1 |
Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Question-Based Salient Span Selection for More Controllable Text Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
What is Your Article Based On? Inferring Fine-grained Provenance ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
BabyBERTa: Learning More Grammar With Small-Scale Child-Directed Language ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
{Z}ero-shot {L}abel-Aware {E}vent {T}rigger and {A}rgument {C}lassification ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Do We Know What We Don't Know? Studying Unanswerable Questions beyond SQuAD 2.0 ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Extending Multilingual BERT to Low-Resource Languages ...
|
|
|
|
Abstract:
Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success has focused only on the top 104 languages in Wikipedia that it was trained on. In this paper, we propose a simple but effective approach to extend M-BERT (E-BERT) so that it can benefit any new language, and show that our approach benefits languages that are already in M-BERT as well. We perform an extensive set of experiments with Named Entity Recognition (NER) on 27 languages, only 16 of which are in M-BERT, and show an average increase of about 6% F1 on languages that are already in M-BERT and 23% F1 increase on new languages. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2004.13640 https://dx.doi.org/10.48550/arxiv.2004.13640
|
|
BASE
|
|
Hide details
|
|
15 |
Cross-lingual Entity Alignment with Incidental Supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
TransOMCS: From Linguistic Graphs to Commonsense Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Extending Wikification: Nominal discovery, nominal linking, and the grounding of nouns
|
|
|
|
BASE
|
|
Show details
|
|
|
|