1 |
Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Graph Algorithms for Multiparallel Word Alignment
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Measuring and Improving Consistency in Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Continuous Entailment Patterns for Lexical Inference in Context ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Measuring and Improving Consistency in Pretrained Language Models
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1012-1031 (2021) (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1408-1424 (2021) (2021)
|
|
Abstract:
Abstract⚠ This paper contains prompts and model outputs that are offensive in nature.When trained on large, unfiltered crawls from the Internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: They often generate racist, sexist, violent, or otherwise toxic language. As large models require millions of training examples to achieve good performance, it is difficult to completely prevent them from being exposed to such content. In this paper, we first demonstrate a surprising finding: Pretrained language models recognize, to a considerable degree, their undesirable biases and the toxicity of the content they produce. We refer to this capability as self-diagnosis. Based on this finding, we then propose a decoding algorithm that, given only a textual description of the undesired behavior, reduces the probability of a language model producing problematic text. We refer to this approach as self-debiasing. Self-debiasing does not rely on manually curated word lists, nor does it require any training data or changes to the model’s parameters. While we by no means eliminate the issue of language models generating biased text, we believe our approach to be an important step in this direction.1
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/7865d581bc554481bb1d3d28fe5f98e4 https://doi.org/10.1162/tacl_a_00434
|
|
BASE
|
|
Hide details
|
|
15 |
SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings
|
|
|
|
In: EMNLP 2020 ; https://hal.archives-ouvertes.fr/hal-03013194 ; EMNLP 2020, Association for Computational Linguistics, Nov 2020, Online, United States. pp.1627 - 1643 (2020)
|
|
BASE
|
|
Show details
|
|
16 |
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly
|
|
|
|
BASE
|
|
Show details
|
|
18 |
BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Predicting the Growth of Morphological Families from Social and Linguistic Factors
|
|
|
|
BASE
|
|
Show details
|
|
|
|