46 citations · 300 across the 39 of their papers we have counts for
40 papers
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
Chen Wang, Minpeng Liao, Zhongqiang Huang +5
The emergence of large language models (LLMs) has sparked significant interest in extending their remarkable language capabilities to speech. However, modality alignment between sp…
Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation
Yang Zhao, Junnan Zhu, Lu Xiang +4
A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavail…
1st Place Solutions for the UVO Challenge 2022
Jiajun Zhang, Boyu Chen, Zhilong Ji +2
This paper describes the approach we have taken in the challenge. We still adopted the two-stage scheme same as the last champion, that is, detection first and segmentation followe…
Learning Confidence for Transformer-based Neural Machine Translation
Yu Lu, Jiali Zeng, Jiajun Zhang +2
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success. A well-calibrated confidence estimate enables accurate failure p…
Instance-aware Prompt Learning for Language Understanding and Generation
Feihu Jin, Jinliang Lu, Jiajun Zhang +1
Recently, prompt learning has become a new paradigm to utilize pre-trained language models (PLMs) and achieves promising results in downstream tasks with a negligible increase of p…
Parameter Differentiation based Multilingual Neural Machine Translation
Qian Wang, Jiajun Zhang
Multilingual neural machine translation (MNMT) aims to translate multiple languages with a single model and has been proved successful thanks to effective knowledge transfer among…
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Yuan Yao, Qingxiu Dong, Jian Guan +32
Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding ro…
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
Jiajun Zhang, Pengyuan Ren, Jianmin Li
Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attri…
Bridging the Modality Gap for Speech-to-Text Translation
Yuchen Liu, Junnan Zhu, Jiajun Zhang +1
End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structur…
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning
Xiaomian Kang, Yang Zhao, Jiajun Zhang +1
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglec…
Neural Machine Translation: Challenges, Progress and Future
Jiajun Zhang, Chengqing Zong
Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping…
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
Yuchen Liu, Jiajun Zhang, Hao Xiong +5
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional p…
Chinese Spelling Error Detection Using a Fusion Lattice LSTM
Hao Wang, Bing Wang, Jianyong Duan +1
Spelling error detection serves as a crucial preprocessing in many natural language processing applications. Due to the characteristics of Chinese Language, Chinese spelling error…
NCLS: Neural Cross-Lingual Summarization
Junnan Zhu, Qian Wang, Yining Wang +4
Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language. Existing methods simply divide this tas…
Are You for Real? Detecting Identity Fraud via Dialogue Interactions
Weikang Wang, Jiajun Zhang, Qian Li +2
Identity fraud detection is of great importance in many real-world scenarios such as the financial industry. However, few studies addressed this problem before. In this paper, we f…
Understanding Memory Modules on Learning Simple Algorithms
Kexin Wang, Yu Zhou, Shaonan Wang +2
Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms. However, we still have little understanding o…
Sequence Generation: From Both Sides to the Middle
Long Zhou, Jiajun Zhang, Chengqing Zong +1
The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually…
Incremental Learning from Scratch for Task-Oriented Dialogue Systems
Weikang Wang, Jiajun Zhang, Qian Li +3
Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands a…
Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
He Bai, Yu Zhou, Jiajun Zhang +1
Dialogue contexts are proven helpful in the spoken language understanding (SLU) system and they are typically encoded with explicit memory representations. However, most of the pre…
Synchronous Bidirectional Neural Machine Translation
Long Zhou, Jiajun Zhang, Chengqing Zong
Existing approaches to neural machine translation (NMT) generate the target language sequence token by token from left to right. However, this kind of unidirectional decoding frame…
End-to-End Speech Translation with Knowledge Distillation
Yuchen Liu, Hao Xiong, Zhongjun He +4
End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to…
Synchronous Bidirectional Inference for Neural Sequence Generation
Jiajun Zhang, Long Zhou, Yang Zhao +1
In sequence to sequence generation tasks (e.g. machine translation and abstractive summarization), inference is generally performed in a left-to-right manner to produce the result…
Language-Independent Representor for Neural Machine Translation
Long Zhou, Yuchen Liu, Jiajun Zhang +2
Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation.…
Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
He Bai, Yu Zhou, Jiajun Zhang +3
To deploy a spoken language understanding (SLU) model to a new language, language transferring is desired to avoid the trouble of acquiring and labeling a new big SLU corpus. Trans…