1 |
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Human-like informative conversations: Better acknowledgements using conditional mutual information ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Biomedical and clinical English model packages for the Stanza Python NLP library
|
|
|
|
In: J Am Med Inform Assoc (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Finding Universal Grammatical Relations in Multilingual BERT ...
|
|
|
|
Abstract:
Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually. To better understand this overlap, we extend recent work on finding syntactic trees in neural networks' internal representations to the multilingual setting. We show that subspaces of mBERT representations recover syntactic tree distances in languages other than English, and that these subspaces are approximately shared across languages. Motivated by these results, we present an unsupervised analysis method that provides evidence mBERT learns representations of syntactic dependency labels, in the form of clusters which largely agree with the Universal Dependencies taxonomy. This evidence suggests that even without explicit supervision, multilingual masked language models learn certain linguistic universals. ... : To appear in ACL 2020; Farsi typo corrected ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.7; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2005.04511 https://arxiv.org/abs/2005.04511
|
|
BASE
|
|
Hide details
|
|
10 |
CoQA: A Conversational Question Answering Challenge
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 249-266 (2019) (2019)
|
|
BASE
|
|
Show details
|
|
12 |
Arc-swift: A Novel Transition System for Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Improving Coreference Resolution by Learning Entity-Level Distributed Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
A large annotated corpus for learning natural language inference ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Text to 3D Scene Generation with Rich Lexical Grounding ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Learning Distributed Word Representations for Natural Logic Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Discovery of Deep Structure from Unlabeled Data
|
|
|
|
In: DTIC (2014)
|
|
BASE
|
|
Show details
|
|
20 |
Induced lexico-syntactic patterns improve information extraction from online medical forums
|
|
|
|
BASE
|
|
Show details
|
|
|
|