VLSP 2021 - vnNLI Challenge: Vietnamese and English-Vietnamese Textual Entailment

Natural Language Inference (NLI) is one of the critical tasks in natural language understanding which we take through the VLSP2021-NLI Shared Task competition. VLSP2021-NLI Shared Task is a competition to improve existing methods for NLI tasks, thereby enhancing the efficiency of applications. One of the challenges of the competition is the dataset in both Vietnamese and English. In this article, we report on evaluating the NLI task of the competition. We first implement the 5-fold cross-validation evaluation method. We following leverage model architectures pre-trained on cross-lingual language datasets such as XLM-RoBERTa and RemBERT to create contextual word embeddings for classification. Our final result reaches 90.00% on the test dataset of the organizers.

Section: Introductionmentioning

confidence: 99%

The VNNLI - VLSP 2021: Leveraging Contextual Word Embedding for NLI Task on Bilingual Dataset

Duong

2022

“…In solving NLI problems, the common approach is to examine the relationship between a pair of sentences or paragraphs (premise and hypothesis) and whether they semantically agree, disagree, or are neutral to each other [2]. In the shared-task VLSP 2021: "Vietnamese and English-Vietnamese Textual Entailment" [3]. This task is presented as a multi-class classification problem involving sentences_1 and sentences_2 and the output is a relation of two sentences.…”

Section: Introductionmentioning

confidence: 99%

vnNLI - VLSP2021: An Empirical Study on Vietnamese-English Natural Language Inference Based on Pretrained Language Models with Data Augmentation

Van

Hao²,

Nguyễn³

et al. 2022

In this paper, we describe an empirical study of data augmentation techniques with various pre-trained language models on the bilingual dataset which was presented at the VLSP 2021 - Vietnamese and English-Vietnamese Textual Entailment. We apply the machine translation tool to generate new training set from original training data and then investigate and compare the effectiveness of a monolingual and multilingual model on the new data set. Our experimental results show that fine-tuning a pre-trained multilingual language XLM-R model with an augmented training set gives the best performance. Our system was ranked third in the shared-task VLSP 2021 with the F1-score of about 0.88.

“…• We conduct an investigation into the benefit of using two of state-of-the-art pre-trained multilingual language models (XLM-R and InfoXLM) to evaluate cross-lingual natural language inference task in VLSP 2021 [17].…”

mentioning

confidence: 99%

vnNLI - VLSP 2021: Vietnamese and English-Vietnamese Textual Entailment Based on Pre-trained Multilingual Language Models

Thuy

Thìn²,

Vũ³

et al. 2022

Natural Language Inference (NLI) is a high-level semantic task in Natural Language Processing - NLP, and it extends further challenges if it is in the cross-lingual scenario. In recent years, pre-trained multilingual language models (e.g., mBERT ,XLM-R, InfoXLM) have greatly contributed to the success of dealing with these challenges. Based on the motivation behind these achievements, this paper describes our approach based on fine-tuning pretrained multilingual language models (XLM-R, InfoXLM) to tackle the shared task ``Vietnamese and English\-Vietnamese Textual Entailment'' at the 8th International Workshop on Vietnamese Language and Speech Processing (VLSP 2021\footnote{https://vlsp.org.vn/vlsp2021}). We investigate other techniques to improve the performance of our work: Cross-validation, Pseudo-labeling (PL), Learning rate adjustment, and Postagging. All experimental results demonstrated that our approach based on the InfoXLM model achieved competitive results, ranking 2nd for the task evaluation in VLSP 2021 with 0.89 in terms of F1-score on the private test set.