Zhuoyuan Mao


2023

pdf bib
Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation
Zhuoyuan Mao | Raj Dabre | Qianying Liu | Haiyue Song | Chenhui Chu | Sadao Kurohashi
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST). Recent efforts for ZST often utilize the Transformer architecture as the backbone, with LayerNorm at the input of layers (PreNorm) set as the default. However, Xu et al. (2019) has revealed that PreNorm carries the risk of overfitting the training data. Based on this, we hypothesize that PreNorm may overfit supervised directions and thus have low generalizability for ZST. Through experiments on OPUS, IWSLT, and Europarl datasets for 54 ZST directions, we demonstrate that the original Transformer setting of LayerNorm after residual connections (PostNorm) consistently outperforms PreNorm by up to 12.3 BLEU points. We then study the performance disparities by analyzing the differences in off-target rates and structural variations between PreNorm and PostNorm. This study highlights the need for careful consideration of the LayerNorm setting for ZST.

pdf bib
Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation
Zhuoyuan Mao | Haiyue Song | Raj Dabre | Chenhui Chu | Sadao Kurohashi
Proceedings of the 1st International Workshop on Multilingual, Multimodal and Multitask Language Generation

pdf bib
Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Zhen Wan | Fei Cheng | Qianying Liu | Zhuoyuan Mao | Haiyue Song | Sadao Kurohashi
Findings of the Association for Computational Linguistics: EACL 2023

Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks. However, the existing methods ignore the intrinsic noise of distant supervision during the pre-training stage. In this paper, we propose a weighted contrastive learning method by leveraging the supervised data to estimate the reliability of pre-training instances and explicitly reduce the effect of noise. Experimental results on three supervised datasets demonstrate the advantages of our proposed weighted contrastive learning approach compared to two state-of-the-art non-weighted baselines. Our code and models are available at: https://github.com/YukinoWan/WCL.

pdf bib
GPT-RE: In-context Learning for Relation Extraction using Large Language Models
Zhen Wan | Fei Cheng | Zhuoyuan Mao | Qianying Liu | Haiyue Song | Jiwei Li | Sadao Kurohashi
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e.g., GPT-3) via in-context learning (ICL), they still lag significantly behind fully-supervised baselines (e.g., fine-tuned BERT) in relation extraction (RE). This is due to the two major shortcomings of ICL for RE: (1) low relevance regarding entity and relation in existing sentence-level demonstration retrieval approaches for ICL; and (2) the lack of explaining input-label mappings of demonstrations leading to poor ICL effectiveness. In this paper, we propose GPT-RE to successfully address the aforementioned issues by (1) incorporating task-aware representations in demonstration retrieval; and (2) enriching the demonstrations with gold label-induced reasoning logic. We evaluate GPT-RE on four widely-used RE datasets, and observe that GPT-RE achieves improvements over not only existing GPT-3 baselines, but also fully-supervised baselines as in Figure 1. Specifically, GPT-RE achieves SOTA performances on the Semeval and SciERC datasets, and competitive performances on the TACRED and ACE05 datasets. Additionally, a critical issue of LLMs revealed by previous work, the strong inclination to wrongly classify NULL examples into other pre-defined labels, is substantially alleviated by our method. We show an empirical analysis.

pdf bib
LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation
Zhuoyuan Mao | Tetsuji Nakagawa
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment. However, these large-scale models can suffer from inference speed and computation overhead. This study systematically explores learning language-agnostic sentence embeddings with lightweight models. We demonstrate that a thin-deep encoder can construct robust low-dimensional sentence embeddings for 109 languages. With our proposed distillation methods, we achieve further improvements by incorporating knowledge from a teacher model. Empirical results on Tatoeba, United Nations, and BUCC show the effectiveness of our lightweight models. We release our lightweight language-agnostic sentence embedding models LEALLA on TensorFlow Hub.

