Neural Data-to-Text Generation with LM-based Text Augmentation

Chang, Ernie; Shen, Xiaoyu; Zhu, Dawei; Demberg, Vera; Su, Hui

doi:10.18653/v1/2021.eacl-main.64

Cited by 31 publications

(15 citation statements)

References 34 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Du and Black, 2018) or paraphrasing-based methods (Niu and Bansal, 2019;Li et al, 2019;Cai et al, 2020;Zhang et al, 2020a;Xie et al, 2022;Cao et al, 2022). Another line of work (Chang et al, 2021;Schick and Schütze, 2021;Zheng et al, 2022) is exploiting large-scale pretrained language models for data augmentation. However, these existing methods do not focus on creating semantically different responses.…”

Section: Further Discussionmentioning

confidence: 99%

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues

Ou¹,

Zhang²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting high-quality such a dataset in most scenarios is labor-intensive and timeconsuming. In this paper, we propose a data augmentation method to automatically augment high-quality responses with different semantics by counterfactual inference. Specifically, given an observed dialogue, our counterfactual generation model first infers semantically different responses by replacing the observed reply perspective with substituted ones. Furthermore, our data selection method filters out detrimental augmented responses. Experimental results show that our data augmentation method can augment high-quality responses with different semantics for a given dialogue history, and can outperform competitive baselines on multiple downstream tasks.

show abstract

Section: Further Discussionmentioning

confidence: 99%

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues

Ou¹,

Zhang²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, to obtain the hidden state, (7) and the updated cell state tanh are used. The (8) obtains the maximum score as an output for the prediction.…”

Section: Methods and Implementation Of The Casementioning

confidence: 99%

“…They also proposed several methods for extracting context vectors. Similarly, Chang et al [8] proposed an approach that automatically augments the data available for training by generating new text samples based on the GPT-2, and proposed to match the new text samples with the data. The Buddana et al [9] created a model describing the design and operation of text generation, for which they used LSTM as an innovative solution for handling sequential data and text data in particular.…”

Section: Related Workmentioning

confidence: 99%

Text prediction recurrent neural networks using long short-term memory-dropout

Iparraguirre-Villanueva¹,

Guevara-Ponce²,

Ruiz-Alvarado³

et al. 2023

IJEECS

View full text Add to dashboard Cite

Unit short-term memory (LSTM) is a type of recurrent neural network (RNN) whose sequence-based models are being used in text generation and/or prediction tasks, question answering, and classification systems due to their ability to learn long-term dependencies. The present research integrates the LSTM network and dropout technique to generate a text from a corpus as input, a model is developed to find the best way to extract the words from the context. For training the model, the poem "La Ciudad y los perros" which is composed of 128,600 words is used as input data. The poem was divided into two data sets, 38.88% for training and the remaining 61.12% for testing the model. The proposed model was tested in two variants: word importance and context. The results were evaluated in terms of the semantic proximity of the generated text to the given context.

show abstract

“…For the generation of court view, we can take them as text generation problems, such as BLEU-1, BLEU-2, BLEU-N, ROUGE-1, ROUGE-2, ROUGE-L and BERT SCORE [71,72,73,74,34,75,76,77]. The following evaluation metrics to evaluate the performance of LJP text generation are summarized, as shown in Fig.…”

Section: Evaluation Of Text Generationmentioning

confidence: 99%

A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges

Cui¹,

Shen²,

Nie³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Legal judgment prediction (LJP) applies Natural Language Processing (NLP) techniques to predict judgment results based on fact descriptions automatically. Recently, large-scale public datasets and advances in NLP research have led to increasing interest in LJP. Despite a clear gap between machine and human performance, impressive results have been achieved in various benchmark datasets. In this paper, to address the current lack of comprehensive survey of existing LJP tasks, datasets, models and evaluations, (1) we analyze 31 LJP datasets in 6 languages, present their construction process and define a classification method of LJP with 3 different attributes;(2) we summarize 14 evaluation metrics under four categories for different outputs of LJP tasks; (3) we review 12 legal-domain pretrained models in 3 languages and highlight 3 major research directions for LJP; (4) we show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges. This paper can provide up-to-date and comprehensive reviews to help readers understand the status of LJP. We hope to facilitate both NLP researchers and legal professionals for further joint efforts in this problem.

show abstract

Neural Data-to-Text Generation with LM-based Text Augmentation

Cited by 31 publications

References 34 publications

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues

Text prediction recurrent neural networks using long short-term memory-dropout

A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges

Contact Info

Product

Resources

About