1 |
Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
CLICKER: A Computational LInguistics Classification Scheme for Educational Resources ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning ...
|
|
Tang, Xiangru; Nair, Arjun; Wang, Borui; Wang, Bingyao; Desai, Jai; Wade, Aaron; Li, Haoran; Celikyilmaz, Asli; Mehdad, Yashar; Radev, Dragomir. - : arXiv, 2021
|
|
Abstract:
Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated content are found during the human evaluation. Pre-trained models are most commonly fine-tuned with cross-entropy loss for text summarization, which may not be an optimal strategy. In this work, we provide a typology of factual errors with annotation data to highlight the types of errors and move away from a binary understanding of factuality. We further propose a training strategy that improves the factual consistency and overall quality of summaries via a novel contrastive fine-tuning, called ConFiT. Based on our linguistically-informed typology of errors, we design different modular objectives that each target a specific type. Specifically, we utilize hard negative samples with errors to reduce the generation of factual inconsistency. In order to capture the key ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2112.08713 https://arxiv.org/abs/2112.08713
|
|
BASE
|
|
Hide details
|
|
5 |
ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The CL-SciSumm Shared Task 2018: Results and Key Insights ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Selecting and Generating Computational Meaning Representations for Short Texts
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Robust Multilingual Part-of-Speech Tagging via Adversarial Training ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Classifying Syntactic Regularities for Hundreds of Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Predicting the impact of scientific concepts using full‐text features
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Sentence simplification, compression, and disaggregation for summarization of sophisticated documents
|
|
|
|
BASE
|
|
Show details
|
|
|
|