2022

pdf bib
BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation
Haiyue Song | Raj Dabre | Zhuoyuan Mao | Chenhui Chu | Sadao Kurohashi
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Existing subword segmenters are either 1) frequency-based without semantics information or 2) neural-based but trained on parallel corpora. To address this, we present BERTSeg, an unsupervised neural subword segmenter for neural machine translation, which utilizes the contextualized semantic embeddings of words from characterBERT and maximizes the generation probability of subword segmentations. Furthermore, we propose a generation probability-based regularization method that enables BERTSeg to produce multiple segmentations for one word to improve the robustness of neural machine translation. Experimental results show that BERTSeg with regularization achieves up to 8 BLEU points improvement in 9 translation directions on ALT, IWSLT15 Vi->En, WMT16 Ro->En, and WMT15 Fi->En datasets compared with BPE. In addition, BERTSeg is efficient, needing up to 5 minutes for training.

pdf bib
Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Yibin Shen | Qianying Liu | Zhuoyuan Mao | Zhen Wan | Fei Cheng | Sadao Kurohashi
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution equation supervised by human annotation. In this paper, we propose a controlled equation generation solver by leveraging a set of control codes to guide the model to consider certain reasoning logic and decode the corresponding equations expressions transformed from the human reference. The empirical results suggest that our method universally improves the performance on single-unknown (Math23K) and multiple-unknown (DRAW1K, HMWP) benchmarks, with substantial improvements up to 13.2% accuracy on the challenging multiple-unknown datasets.

pdf bib
Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction
Zhen Wan | Qianying Liu | Zhuoyuan Mao | Fei Cheng | Sadao Kurohashi | Jiwei Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models. However, existing RE models are usually incapable of handling two situations: implicit expressions and long-tail relation types, caused by language complexity and data sparsity. In this paper, we introduce a simple enhancement of RE using k nearest neighbors (kNN-RE). kNN-RE allows the model to consult training relations at test time through a nearest-neighbor search and provides a simple yet effective means to tackle the two issues above. Additionally, we observe that kNN-RE serves as an effective way to leverage distant supervision (DS) data for RE. Experimental results show that the proposed kNN-RE achieves state-of-the-art performances on a variety of supervised RE datasets, i.e., ACE05, SciERC, and Wiki80, along with outperforming the best model to date on the i2b2 and Wiki80 datasets in the setting of allowing using DS. Our code and models are available at: https://github.com/YukinoWan/kNN-RE.

pdf bib
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Zhuoyuan Mao | Chenhui Chu | Raj Dabre | Haiyue Song | Zhen Wan | Sadao Kurohashi
Findings of the Association for Computational Linguistics: NAACL 2022

Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs. Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT. This work proposes a word-level contrastive objective to leverage word alignments for many-to-many NMT. Empirical results show that this leads to 0.8 BLEU gains for several language pairs. Analyses reveal that in many-to-many NMT, the encoder’s sentence retrieval performance highly correlates with the translation quality, which explains when the proposed method impacts translation. This motivates future exploration for many-to-many NMT to improve the encoder’s sentence retrieval performance.

pdf bib
Textual Enhanced Contrastive Learning for Solving Math Word Problems
Yibin Shen | Qianying Liu | Zhuoyuan Mao | Fei Cheng | Sadao Kurohashi
Findings of the Association for Computational Linguistics: EMNLP 2022

Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies show that current models rely on shallow heuristics to predict solutions and could be easily misled by small textual perturbations. To address this problem, we propose a Textual Enhanced Contrastive Learning framework, which enforces the models to distinguish semantically similar examples while holding different mathematical logic. We adopt a self-supervised manner strategy to enrich examples with subtle textual variance by textual reordering or problem re-construction. We then retrieve the hardest to differentiate samples from both equation and textual perspectives and guide the model to learn their representations. Experimental results show that our method achieves state-of-the-art on both widely used benchmark datasets and also exquisitely designed challenge datasets in English and Chinese.

