Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 to Improve Lexical Faithfulness and Vocabulary Accuracy
Control-DAG introduces constrained decoding algorithms for Directed Acyclic T5 (DA-T5), a non-autoregressive text generation model, to address key limitations such as frequent out-of-vocabulary errors and inability to faithfully generate entity names. The proposed methods incorporate lexical, vocabulary, and length constraints to significantly enhance DA-T5's performance on Task-Oriented Dialogue and Data-to-Text generation tasks.
Advancements in Neural Data-to-Text Generation: A Comprehensive Survey
This survey offers a consolidated view of the neural data-to-text (D2T) paradigm, examining the latest approaches, benchmark datasets, and evaluation protocols. It highlights promising avenues for D2T research that focus on linguistic capabilities as well as fairness and accountability.
SemEval-2024 Task 6: Hallucination Detection with Synthetic Data for LLM
최신 언어 생성 모델에서 발생하는 환각을 감지하기 위해 합성 데이터를 활용하는 방법 소개
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder
VOLTAは、TransformerとVAEを組み合わせて生成的多様性を向上させる革新的なフレームワークです。
Evaluation of NLG Systems: Reference vs. Reference-Free Metrics
Reference-free metrics show higher correlation with human judgment and sensitivity to language quality deficiencies compared to reference-based metrics.
Improving Generative Diversity in Natural Language Generation with VOLTA Framework
VOLTA introduces a novel framework that enhances generative diversity in natural language generation by combining Transformer models with VAE and InfoGAN, improving quality while maintaining diversity.
© 2024 by Linnk AI