MIRACLE’s Cross-Lingual Question Answering Experiments with Spanish as a Target Language

Author(s):  
César de Pablo-Sánchez ◽  
Ana González-Ledesma ◽  
José Luis Martínez-Fernández ◽  
José María Guirao ◽  
Paloma Martínez ◽  
...  
2020 ◽  
Vol 34 (05) ◽  
pp. 8058-8065
Author(s):  
Katharina Kann ◽  
Samuel R. Bowman ◽  
Kyunghyun Cho

We propose to cast the task of morphological inflection—mapping a lemma to an indicated inflected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shaofei Wang ◽  
Depeng Dang

PurposePrevious knowledge base question answering (KBQA) models only consider the monolingual scenario and cannot be directly extended to the cross-lingual scenario, in which the language of questions and that of knowledge base (KB) are different. Although a machine translation (MT) model can bridge the gap through translating questions to the language of KB, the noises of translated questions could accumulate and further sharply impair the final performance. Therefore, the authors propose a method to improve the robustness of KBQA models in the cross-lingual scenario.Design/methodology/approachThe authors propose a knowledge distillation-based robustness enhancement (KDRE) method. Specifically, first a monolingual model (teacher) is trained by ground truth (GT) data. Then to imitate the practical noises, a noise-generating model is designed to inject two types of noise into questions: general noise and translation-aware noise. Finally, the noisy questions are input into the student model. Meanwhile, the student model is jointly trained by GT data and distilled data, which are derived from the teacher when feeding GT questions.FindingsThe experimental results demonstrate that KDRE can improve the performance of models in the cross-lingual scenario. The performance of each module in KBQA model is improved by KDRE. The knowledge distillation (KD) and noise-generating model in the method can complementarily boost the robustness of models.Originality/valueThe authors first extend KBQA models from monolingual to cross-lingual scenario. Also, the authors first implement KD for KBQA to develop robust cross-lingual models.


2020 ◽  
Vol 34 (05) ◽  
pp. 9274-9281
Author(s):  
Qianhui Wu ◽  
Zijia Lin ◽  
Guoxin Wang ◽  
Hui Chen ◽  
Börje F. Karlsson ◽  
...  

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.


2020 ◽  
pp. 016555152096278
Author(s):  
Rouzbeh Ghasemi ◽  
Seyed Arad Ashrafi Asli ◽  
Saeedeh Momtazi

With the advent of deep neural models in natural language processing tasks, having a large amount of training data plays an essential role in achieving accurate models. Creating valid training data, however, is a challenging issue in many low-resource languages. This problem results in a significant difference between the accuracy of available natural language processing tools for low-resource languages compared with rich languages. To address this problem in the sentiment analysis task in the Persian language, we propose a cross-lingual deep learning framework to benefit from available training data of English. We deployed cross-lingual embedding to model sentiment analysis as a transfer learning model which transfers a model from a rich-resource language to low-resource ones. Our model is flexible to use any cross-lingual word embedding model and any deep architecture for text classification. Our experiments on English Amazon dataset and Persian Digikala dataset using two different embedding models and four different classification networks show the superiority of the proposed model compared with the state-of-the-art monolingual techniques. Based on our experiment, the performance of Persian sentiment analysis improves 22% in static embedding and 9% in dynamic embedding. Our proposed model is general and language-independent; that is, it can be used for any low-resource language, once a cross-lingual embedding is available for the source–target language pair. Moreover, by benefitting from word-aligned cross-lingual embedding, the only required data for a reliable cross-lingual embedding is a bilingual dictionary that is available between almost all languages and the English language, as a potential source language.


2014 ◽  
Vol 102 (1) ◽  
pp. 93-104
Author(s):  
Ramasamy Loganathan ◽  
Mareček David ◽  
Žabokrtský Zdenčk

Abstract This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers.


2019 ◽  
Author(s):  
Jiahua Liu ◽  
Yankai Lin ◽  
Zhiyuan Liu ◽  
Maosong Sun

2021 ◽  
Author(s):  
Arij Riabi ◽  
Thomas Scialom ◽  
Rachel Keraron ◽  
Benoît Sagot ◽  
Djamé Seddah ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document