2021

pdf bib
Lightweight Cross-Lingual Sentence Representation Learning
Zhuoyuan Mao | Prakhar Gupta | Chenhui Chu | Martin Jaggi | Sadao Kurohashi
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)

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and modifications based on such large-scale models are usually impractical due to memory limitations. In this work, we introduce a lightweight dual-transformer architecture with just 2 layers for generating memory-efficient cross-lingual sentence representations. We explore different training tasks and observe that current cross-lingual training tasks leave a lot to be desired for this shallow architecture. To ameliorate this, we propose a novel cross-lingual language model, which combines the existing single-word masked language model with the newly proposed cross-lingual token-level reconstruction task. We further augment the training task by the introduction of two computationally-lite sentence-level contrastive learning tasks to enhance the alignment of cross-lingual sentence representation space, which compensates for the learning bottleneck of the lightweight transformer for generative tasks. Our comparisons with competing models on cross-lingual sentence retrieval and multilingual document classification confirm the effectiveness of the newly proposed training tasks for a shallow model.

2020

pdf bib
Pre-training via Leveraging Assisting Languages for Neural Machine Translation
Haiyue Song | Raj Dabre | Zhuoyuan Mao | Fei Cheng | Sadao Kurohashi | Eiichiro Sumita
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks. However, large monolingual corpora might not always be available for the languages of interest (LOI). Thus, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI. We utilize script mapping (Chinese to Japanese) to increase the similarity (number of cognates) between the monolingual corpora of helping languages and LOI. An empirical case study of low-resource Japanese-English neural machine translation (NMT) reveals that leveraging large Chinese and French monolingual corpora can help overcome the shortage of Japanese and English monolingual corpora, respectively, for S2S pre-training. Using only Chinese and French monolingual corpora, we were able to improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios.

pdf bib
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
Zhuoyuan Mao | Fabien Cromieres | Raj Dabre | Haiyue Song | Sadao Kurohashi
Proceedings of the Twelfth Language Resources and Evaluation Conference

Neural machine translation (NMT) needs large parallel corpora for state-of-the-art translation quality. Low-resource NMT is typically addressed by transfer learning which leverages large monolingual or parallel corpora for pre-training. Monolingual pre-training approaches such as MASS (MAsked Sequence to Sequence) are extremely effective in boosting NMT quality for languages with small parallel corpora. However, they do not account for linguistic information obtained using syntactic analyzers which is known to be invaluable for several Natural Language Processing (NLP) tasks. To this end, we propose JASS, Japanese-specific Sequence to Sequence, as a novel pre-training alternative to MASS for NMT involving Japanese as the source or target language. JASS is joint BMASS (Bunsetsu MASS) and BRSS (Bunsetsu Reordering Sequence to Sequence) pre-training which focuses on Japanese linguistic units called bunsetsus. In our experiments on ASPEC Japanese–English and News Commentary Japanese–Russian translation we show that JASS can give results that are competitive with if not better than those given by MASS. Furthermore, we show for the first time that joint MASS and JASS pre-training gives results that significantly surpass the individual methods indicating their complementary nature. We will release our code, pre-trained models and bunsetsu annotated data as resources for researchers to use in their own NLP tasks.

pdf bib
Meta Ensemble for Japanese-Chinese Neural Machine Translation: Kyoto-U+ECNU Participation to WAT 2020
Zhuoyuan Mao | Yibin Shen | Chenhui Chu | Sadao Kurohashi | Cheqing Jin
Proceedings of the 7th Workshop on Asian Translation

This paper describes the Japanese-Chinese Neural Machine Translation (NMT) system submitted by the joint team of Kyoto University and East China Normal University (Kyoto-U+ECNU) to WAT 2020 (Nakazawa et al.,2020). We participate in APSEC Japanese-Chinese translation task. We revisit several techniques for NMT including various architectures, different data selection and augmentation methods, denoising pre-training, and also some specific tricks for Japanese-Chinese translation. We eventually perform a meta ensemble to combine all of the models into a single model. BLEU results of this meta ensembled model rank the first both on 2 directions of ASPEC Japanese-Chinese translation.