paper-with-me

홈 › Papers

Adversarial NLI for Factual Correctness in Text Summarisation Models

2020-05-24 · Mario Barrantes, Benedikt Herudek, Richard Wang

We apply the Adversarial NLI dataset to train the NLI model and show that the model has the potential to enhance factual correctness in abstract summarization. We follow the work of Falke et al. (2019), which rank multiple generated summaries based on the entailment probabilities between an source document and summaries and select the summary that has the highest entailment probability. The authors' earlier study concluded that current NLI models are not sufficiently accurate for the ranking task. We show that the Transformer models fine-tuned on the new dataset achieve significantly higher accuracy and have the potential of selecting a coherent summary.

📄 PDF Abstract BibTeX arXiv:2005.11739

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation

2023-09-21 · Jennifer A Bishop, Qianqian Xie, Sophia Ananiadou

Maintaining factual consistency is a critical issue in abstractive text summarisation, however, it cannot be assessed by traditional automatic metrics used for evaluating text summarisation, such as ROUGE scoring. Recent…

The Exploration of Knowledge-Preserving Prompts for Document Summarisation

2023-01-27 · Chen Chen, Wei Emma Zhang, Alireza Seyed Shakeri, Makhmoor Fiza

Despite the great development of document summarisation techniques nowadays, factual inconsistencies between the generated summaries and the original texts still occur from time to time. This study explores the possibili…

Document Summarization

Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour

2025-05-23 · Bálint Gyevnár, Christopher G. Lucas, Stefano V. Albrecht, Shay B. Cohen

Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks like miscoordination and goal misalignment. Explainability is vital for trust calibration, but explainabl…

Autonomous DrivingcounterfactualPrediction

Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning

2023-06-06 · Peggy Tang, Junbin Gao, Lei Zhang, Zhiyong Wang

Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation. However, most existing compressive sum…

Hallucinationreinforcement-learning

Unsupervised Compressive Text Summarisation with Reinforcement Learning

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation. However, most existing compressive sum…

Hallucinationreinforcement-learningReinforcement LearningReinforcement Learning (RL)