30 citations · 237 across the 51 of their papers we have counts for
19 papers · 1 filter
Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning
Hongzhan Lin, Pengyao Yi, Jing Ma +4
The spread of rumors along with breaking events seriously hinders the truth in the era of social media. Previous studies reveal that due to the lack of annotated resources, rumors…
Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure
Xueliang Zhao, Lemao Liu, Tingchen Fu +3
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downst…
Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages
Wenxiang Jiao, Zhaopeng Tu, Jiarui Li +3
This paper describes Tencent's multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages. We participat…
Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task
Zhiwei He, Xing Wang, Zhaopeng Tu +2
This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation…
Effidit: Your AI Writing Assistant
Shuming Shi, Enbo Zhao, Duyu Tang +10
In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently…
One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Yong Dai, Duyu Tang, Liangxin Liu +7
People perceive the world with multiple senses (e.g., through hearing sounds, reading words and seeing objects). However, most existing AI systems only process an individual modali…
SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach
Junwei Liao, Duyu Tang, Fan Zhang +1
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model. Different from traditional dense models that always activ…
Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Cong Zhou, Yong Dai, Duyu Tang +4
Chinese BERT models achieve remarkable progress in dealing with grammatical errors of word substitution. However, they fail to handle word insertion and deletion because BERT assum…
A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
Yu Cao, Wei Bi, Meng Fang +2
Towards building intelligent dialogue agents, there has been a growing interest in introducing explicit personas in generation models. However, with limited persona-based dialogue…
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
Jiannan Xiang, Huayang Li, Yahui Liu +4
Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year's WMT Metrics Shared Task. However, in this paper, we qualitatively and quan…
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…
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
Wenxuan Wang, Wenxiang Jiao, Yongchang Hao +4
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying…
Efficient Sub-structured Knowledge Distillation
Wenye Lin, Yangming Li, Lemao Liu +2
Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such mod…
Exploring and Adapting Chinese GPT to Pinyin Input Method
Minghuan Tan, Yong Dai, Duyu Tang +5
While GPT has become the de-facto method for text generation tasks, its application to pinyin input method remains unexplored. In this work, we make the first exploration to levera…
MarkBERT: Marking Word Boundaries Improves Chinese BERT
Linyang Li, Yong Dai, Duyu Tang +3
We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary…
SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding
Fan Zhang, Duyu Tang, Yong Dai +3
Prevailing deep models are single-purpose and overspecialize at individual tasks. However, when being extended to new tasks, they typically forget previously learned skills and lea…
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
Zhangyin Feng, Duyu Tang, Cong Zhou +6
The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconven…
Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing
Lingfeng Shen, Haiyun Jiang, Lemao Liu +1
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm…
On the Evaluation Metrics for Paraphrase Generation
Lingfeng Shen, Lemao Liu, Haiyun Jiang +1
In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance…