1 |
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Specializing Multilingual Language Models: An Empirical Study ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Measuring Association Between Labels and Free-Text Rationales ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Promoting Graph Awareness in Linearized Graph-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Challenges in Automated Debiasing for Toxic Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Competency Problems: On Finding and Removing Artifacts in Language Data ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Semantic Comparisons for Natural Language Processing Applications
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Challenges in Automated Debiasing for Toxic Language Detection
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings ...
|
|
|
|
Abstract:
We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model via self-training. We validate our technique by extracting parallel sentence pairs on the BUCC 2017 bitext mining task and observe up to a 24.5 point increase (absolute) in F1 scores over previous unsupervised methods. We then improve an XLM-based unsupervised neural MT system pre-trained on Wikipedia by supplementing it with pseudo-parallel text mined from the same corpus, boosting unsupervised translation performance by up to 3.5 BLEU on the WMT'14 French-English and WMT'16 German-English tasks and outperforming the previous state-of-the-art. Finally, we enrich the IWSLT'15 English-Vietnamese corpus with pseudo-parallel Wikipedia sentence pairs, yielding a 1.2 BLEU improvement on the low-resource MT task. We demonstrate that unsupervised bitext mining is an effective way ... : To appear in the Transactions of the Association for Computational Linguistics ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2010.07761 https://dx.doi.org/10.48550/arxiv.2010.07761
|
|
BASE
|
|
Hide details
|
|
19 |
Evaluating Models' Local Decision Boundaries via Contrast Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Grounded Compositional Outputs for Adaptive Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|