246 citations · 1.2k across the 71 of their papers we have counts for
49 papers · 1 filter
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
Wenkai Yang, Yankai Lin, Peng Li +2
Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusin…
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
Shaopeng Lai, Ante Wang, Fandong Meng +6
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models,…
WeTS: A Benchmark for Translation Suggestion
Zhen Yang, Fandong Meng, Yingxue Zhang +2
Translation Suggestion (TS), which provides alternatives for specific words or phrases given the entire documents translated by machine translation (MT) \cite{lee2021intellicat}, h…
Dynamic Knowledge Distillation for Pre-trained Language Models
Lei Li, Yankai Lin, Shuhuai Ren +3
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student mo…
Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
Lei Shen, Jinchao Zhang, Jiao Ou +2
Researches on dialogue empathy aim to endow an agent with the capacity of accurate understanding and proper responding for emotions. Existing models for empathetic dialogue generat…
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
Feilong Chen, Fandong Meng, Xiuyi Chen +2
Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment. Previous studies focus on the im…
Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training
Yao Qiu, Jinchao Zhang, Huiying Ren +1
Retrieval-based chatbot selects the appropriate response from candidates according to the context, which heavily depends on a response selection module. A response selection module…
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
Yao Qiu, Jinchao Zhang, Jie Zhou
Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness c…
Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks
Yao Qiu, Jinchao Zhang, Jie Zhou
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Pr…
Competence-based Curriculum Learning for Multilingual Machine Translation
Mingliang Zhang, Fandong Meng, Yunhai Tong +1
Currently, multilingual machine translation is receiving more and more attention since it brings better performance for low resource languages (LRLs) and saves more space. However,…
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser
Duo Zheng, Zipeng Xu, Fandong Meng +3
Considering the importance of building a good Visual Dialog (VD) Questioner, many researchers study the topic under a Q-Bot-A-Bot image-guessing game setting, where the Questioner…
Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark
Zhengcong Fei, Zekang Li, Jinchao Zhang +2
As a kind of new expression elements, Internet memes are popular and extensively used in online chatting scenarios since they manage to make dialogues vivid, moving, and interestin…
Towards Making the Most of Dialogue Characteristics for Neural Chat Translation
Yunlong Liang, Chulun Zhou, Fandong Meng +4
Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware n…
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
Feilong Chen, Xiuyi Chen, Fandong Meng +2
Visual dialog, which aims to hold a meaningful conversation with humans about a given image, is a challenging task that requires models to reason the complex dependencies among vis…
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
Shuhuai Ren, Jinchao Zhang, Lei Li +2
Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations. Traditional methods first devise task-specif…
Scheduled Sampling Based on Decoding Steps for Neural Machine Translation
Yijin Liu, Fandong Meng, Yufeng Chen +2
Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by re…
Modeling Bilingual Conversational Characteristics for Neural Chat Translation
Yunlong Liang, Fandong Meng, Yufeng Chen +2
Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performanc…
Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognition
Ying Zhang, Fandong Meng, Yufeng Chen +2
Zero-resource named entity recognition (NER) severely suffers from data scarcity in a specific domain or language. Most studies on zero-resource NER transfer knowledge from various…
Confidence-Aware Scheduled Sampling for Neural Machine Translation
Yijin Liu, Fandong Meng, Yufeng Chen +2
Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth…
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
Yuanxin Liu, Fandong Meng, Zheng Lin +2
Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find th…
Sequence-Level Training for Non-Autoregressive Neural Machine Translation
Chenze Shao, Yang Feng, Jinchao Zhang +2
In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregre…
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade
Lei Li, Yankai Lin, Deli Chen +4
Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In…
DisenE: Disentangling Knowledge Graph Embeddings
Xiaoyu Kou, Yankai Lin, Yuntao Li +4
Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainl…
WeChat Neural Machine Translation Systems for WMT20
Fandong Meng, Jianhao Yan, Yijin Liu +8
We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DT…