DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6
Hits 61 – 80 of 116

61
Universal Phone Recognition with a Multilingual Allophone System ...
BASE
Show details
62
The Return of Lexical Dependencies: Neural Lexicalized PCFGs ...
BASE
Show details
63
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization ...
BASE
Show details
64
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models ...
BASE
Show details
65
AlloVera: a multilingual allophone database
In: LREC 2020: 12th Language Resources and Evaluation Conference ; https://halshs.archives-ouvertes.fr/halshs-02527046 ; LREC 2020: 12th Language Resources and Evaluation Conference, European Language Resources Association, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/ (2020)
BASE
Show details
66
How Can We Know What Language Models Know?
In: Transactions of the Association for Computational Linguistics, Vol 8, Pp 423-438 (2020) (2020)
Abstract: Recent work has presented intriguing results examining the knowledge contained in language models (LMs) by having the LM fill in the blanks of prompts such as “ Obama is a __ by profession”. These prompts are usually manually created, and quite possibly sub-optimal; another prompt such as “ Obama worked as a __ ” may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github.com/jzbjyb/LPAQA .
Keyword: Computational linguistics. Natural language processing; P98-98.5
URL: https://doaj.org/article/861ecb5d6ec2467287cf263aa94e6a75
https://doi.org/10.1162/tacl_a_00324
BASE
Hide details
67
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
In: Transactions of the Association for Computational Linguistics, Vol 8, Pp 109-124 (2020) (2020)
BASE
Show details
68
A Bilingual Generative Transformer for Semantic Sentence Embedding ...
BASE
Show details
69
Generalized Data Augmentation for Low-Resource Translation ...
BASE
Show details
70
Improving Robustness of Machine Translation with Synthetic Noise ...
BASE
Show details
71
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework ...
Wang, Zirui; Xie, Jiateng; Xu, Ruochen. - : arXiv, 2019
BASE
Show details
72
Towards Zero-resource Cross-lingual Entity Linking ...
BASE
Show details
73
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation ...
Wang, Xinyi; Neubig, Graham. - : arXiv, 2019
BASE
Show details
74
Pushing the Limits of Low-Resource Morphological Inflection ...
BASE
Show details
75
Self-Attentional Models for Lattice Inputs ...
BASE
Show details
76
Multilingual Neural Machine Translation With Soft Decoupled Encoding ...
BASE
Show details
77
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity ...
BASE
Show details
78
Domain Adaptation of Neural Machine Translation by Lexicon Induction ...
BASE
Show details
79
Should All Cross-Lingual Embeddings Speak English? ...
BASE
Show details
80
DIRE: A Neural Approach to Decompiled Identifier Naming ...
BASE
Show details

Page: 1 2 3 4 5 6

Catalogues
0
0
2
0
1
0
0
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
113
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern