195 citations · 493 across the 31 of their papers we have counts for
30 papers · 1 filter
Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
Yiming Wang, Zhuosheng Zhang, Pei Zhang +2
Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically ma…
Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer
Ruize Gao, Zhirui Zhang, Yichao Du +2
Nearest Neighbor Machine Translation (NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain…
Universal Multimodal Representation for Language Understanding
Zhuosheng Zhang, Kehai Chen, Rui Wang +4
Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP task…
Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
Zhiwei He, Xing Wang, Rui Wang +2
Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is train…
Text Compression-aided Transformer Encoding
Zuchao Li, Zhuosheng Zhang, Hai Zhao +4
Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transfo…
SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
Zuchao Li, Hai Zhao, Rui Wang +3
In this paper, we introduced our joint team SJTU-NICT 's participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation dir…
Document-level Neural Machine Translation with Document Embeddings
Shu Jiang, Hai Zhao, Zuchao Li +1
Standard neural machine translation (NMT) is on the assumption of document-level context independent. Most existing document-level NMT methods are satisfied with a smattering sense…
Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
Zhuosheng Zhang, Hai Zhao, Rui Wang
Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burs…
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
Haipeng Sun, Rui Wang, Kehai Chen +3
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair an…
Explicit Reordering for Neural Machine Translation
Kehai Chen, Rui Wang, Masao Utiyama +1
In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency,…
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios
Haipeng Sun, Rui Wang, Kehai Chen +3
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-worl…
Reference Language based Unsupervised Neural Machine Translation
Zuchao Li, Hai Zhao, Rui Wang +2
Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enh…
Modeling Future Cost for Neural Machine Translation
Chaoqun Duan, Kehai Chen, Rui Wang +4
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each…
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
Haipeng Sun, Rui Wang, Kehai Chen +4
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collectio…
Explicit Sentence Compression for Neural Machine Translation
Zuchao Li, Rui Wang, Kehai Chen +4
State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well d…
Probing Contextualized Sentence Representations with Visual Awareness
Zhuosheng Zhang, Rui Wang, Kehai Chen +3
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel da…
Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
Zuchao Li, Hai Zhao, Junru Zhou +2
The latest developments in neural semantic role labeling (SRL) have shown great performance improvements with both the dependency and span formalisms/styles. Although the two style…
Document-level Neural Machine Translation with Associated Memory Network
Shu Jiang, Rui Wang, Zuchao Li +5
Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smat…
Regularized Context Gates on Transformer for Machine Translation
Xintong Li, Lemao Liu, Rui Wang +2
Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation (NMT). However,…
Controllable Dual Skew Divergence Loss for Neural Machine Translation
Zuchao Li, Hai Zhao, Yingting Wu +2
In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper…
SG-Net: Syntax-Guided Machine Reading Comprehension
Zhuosheng Zhang, Yuwei Wu, Junru Zhou +3
For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is esse…
Lattice-Based Transformer Encoder for Neural Machine Translation
Fengshun Xiao, Jiangtong Li, Hai Zhao +2
Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split…
NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filtering Task
Rui Wang, Benjamin Marie, Masao Utiyama +1
This paper presents the NICT's participation in the WMT18 shared parallel corpus filtering task. The organizers provided 1 billion words German-English corpus crawled from the web…
NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task
Benjamin Marie, Rui Wang, Atsushi Fujita +2
This paper presents the NICT's participation to the WMT18 shared news translation task. We participated in the eight translation directions of four language pairs: Estonian-English…