1 |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
SpanNER: Named Entity Re-/Recognition as Span Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Align Voting Behavior with Public Statements for Legislator Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
{K-Adapter}: {I}nfusing {K}nowledge into {P}re-{T}rained {M}odels with {A}dapters ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Classifying Dyads for Militarized Conflict Analysis
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Efficient Sampling of Dependency Structure
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Searching for More Efficient Dynamic Programs
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 (2021)
|
|
BASE
|
|
Show details
|
|
11 |
“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 (2021)
|
|
BASE
|
|
Show details
|
|
12 |
A Bayesian Framework for Information-Theoretic Probing
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
Abstract:
Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactly the same information about a target task as the original sentences. The mutual information, however, assumes the true probability distribution of a pair of random variables is known, leading to unintuitive results in settings where it is not. This paper proposes a new framework to measure what we term Bayesian mutual information, which analyses information from the perspective of Bayesian agents—allowing for more intuitive findings in scenarios with finite data. For instance, under Bayesian MI we have that data can add information, processing can help, and information can hurt, which makes it more intuitive for machine learning applications. Finally, we apply our framework to probing where we believe Bayesian mutual information naturally operationalises ease of extraction by explicitly limiting the available background knowledge to solve a task.
|
|
URL: https://doi.org/10.3929/ethz-b-000518995 https://hdl.handle.net/20.500.11850/518995
|
|
BASE
|
|
Hide details
|
|
13 |
Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Come hither or go away? Recognising pre-electoral coalition signals in the news
|
|
|
|
BASE
|
|
Show details
|
|
|
|