MovieChats: Chat like Humans in a Closed Domain

Su, Hui; Shen, Xiaoyu; Zhang, Xiao; Zhang, Zheng; Chang, Ernie; Zhang, Cheng; Niu, Cheng; Zhou, Jie

doi:10.18653/v1/2020.emnlp-main.535

Cited by 24 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The threshold for determining the matched category is set to 0.6. When training the model, dropout [16] and early-stopping [6,36] are used to alleviate the over-fitting phenomenon. We use cross-entropy loss function and the Adam optimizer [20] to optimize parameters.…”

Section: Multi-level Matching Network (Mlmn)mentioning

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

Section: Multi-level Matching Network (Mlmn)mentioning

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

show abstract

“…Leveraging a single unified text-to-text Transformer has also been applied in other NLP tasks like dialogue generation [43], [44] and question answering [45]. We adopt a similar approach in our work and further show its flexibility of enabling effective dependency learning.…”

Section: Related Workmentioning

confidence: 99%

Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer

Yunyun¹,

Shen²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Given the fact of a case, Legal Judgment Prediction (LJP) involves a series of sub-tasks such as predicting violated law articles, charges and term of penalty. We propose leveraging a unified text-to-text Transformer for LJP, where the dependencies among sub-tasks can be naturally established within the auto-regressive decoder. Compared with previous works, it has three advantages: (1) it fits in the pretraining pattern of masked language models, and thereby can benefit from the semantic prompts of each sub-task rather than treating them as atomic labels, (2) it utilizes a single unified architecture, enabling full parameter sharing across all sub-tasks, and (3) it can incorporate both classification and generative sub-tasks. We show that this unified transformer, albeit pretrained on general-domain text, outperforms pretrained models tailored specifically for the legal domain. Through an extensive set of experiments, we find that the best order to capture dependencies is different from human intuitions, and the most reasonable logical order for humans can be sub-optimal for the model. We further include two more auxiliary tasks: court view generation and article content prediction, showing they can not only improve the prediction accuracy, but also provide interpretable explanations for model outputs even when an error is made. With the best configuration, our model outperforms both previous SOTA and a single-tasked version of the unified transformer by a large margin. Code and dataset are available at https://github.com/oli-yun/Dependency-LJP.

show abstract

“…We will also provide human evaluation scores on the system outputs since none of the automatic metrics can correlate perfectly with the generation quality. We will follow the recently proposed taxonomy of human evaluation measures by Belz et al (2020); Su et al (2020) and follow the reporting strategies proposed by Howcroft et al (2020). The human evaluation will be focused on the following two parts, which are specifically hard to be accurately measured by automatic metrics:…”

Section: Human Evaluationmentioning

confidence: 99%

The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation

Chang,

Shen,

Marin

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a shared task on training instance selection for few-shot neural text generation. Large-scale pretrained language models have led to dramatic improvements in few-shot text generation. Nonetheless, almost all previous work simply applies random sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance.The study of the selection strategy can help us to (1) make the most use of our annotation budget in downstream tasks and (2) better benchmark few-shot text generative models. We welcome submissions that present their selection strategies and the effects on the generation quality.

show abstract

MovieChats: Chat like Humans in a Closed Domain

Cited by 24 publications

References 36 publications

Learning Fine-grained Fact-Article Correspondence in Legal Cases

Learning Fine-grained Fact-Article Correspondence in Legal Cases

Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer

The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation

Contact Info

Product

Resources

About