Page: 1 2 3 4 5 6 7 8 9... 48
82 |
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline ...
|
|
|
|
BASE
|
|
Show details
|
|
84 |
Fine-grained Factual Consistency Assessment for Abstractive Summarization Models ...
|
|
|
|
BASE
|
|
Show details
|
|
85 |
Modeling Endorsement for Multi-Document Abstractive Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
86 |
COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images ...
|
|
|
|
BASE
|
|
Show details
|
|
87 |
Are We Summarizing the Right Way? A Survey of Dialogue Summarization Data Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
88 |
A Large-Scale Dataset for Empathetic Response Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
90 |
Knowledge and Keywords Augmented Abstractive Sentence Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior ...
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
93 |
Sentence-level Planning for Especially Abstractive Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
94 |
Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.599/ Abstract: Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging. Previous work has typically focused on a single task and developed individual evaluation metrics based on specific intuitions. In this paper, we propose a unifying perspective based on the nature of information change in NLG tasks, including compression (e.g., summarization), transduction (e.g., text rewriting), and creation (e.g., dialog). Information alignment between input, context, and output text plays a common central role in characterizing the generation. With automatic alignment prediction models, we develop a family of interpretable metrics that are suitable for evaluating key aspects of different NLG tasks, often without need of gold reference data. Experiments show the uniformly designed ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural language generation; Natural Language Processing; Text Summarization
|
|
URL: https://dx.doi.org/10.48448/39mx-d326 https://underline.io/lecture/38012-compression,-transduction,-and-creation-a-unified-framework-for-evaluating-natural-language-generation
|
|
BASE
|
|
Hide details
|
|
100 |
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 48
|
|