39 citations · 145 across the 11 of their papers we have counts for
11 papers · 1 filter
Attention Mechanism with Energy-Friendly Operations
Yu Wan, Baosong Yang, Dayiheng Liu +5
Attention mechanism has become the dominant module in natural language processing models. It is computationally intensive and depends on massive power-hungry multiplications. In th…
RoBLEURT Submission for the WMT2021 Metrics Task
Yu Wan, Dayiheng Liu, Baosong Yang +6
In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics…
UniTE: Unified Translation Evaluation
Yu Wan, Dayiheng Liu, Baosong Yang +4
Translation quality evaluation plays a crucial role in machine translation. According to the input format, it is mainly separated into three tasks, i.e., reference-only, source-onl…
Frequency-Aware Contrastive Learning for Neural Machine Translation
Tong Zhang, Wei Ye, Baosong Yang +7
Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emp…
KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
Xin Liu, Dayiheng Liu, Baosong Yang +6
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. Howeve…
Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval
Linlong Xu, Baosong Yang, Xiaoyu Lv +3
Interactive and non-interactive model are the two de-facto standard frameworks in vector-based cross-lingual information retrieval (V-CLIR), which embed queries and documents in sy…
Towards User-Driven Neural Machine Translation
Huan Lin, Liang Yao, Baosong Yang +5
A good translation should not only translate the original content semantically, but also incarnate personal traits of the original text. For a real-world neural machine translation…
Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation
Xin Liu, Baosong Yang, Dayiheng Liu +5
A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary. This potentially weakens the effect when applying pretra…
Exploiting Neural Query Translation into Cross Lingual Information Retrieval
Liang Yao, Baosong Yang, Haibo Zhang +2
As a crucial role in cross-language information retrieval (CLIR), query translation has three main challenges: 1) the adequacy of translation; 2) the lack of in-domain parallel tra…
Constraint Translation Candidates: A Bridge between Neural Query Translation and Cross-lingual Information Retrieval
Tianchi Bi, Liang Yao, Baosong Yang +3
Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR). With the help of deep learning, neural machine translation (NMT) has shown promising…
Self-Paced Learning for Neural Machine Translation
Yu Wan, Baosong Yang, Derek F. Wong +4
Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such…