functions. We also train Template-GPT-2 on this dataset to observe pre-trained model's performance.…”

Section: E2e Challengementioning

confidence: 99%

See 1 more Smart Citation

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

Chen¹,

Su²,

Yan³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of labeled data for each task, which is costly to acquire and thus limits their application to new tasks and domains. In this paper, we propose to leverage pre-training and transfer learning to address this issue. We propose a knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text. 2) a pretraining paradigm on a massive knowledgegrounded text corpus crawled from the web. The pre-trained model can be fine-tuned on various data-to-text generation tasks to generate task-specific text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under the fullysupervised setting, our model can achieve remarkable gains over the known baselines. Under zero-shot setting, our model without seeing any examples achieves over 30 ROUGE-L on WebNLG while all other baselines fail. Under the few-shot setting, our model only needs about one-fifteenth as many labeled examples to achieve the same level of performance as baseline models. These experiments consistently prove the strong generalization ability of our proposed framework 1 .

show abstract

Section: E2e Challengementioning

confidence: 99%

“…Model BLEU Table NLM (Lebret et al, 2016) 34.70 Table2Seq (Bao et al, 2018) 40.26 Order Planning 43.91 Field-Gating 44.71 KBAtt (Chen et al, 2019) 44.59 Hierarchical+Auxiliary Loss (Liu et al, 2019a) 45…”

Section: E2e Challengementioning

confidence: 99%

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

Chen¹,

Su²,

Yan³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Nie et al (2018) utilize pre-executed symbolic operations on the input table in a sequence-to-sequence model to improve the fidelity of neural table-to-text generation. Chen et al (2019) introduce the background knowledge of the entity in the table to improve results.…”

Section: Related Workmentioning

confidence: 99%

Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation

Li¹,

Ma²,

Yue³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Table -to-text generation aims at automatically generating natural text to help people conveniently obtain salient information in tables. Although neural models for table-to-text have achieved remarkable progress, some problems are still overlooked. Previous methods cannot deduce the factual results from the entity's (player or team) performance and the relations between entities. To solve this issue, we first build an entity graph from the input tables and introduce a reasoning module to perform reasoning on the graph. Moreover, there are different relations (e.g., the numeric size relation and the importance relation) between records in different dimensions. And these relations may contribute to the data-to-text generation. However, it is hard for a vanilla encoder to capture these. Consequently, we propose to utilize two auxiliary tasks, Number Ranking (NR) and Importance Ranking (IR), to supervise the encoder to capture the different relations. Experimental results on ROTOWIRE and RW-FG show that our method not only has a good generalization but also outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering.

show abstract

“…Another line of work attempts to use external knowledge to improve the quality of generated text (Chen et al, 2019b). These methods allow generation from an expanded external knowledge base that may contain information not relevant to the input table.…”

Section: Related Workmentioning

confidence: 99%

Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints

Wang

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Text generation from a knowledge base aims to translate knowledge triples to naturallanguage descriptions. Most existing methods ignore the faithfulness between a generated text description and the original table, leading to generated information that goes beyond the content of the table. In this paper, for the first time, we propose a novel Transformerbased generation framework to achieve the goal. The core techniques in our method to enforce faithfulness include a new table-text optimal-transport matching loss and a tabletext embedding similarity loss based on the Transformer model. Furthermore, to evaluate faithfulness, we propose a new automatic metric specialized to the table-to-text generation problem. We also provide detailed analysis on each component of our model in our experiments. Automatic and human evaluations show that our framework can significantly outperform state-of-the-art by a large margin.

show abstract

Enhancing Neural Data-To-Text Generation Models with External Background Knowledge

Cited by 24 publications

References 21 publications

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation

Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints

Contact Info

Product

Resources

About