Search Results for author: Yijin Liu

Found 17 papers, 11 papers with code

Improving Translation Faithfulness of Large Language Models via Augmenting Instructions

1 code implementation24 Aug 2023 Yijie Chen, Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou

The experimental results demonstrate significant improvements in translation performance with SWIE based on BLOOMZ-3b, particularly in zero-shot and long text translations due to reduced instruction forgetting risk.

Instruction Following Machine Translation +2

Instruction Position Matters in Sequence Generation with Large Language Models

1 code implementation23 Aug 2023 Yijin Liu, Xianfeng Zeng, Fandong Meng, Jie zhou

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning.

Instruction Following Position +2

Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation

1 code implementation6 Aug 2023 Xianfeng Zeng, Yijin Liu, Fandong Meng, Jie zhou

To address this issue, we propose to utilize \textit{multiple references} to enhance the consistency between these metrics and human evaluations.

nlg evaluation Text Generation

BranchNorm: Robustly Scaling Extremely Deep Transformers

no code implementations4 May 2023 Yijin Liu, Xianfeng Zeng, Fandong Meng, Jie zhou

Recently, DeepNorm scales Transformers into extremely deep (i. e., 1000 layers) and reveals the promising potential of deep scaling.

Towards Robust Online Dialogue Response Generation

no code implementations7 Mar 2022 Leyang Cui, Fandong Meng, Yijin Liu, Jie zhou, Yue Zhang

Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings.

Chatbot Re-Ranking +1

Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

1 code implementation ACL 2022 Songming Zhang, Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jian Liu, Jie zhou

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e. g., token frequency or mutual information).

Language Modelling Machine Translation +2

Subspace modeling for fast and high-sensitivity X-ray chemical imaging

no code implementations1 Jan 2022 Jizhou Li, Bin Chen, Guibin Zan, Guannan Qian, Piero Pianetta, Yijin Liu

Resolving morphological chemical phase transformations at the nanoscale is of vital importance to many scientific and industrial applications across various disciplines.

Denoising Vocal Bursts Intensity Prediction

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation

1 code implementation EMNLP 2021 Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou

Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the gap between training and inference.

Machine Translation Text Summarization +1

WeChat Neural Machine Translation Systems for WMT21

no code implementations WMT (EMNLP) 2021 Xianfeng Zeng, Yijin Liu, Ernan Li, Qiu Ran, Fandong Meng, Peng Li, Jinan Xu, Jie zhou

This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German.

Knowledge Distillation Machine Translation +3

Confidence-Aware Scheduled Sampling for Neural Machine Translation

1 code implementation Findings (ACL) 2021 Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou

In this way, the model is exactly exposed to predicted tokens for high-confidence positions and still ground-truth tokens for low-confidence positions.

Machine Translation Translation

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

1 code implementation ACL 2021 Yangyifan Xu, Yijin Liu, Fandong Meng, Jiajun Zhang, Jinan Xu, Jie zhou

Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem.

Machine Translation Translation

Prevent the Language Model from being Overconfident in Neural Machine Translation

1 code implementation ACL 2021 Mengqi Miao, Fandong Meng, Yijin Liu, Xiao-Hua Zhou, Jie zhou

The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation.

Hallucination Language Modelling +4

Faster Depth-Adaptive Transformers

no code implementations27 Apr 2020 Yijin Liu, Fandong Meng, Jie zhou, Yufeng Chen, Jinan Xu

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency.

Sentence Embeddings text-classification +1

Depth-Adaptive Graph Recurrent Network for Text Classification

1 code implementation29 Feb 2020 Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously.

General Classification Sentence +2

CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding

2 code implementations IJCNLP 2019 Yijin Liu, Fandong Meng, Jinchao Zhang, Jie zhou, Yufeng Chen, Jinan Xu

Spoken Language Understanding (SLU) mainly involves two tasks, intent detection and slot filling, which are generally modeled jointly in existing works.

Intent Detection slot-filling +2

GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling

1 code implementation ACL 2019 Yijin Liu, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen, Jie zhou

Current state-of-the-art systems for sequence labeling are typically based on the family of Recurrent Neural Networks (RNNs).

Ranked #17 on Named Entity Recognition (NER) on CoNLL 2003 (English) (using extra training data)

Chunking NER +2

Cannot find the paper you are looking for? You can Submit a new open access paper.