Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task
We explore the use of self-training and acceptability classifiers with pre-trained models for natural language generation in structure-to-text settings using three GEM datasets (E2E, WebNLG-en, Schema-Guided Dialog). With the Schema-Guided Dialog dataset, we also experiment with including multiple turns of context in the input. We find that self-training with reconstruction matching along with acceptability classifier filtering can improve semantic correctness, though gains are limited in the full-data setting. With context-conditioning, we find that including multiple turns in the context encourages the model to align with the user’s word and phrasing choices as well as to generate more self-consistent responses. In future versions of the GEM challenge, we encourage the inclusion of few-shot tracks to encourage research on data efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
Free-text explanations are expressive and easy to understand, but many datasets lack annotated explanation data, making it challenging to train models for explainable predictions. To address this, we investigate how to u…
Abstractive Text SummarizationExplanation GenerationFact CheckingHallucination+1Building Adaptive Acceptability Classifiers for Neural NLG
We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches. An NL…
SentenceSynthetic Data GenerationText GenerationFrom Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences
Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on training corpora to reflect distribution…
DecoderThe Influence of Context on Sentence Acceptability Judgements
We investigate the influence that document context exerts on human acceptability judgements for English sentences, via two sets of experiments. The first compares ratings for sentences presented on their own with ratings…
Language ModelingLanguage ModellingMachine TranslationSentence+1RuCoLA: Russian Corpus of Linguistic Acceptability
Linguistic acceptability (LA) attracts the attention of the research community due to its many uses, such as testing the grammatical knowledge of language models and filtering implausible texts with acceptability classif…
Linguistic AcceptabilityText Generation