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 |
Challenges in Automated Debiasing for Toxic Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Evaluating Models' Local Decision Boundaries via Contrast Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Grounded Compositional Outputs for Adaptive Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Polyglot Contextual Representations Improve Crosslingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Situating Sentence Embedders with Nearest Neighbor Overlap ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Low-Resource Parsing with Crosslingual Contextualized Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Shallow Syntax in Deep Water ...
|
|
|
|
Abstract:
Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain. We investigate the role of shallow syntax-aware representations for NLP tasks using two techniques. First, we enhance the ELMo architecture to allow pretraining on predicted shallow syntactic parses, instead of just raw text, so that contextual embeddings make use of shallow syntactic context. Our second method involves shallow syntactic features obtained automatically on downstream task data. Neither approach leads to a significant gain on any of the four downstream tasks we considered relative to ELMo-only baselines. Further analysis using black-box probes confirms that our shallow-syntax-aware contextual embeddings do not transfer to linguistic tasks any more easily than ELMo's embeddings. We take these findings as evidence that ELMo-style pretraining discovers representations which make additional awareness of shallow syntax redundant. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1908.11047 https://arxiv.org/abs/1908.11047
|
|
BASE
|
|
Hide details
|
|
17 |
Empirical Risk Minimization for Probabilistic Grammars: Sample Complexity and Hardness of Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Nonparametric Word Segmentation for Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|