1 |
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Data for paper: "Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval" ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Data for paper: "Evaluating Resource-Lean Cross-Lingual Embedding Models in Unsupervised Retrieval" ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
On Cross-Lingual Retrieval with Multilingual Text Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Data for paper: "Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval" ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Evaluating multilingual text encoders for unsupervised cross-lingual retrieval
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Probing Pretrained Language Models for Lexical Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers
|
|
Glavas, Goran; Agic, Zeljko; Vulic, Ivan; Litschko, Robert. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.345, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
|
|
Abstract:
Current methods of cross-lingual parser transfer focus on predicting the best parser for a low-resource target language globally, that is, "at treebank level”. In this work, we propose and argue for a novel cross-lingual transfer paradigm: instance-level parser selection (ILPS), and present a proof-of-concept study focused on instance-level selection in the framework of delexicalized parser transfer. Our work is motivated by an empirical observation that different source parsers are the best choice for different Universal POS-sequences (i.e., UPOS sentences) in the target language. We then propose to predict the best parser at the instance level. To this end, we train a supervised regression model, based on the Transformer architecture, to predict parser accuracies for individual POS-sequences. We compare ILPS against two strong single-best parser selection baselines (SBPS): (1) a model that compares POS n-gram distributions between the source and target languages (KL) and (2) a model that selects the source based on the similarity between manually created language vectors encoding syntactic properties of languages (L2V). The results from our extensive evaluation, coupling 42 source parsers and 20 diverse low-resource test languages, show that ILPS outperforms KL and L2V on 13/20 and 14/20 test languages, respectively. Further, we show that by predicting the best parser “at treebank level” (SBPS), using the aggregation of predictions from our instance-level model, we outperform the same baselines on 17/20 and 16/20 test languages.
|
|
URL: https://doi.org/10.17863/CAM.62214 https://www.repository.cam.ac.uk/handle/1810/315107
|
|
BASE
|
|
Hide details
|
|
15 |
Towards instance-level parser selection for cross-lingual transfer of dependency parsers
|
|
|
|
BASE
|
|
Show details
|
|
16 |
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
How to (properly) evaluate cross-lingual word embeddings: On strong baselines, comparative analyses, and some misconceptions
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
|
|
|
|
BASE
|
|
Show details
|
|
|
|