22 |
Semantic Comparisons for Natural Language Processing Applications
|
|
|
|
BASE
|
|
Show details
|
|
23 |
Challenges in Automated Debiasing for Toxic Language Detection
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Evaluating Models' Local Decision Boundaries via Contrast Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
28 |
Grounded Compositional Outputs for Adaptive Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Multilingual and Interlingual Semantic Representations for Natural Language Processing: A Brief Introduction
|
|
|
|
In: Computational Linguistics, Vol 46, Iss 2, Pp 249-255 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
30 |
Polyglot Contextual Representations Improve Crosslingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Situating Sentence Embedders with Nearest Neighbor Overlap ...
|
|
|
|
BASE
|
|
Show details
|
|
32 |
Low-Resource Parsing with Crosslingual Contextualized Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
35 |
Measuring Online Debaters’ Persuasive Skill from Text over Time
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 537-550 (2019) (2019)
|
|
BASE
|
|
Show details
|
|
36 |
Empirical Risk Minimization for Probabilistic Grammars: Sample Complexity and Hardness of Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Nonparametric Word Segmentation for Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
38 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
39 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
40 |
Polyglot Semantic Role Labeling ...
|
|
|
|
Abstract:
Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages. We experiment with a new approach where we combine resources from a pair of languages in the CoNLL 2009 shared task to build a polyglot semantic role labeler. Notwithstanding the absence of parallel data, and the dissimilarity in annotations between languages, our approach results in an improvement in SRL performance on multiple languages over a monolingual baseline. Analysis of the polyglot model shows it to be advantageous in lower-resource settings. ... : To appear at ACL 2018 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1805.11598 https://dx.doi.org/10.48550/arxiv.1805.11598
|
|
BASE
|
|
Hide details
|
|
|
|