616 citations · 1.8k across the 64 of their papers we have counts for
54 papers · 1 filter
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
Pengzhi Gao, Ruiqing Zhang, Zhongjun He +2
Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neur…
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Pengzhi Gao, Liwen Zhang, Zhongjun He +2
Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to mo…
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Pengzhi Gao, Liwen Zhang, Zhongjun He +2
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during…
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Siqi Bao, Huang He, Jun Xu +7
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy. To this end, we introdu…
Towards Boosting the Open-Domain Chatbot with Human Feedback
Hua Lu, Siqi Bao, Huang He +3
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real…
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Pengzhi Gao, Zhongjun He, Hua Wu +1
We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and…
Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge
Han Zhou, Xinchao Xu, Wenquan Wu +5
Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state. Several recent advances h…
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
Yuxiang Lu, Yiding Liu, Jiaxiang Liu +8
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their…
Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation
Yanrui Du, Jing Yan, Yan Chen +6
Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world app…
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
Lijie Wang, Yaozong Shen, Shuyuan Peng +7
While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation data…
Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitation
Shihang Wang, Xinchao Xu, Wenquan Wu +3
Emotional support is a crucial skill for many real-world scenarios, including caring for the elderly, mental health support, and customer service chats. This paper presents a novel…
Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals
Zeming Liu, Jun Xu, Zeyang Lei +3
Most dialog systems posit that users have figured out clear and specific goals before starting an interaction. For example, users have determined the departure, the destination, an…
A Thorough Examination on Zero-shot Dense Retrieval
Ruiyang Ren, Yingqi Qu, Jing Liu +6
Recent years have witnessed the significant advance in dense retrieval (DR) based on powerful pre-trained language models (PLM). DR models have achieved excellent performance in se…
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Xinchao Xu, Zhibin Gou, Wenquan Wu +4
Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understa…
DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
Yifu Qiu, Hongyu Li, Yingqi Qu +5
In this paper, we present DuReader_retrieval, a large-scale Chinese dataset for passage retrieval. DuReader_retrieval contains more than 90K queries and over 8M unique passages fro…
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Shuohuan Wang, Yu Sun, Yang Xiang +26
Pre-trained language models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. GPT-3 has shown that scaling up pre-trained language models c…
TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations
Xin Tian, Xinxian Huang, Dongfeng He +11
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available…
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
Hongyu Zhu, Yan Chen, Jing Yan +5
In this paper, we focus on studying robustness evaluation of Chinese question matching. Most of the previous work on analyzing robustness issue focus on just one or a few types of…
SgSum: Transforming Multi-document Summarization into Sub-graph Selection
Moye Chen, Wei Li, Jiachen Liu +3
Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have tw…
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
Ruiyang Ren, Yingqi Qu, Jing Liu +5
In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two proced…
Building Chinese Biomedical Language Models via Multi-Level Text Discrimination
Quan Wang, Songtai Dai, Benfeng Xu +4
Pre-trained language models (PLMs), such as BERT and GPT, have revolutionized the field of NLP, not only in the general domain but also in the biomedical domain. Most prior efforts…
DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation
Zeming Liu, Haifeng Wang, Zheng-Yu Niu +2
In this paper, we provide a bilingual parallel human-to-human recommendation dialog dataset (DuRecDial 2.0) to enable researchers to explore a challenging task of multilingual and…
Mixup Decoding for Diverse Machine Translation
Jicheng Li, Pengzhi Gao, Xuanfu Wu +4
Diverse machine translation aims at generating various target language translations for a given source language sentence. Leveraging the linear relationship in the sentence latent…
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
Siqi Bao, Huang He, Fan Wang +11
To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conve…