1 |
Delving Deeper into Cross-lingual Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Multilingual and Cross-Lingual Intent Detection from Spoken Data ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Modelling Latent Translations for Cross-Lingual Transfer ...
|
|
|
|
Abstract:
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations: 1) translation errors percolating to the classification phase and 2) the insufficient expressiveness of the maximum-likelihood translation. To remedy this, we propose a new technique that integrates both steps of the traditional pipeline (translation and classification) into a single model, by treating the intermediate translations as a latent random variable. As a result, 1) the neural machine translation system can be fine-tuned with a variant of Minimum Risk Training where the reward is the accuracy of the downstream task classifier. Moreover, 2) multiple samples can be drawn to approximate the expected loss across all possible translations during inference. We evaluate our novel latent translation-based model on a series of multilingual NLU tasks, including commonsense ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2107.11353 https://arxiv.org/abs/2107.11353
|
|
BASE
|
|
Hide details
|
|
8 |
Prix-LM: Pretraining for Multilingual Knowledge Base Construction ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
On Cross-Lingual Retrieval with Multilingual Text Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|