1 |
Pushing the right buttons: adversarial evaluation of quality estimation
|
|
|
|
In: Proceedings of the Sixth Conference on Machine Translation ; 625 ; 638 (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A Generative Framework for Simultaneous Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Continual Quality Estimation with Online Bayesian Meta-Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
SentSim: Crosslingual Semantic Evaluation of Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
What Makes a Scientific Paper be Accepted for Publication? ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
MultiSubs: A Large-scale Multimodal and Multilingual Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
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
|
|
14 |
Classifying Dyads for Militarized Conflict Analysis
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Efficient Sampling of Dependency Structure
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
16 |
Searching for More Efficient Dynamic Programs
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 (2021)
|
|
Abstract:
Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic programming and are not always unique. Finding one with optimal asymptotic runtime can be unintuitive, time-consuming, and error-prone. Our work aims to automate this laborious process. Given an initial correct declarative program, we search for a sequence of semantics-preserving transformations to improve its running time as much as possible. To this end, we describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a heuristic search procedure to improve this metric. We show that in practice, automated search—like the mental search performed by human programmers—can find substantial improvements to the initial program. Empirically, we show that many speed-ups described in the NLP literature could have been discovered automatically by our system.
|
|
URL: https://hdl.handle.net/20.500.11850/518987 https://doi.org/10.3929/ethz-b-000518987
|
|
BASE
|
|
Hide details
|
|
17 |
“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
|
|
18 |
A Bayesian Framework for Information-Theoretic Probing
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
19 |
Findings of the WMT 2021 Shared Task on Quality Estimation ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|