1 |
Delving Deeper into Cross-lingual Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Combating Temporal Drift in Crisis with Adapted Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Annotation Curricula to Implicitly Train Non-Expert Annotators ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03020314 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2020, 8, ⟨10.1162/tacl_a_00332⟩ (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation ...
|
|
|
|
Abstract:
Sentence encoders map sentences to real valued vectors for use in downstream applications. To peek into these representations - e.g., to increase interpretability of their results - probing tasks have been designed which query them for linguistic knowledge. However, designing probing tasks for lesser-resourced languages is tricky, because these often lack large-scale annotated data or (high-quality) dependency parsers as a prerequisite of probing task design in English. To investigate how to probe sentence embeddings in such cases, we investigate sensitivity of probing task results to structural design choices, conducting the first such large scale study. We show that design choices like size of the annotated probing dataset and type of classifier used for evaluation do (sometimes substantially) influence probing outcomes. We then probe embeddings in a multilingual setup with design choices that lie in a 'stable region', as we identify for English, and find that results on English do not transfer to other ... : Accepted for Publication at CONLL 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2006.09109 https://dx.doi.org/10.48550/arxiv.2006.09109
|
|
BASE
|
|
Hide details
|
|
13 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Predicting the Humorousness of Tweets Using Gaussian Process Preference Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
PuzzLing Machines: A Challenge on Learning From Small Data ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
A Matter of Framing: The Impact of Linguistic Formalism on Probing Results ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Empowering Active Learning to Jointly Optimize System and User Demands ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|