A comprehensive study: Sentence compression with linguistic knowledge-enhanced gated neural network

Zhao, Yang; Shen, Xiaoyu; Senuma, Hajime; Aizawa, Akiko

doi:10.1016/j.datak.2018.05.007

Cited by 8 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it underperforms the neural attention baseline as for generation. Our model is also in spirit related to recent attempts at separating content planning and surface realization in neural data-to-text models (Zhao et al, 2018;Puduppully et al, 2019;Moryossef et al, 2019;Ferreira et al, 2019). Nonetheless, all of them resort to manual annotations or hand-engineered rules applicable only for a narrow domain.…”

Section: Related Workmentioning

confidence: 98%

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

Shen

Chang²,

Su³

et al. 2020

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

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 98%

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

Shen

Chang²,

Su³

et al. 2020

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Adding additional knowledge is also popular in NLP models [10,28,49,51]. It can be applied as a kind of feature enrichment.…”

Section: Related Workmentioning

confidence: 99%

Learning Fine-grained Fact-Article Correspondence in Legal Cases

Ge¹,

huang²,

Shen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Automatically recommending relevant law articles to a given legal case has attracted much attention as it can greatly release human labor from searching over the large database of laws. However, current researches only support coarse-grained recommendation where all relevant articles are predicted as a whole without explaining which specific fact each article is relevant with. Since one case can be formed of many supporting facts, traversing over them to verify the correctness of recommendation results can be timeconsuming. We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system. With this motivation, we perform a pioneering study and create a corpus with manually annotated factarticle correspondences. We treat the learning as a text matching task and propose a multi-level matching network to address it. To help the model better digest the content of law articles, we parse articles in form of premise-conclusion pairs with random forest. Experiments show that the parsed form yielded better performance and the resulting model surpassed other popular text matching baselines. Furthermore, we compare with previous researches and find that establishing the fine-grained fact-article correspondences can improve the recommendation accuracy by a large margin. Our best system reaches an F1 score of 96.3%, making it of great potential for practical use. It can also significantly boost the downstream

show abstract

“…The second class seeks to bring in extra information into existing corpus like structured knowledge (Zhao et al, 2018;Ghazvininejad et al, 2018;Dinan et al, 2019), personal information (Li et al, 2016b;Zhang et al, 2018a) or emotions (Shen et al, 2017b;Zhou et al, 2018). However, corpus with such annotations can be extremely costly to obtain and is usually limited to a specific domain with small data size.…”

Section: Related Workmentioning

confidence: 99%

Diversifying Dialogue Generation with Non-Conversational Text

Shen

Zhao

et al. 2020

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

Self Cite

View full text Add to dashboard Cite

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the lowdiversity problem when it comes to opendomain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our daily chitchat, avoiding them to generate more interesting responses requires complex data filtering, sampling techniques or modifying the training objective.In this paper, we propose a new perspective to diversify dialogue generation by leveraging non-conversational text. Compared with bilateral conversations, nonconversational text are easier to obtain, more diverse and cover a much broader range of topics. We collect a large-scale nonconversational corpus from multi sources including forum comments, idioms and book snippets.We further present a training paradigm to effectively incorporate these text via iterative back translation. The resulting model is tested on two conversational datasets and is shown to produce significantly more diverse responses without sacrificing the relevance with context.

show abstract

A comprehensive study: Sentence compression with linguistic knowledge-enhanced gated neural network

Cited by 8 publications

References 29 publications

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

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

Learning Fine-grained Fact-Article Correspondence in Legal Cases

Diversifying Dialogue Generation with Non-Conversational Text

Contact Info

Product

Resources

About