DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7 8...63
Hits 61 – 80 of 1.259

61
TexSmart: A System for Enhanced Natural Language Understanding ...
BASE
Show details
62
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
BASE
Show details
63
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images ...
BASE
Show details
64
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach ...
BASE
Show details
65
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search ...
BASE
Show details
66
DALC: the Dutch Abusive Language Corpus ...
BASE
Show details
67
Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition ...
BASE
Show details
68
VL-BERT+: Detecting Protected Groups in Hateful Multimodal Memes ...
BASE
Show details
69
Attention-based Contextual Language Model Adaptation for Speech Recognition ...
BASE
Show details
70
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech ...
BASE
Show details
71
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning ...
BASE
Show details
72
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification ...
BASE
Show details
73
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ...
BASE
Show details
74
Evidence-based Factual Error Correction ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-long.256 Abstract: This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to correct written texts that are refuted or only partially supported by evidence. We demonstrate that it is feasible to train factual error correction systems from existing fact checking datasets which only contain labeled claims accompanied by evidence, but not the correction. We achieve this by employing a two-stage distant supervision approach that incorporates evidence into masked claims when generating corrections. Our approach, based on the T5 transformer and using retrieved evidence, achieved better results than existing work which used a pointer copy network and gold evidence, producing accurate factual error corrections for 5x more instances in human evaluation and a .125 increase in SARI score. The ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://dx.doi.org/10.48448/xtb3-ns52
https://underline.io/lecture/25592-evidence-based-factual-error-correction
BASE
Hide details
75
SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images ...
BASE
Show details
76
A DQN-based Approach to Finding Precise Evidences for Fact Verification ...
BASE
Show details
77
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event ...
BASE
Show details
78
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification ...
BASE
Show details
79
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection ...
BASE
Show details
80
2A: Sentiment Analysis, Stylistic Analysis, and Argument Mining #1 ...
BASE
Show details

Page: 1 2 3 4 5 6 7 8...63

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
1.259
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern