DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7 8 9 10...41
Hits 101 – 120 of 812

101
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them ...
BASE
Show details
102
Good-Enough Example Extrapolation ...
BASE
Show details
103
To what extent do human explanations of model behavior align with actual model behavior? ...
BASE
Show details
104
Sequence Length is a Domain: Length-based Overfitting in Transformer Models ...
BASE
Show details
105
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations ...
BASE
Show details
106
Effective Sequence-to-Sequence Dialogue State Tracking ...
BASE
Show details
107
An Investigation into the Contribution of Locally Aggregated Descriptors to Figurative Language Identification ...
BASE
Show details
108
Solving Aspect Category Sentiment Analysis as a Text Generation Task ...
BASE
Show details
109
Discourse-Driven Integrated Dialogue Development Environment for Open-Domain Dialogue Systems ...
BASE
Show details
110
Context or No Context? A preliminary exploration of human-in-the-loop approach for Incremental Temporal Summarization in meetings ...
BASE
Show details
111
Learning Data Augmentation Schedules for Natural Language Processing ...
BASE
Show details
112
Locke's Holiday: Belief Bias in Machine Reading ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.649/ Abstract: I highlight a simple failure mode of state-of- the-art machine reading systems: when contexts do not align with commonly shared beliefs. For example, machine reading systems fail to answer "What did Elizabeth want?" correctly in the context of ’My kingdom for a cough drop, cried Queen Elizabeth.’ Biased by co-occurrence statistics in the training data of pretrained language models, systems predict 'my kingdom', rather than 'a cough drop'. I argue such biases are analogous to human belief biases and present a carefully designed challenge dataset for English machine reading, called AUTO-LOCKE, to quantify such effects. Evaluations of machine reading systems on AUTO-LOCKE show the pervasiveness of be- lief bias in machine reading. ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://underline.io/lecture/37792-locke's-holiday-belief-bias-in-machine-reading
https://dx.doi.org/10.48448/t4tt-2j38
BASE
Hide details
113
Searching for More Efficient Dynamic Programs ...
BASE
Show details
114
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification ...
BASE
Show details
115
Improving Synonym Recommendation Using Sentence Context ...
BASE
Show details
116
Debiasing Methods in Natural Language Understanding Make Bias More Accessible ...
BASE
Show details
117
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks ...
BASE
Show details
118
SPECTRA: Sparse Structured Text Rationalization ...
BASE
Show details
119
Unsupervised Contextualized Document Representation ...
BASE
Show details
120
Layer-wise Model Pruning based on Mutual Information ...
BASE
Show details

Page: 1 2 3 4 5 6 7 8 9 10...41

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
812
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern