Wanying Xie


2021

pdf bib
GX at SemEval-2021 Task 2: BERT with Lemma Information for MCL-WiC Task
Wanying Xie
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper presents the GX system for the Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC) task. The purpose of the MCL-WiC task is to tackle the challenge of capturing the polysemous nature of words without relying on a fixed sense inventory in a multilingual and cross-lingual setting. To solve the problems, we use context-specific word embeddings from BERT to eliminate the ambiguity between words in different contexts. For languages without an available training corpus, such as Chinese, we use neuron machine translation model to translate the English data released by the organizers to obtain available pseudo-data. In this paper, we apply our system to the English and Chinese multilingual setting and the experimental results show that our method has certain advantages.

pdf bib
Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
Shuhao Gu | Yang Feng | Wanying Xie
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both general domain and in-domain data. However, the existing methods for domain adaptation usually suffer from catastrophic forgetting, large domain divergence, and model explosion. To address these three problems, we propose a method of “divide and conquer” which is based on the importance of neurons or parameters for the translation model. In this method, we first prune the model and only keep the important neurons or parameters, making them responsible for both general-domain and in-domain translation. Then we further train the pruned model supervised by the original whole model with knowledge distillation. Last we expand the model to the original size and fine-tune the added parameters for the in-domain translation. We conducted experiments on different language pairs and domains and the results show that our method can achieve significant improvements compared with several strong baselines.

pdf bib
GX@DravidianLangTech-EACL2021: Multilingual Neural Machine Translation and Back-translation
Wanying Xie
Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages

In this paper, we describe the GX system in the EACL2021 shared task on machine translation in Dravidian languages. Given the low amount of parallel training data, We adopt two methods to improve the overall performance: (1) multilingual translation, we use a shared encoder-decoder multilingual translation model handling multiple languages simultaneously to facilitate the translation performance of these languages; (2) back-translation, we collected other open-source parallel and monolingual data and apply back-translation to benefit from the monolingual data. The experimental results show that we can achieve satisfactory translation results in these Dravidian languages and rank first in English-Telugu and Tamil-Telugu translation.

pdf bib
Importance-based Neuron Allocation for Multilingual Neural Machine Translation
Wanying Xie | Yang Feng | Shuhao Gu | Dong Yu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the general knowledge, but ignore the language-specific knowledge. Some previous works try to solve this problem by adding various kinds of language-specific modules to the model, but they suffer from the parameter explosion problem and require specialized manual design. To solve these problems, we propose to divide the model neurons into general and language-specific parts based on their importance across languages. The general part is responsible for preserving the general knowledge and participating in the translation of all the languages, while the language-specific part is responsible for preserving the language-specific knowledge and participating in the translation of some specific languages. Experimental results on several language pairs, covering IWSLT and Europarl corpus datasets, demonstrate the effectiveness and universality of the proposed method.

2020

pdf bib
Token-level Adaptive Training for Neural Machine Translation
Shuhao Gu | Jinchao Zhang | Fandong Meng | Yang Feng | Wanying Xie | Jie Zhou | Dong Yu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution. However, low-frequency tokens may carry critical semantic information that will affect the translation quality once they are neglected. In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training. We aimed that those meaningful but relatively low-frequency words could be assigned with larger weights in objectives to encourage the model to pay more attention to these tokens. Our method yields consistent improvements in translation quality on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens where we can get 1.68, 1.02, and 0.52 BLEU increases compared with baseline, respectively. Further analyses show that our method can also improve the lexical diversity of translation.

2019

pdf bib
BLCU_NLP at SemEval-2019 Task 7: An Inference Chain-based GPT Model for Rumour Evaluation
Ruoyao Yang | Wanying Xie | Chunhua Liu | Dong Yu
Proceedings of the 13th International Workshop on Semantic Evaluation

Researchers have been paying increasing attention to rumour evaluation due to the rapid spread of unsubstantiated rumours on social media platforms, including SemEval 2019 task 7. However, labelled data for learning rumour veracity is scarce, and labels in rumour stance data are highly disproportionate, making it challenging for a model to perform supervised-learning adequately. We propose an inference chain-based system, which fully utilizes conversation structure-based knowledge in the limited data and expand the training data in minority categories to alleviate class imbalance. Our approach obtains 12.6% improvement upon the baseline system for subtask A, ranks 1st among 21 systems in subtask A, and ranks 4th among 12 systems in subtask B.

pdf bib
BLCU_NLP at SemEval-2019 Task 8: A Contextual Knowledge-enhanced GPT Model for Fact Checking
Wanying Xie | Mengxi Que | Ruoyao Yang | Chunhua Liu | Dong Yu
Proceedings of the 13th International Workshop on Semantic Evaluation

Since the resources of Community Question Answering are abundant and information sharing becomes universal, it will be increasingly difficult to find factual information for questioners in massive messages. SemEval 2019 task 8 is focusing on these issues. We participate in the task and use Generative Pre-trained Transformer (OpenAI GPT) as our system. Our innovations are data extension, feature extraction, and input transformation. For contextual knowledge enhancement, we extend the training set of subtask A, use several features to improve the results of our system and adapt the input formats to be more suitable for this task. We demonstrate the effectiveness of our approaches, which achieves 81.95% of subtask A and 61.08% of subtask B in accuracy on the SemEval 2019 task 8.