A Neural Framework for English-Hindi Cross-Lingual Natural Language Inference

Saikh, Tanik and De, Arkadipta and Bandyopadhyay, Dibyanayan and et al, . (2020) A Neural Framework for English-Hindi Cross-Lingual Natural Language Inference. In: 27th International Conference on Neural Information Processing, ICONIP 2020, 18 November 2020through 22 November 2020, Bangkok.

Full text not available from this repository. (Request a copy)

Abstract

Recognizing Textual Entailment (RTE) between two pieces of texts is a very crucial problem in Natural Language Processing (NLP), and it adds further challenges when involving two different languages, i.e. in cross-lingual scenario. The paucity of a large volume of datasets for this problem has become the key bottleneck of nourishing research in this line. In this paper, we provide a deep neural framework for cross-lingual textual entailment involving English and Hindi. As there are no large dataset available for this task, we first create this by translating the premises and hypotheses pairs of Stanford Natural Language Inference (SNLI) (https://nlp.stanford.edu/projects/snli/) dataset into Hindi. We develop a Bidirectional Encoder Representations for Transformers (BERT) based baseline on this newly created dataset. We perform experiments in both mono-lingual and cross-lingual settings. For the mono-lingual setting, we obtain the accuracy scores of 83% and 72% for English and Hindi languages, respectively. In the cross-lingual setting, we obtain the accuracy scores of 69% and 72% for English-Hindi and Hindi-English language pairs, respectively. We hope this dataset can serve as valuable resource for research and evaluation of Cross Lingual Textual Entailment (CLTE) models. © 2020, Springer Nature Switzerland AG.

[error in script]

IITH Creators:

IITH Creators	ORCiD

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

Acknowledgements. We would like to acknowledge “Elsevier Centre of Excellence for Natural Language Processing” at Indian Institute of Technology Patna for partial support of the research work carried out in this paper. Asif Ekbal gratefully acknowledges Visvesvaraya Young Faculty Research Fellowship Award. We also acknowledge the annotators for manually checking the translated outputs.

Uncontrolled Keywords:

Cross-lingual textual entailment; Deep learning; English-Hindi CLTE dataset; SNLI

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

22 Oct 2022 07:22

Last Modified:

22 Oct 2022 07:22