Search Results for author: ShuJian Huang

Found 66 papers, 40 papers with code

Towards Multi-label Unknown Intent Detection

1 code implementation COLING 2022 Yawen Ouyang, Zhen Wu, Xinyu Dai, ShuJian Huang, Jiajun Chen

In this paper, we propose a more desirable task, multi-label unknown intent detection, to detect whether the utterance contains the unknown intent, in which each utterance may contain multiple intents.

Intent Detection

NJU’s submission to the WMT20 QE Shared Task

no code implementations WMT (EMNLP) 2020 Qu Cui, Xiang Geng, ShuJian Huang, Jiajun Chen

This paper describes our system of the sentence-level and word-level Quality Estimation Shared Task of WMT20.

Language Modelling Sentence

Learning from Adjective-Noun Pairs: A Knowledge-enhanced Framework for Target-Oriented Multimodal Sentiment Classification

1 code implementation COLING 2022 Fei Zhao, Zhen Wu, Siyu Long, Xinyu Dai, ShuJian Huang, Jiajun Chen

Target-oriented multimodal sentiment classification (TMSC) is a new subtask of aspect-based sentiment analysis, which aims to determine the sentiment polarity of the opinion target mentioned in a (sentence, image) pair.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification

no code implementations EMNLP 2021 Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, ShuJian Huang, Jiajun Chen

However, the simple extension of meta-learning approaches to multi-label classification is sub-optimal for LMTC tasks due to long-tailed label distribution and coexisting of few- and zero-shot scenarios.

Meta-Learning Multi-Label Classification +3

GLAT: Glancing at Latent Variables for Parallel Text Generation

1 code implementation ACL 2022 Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI

Recently, parallel text generation has received widespread attention due to its success in generation efficiency.

Text Generation

Data Augmentation for Low-resource Word Segmentation and POS Tagging of Ancient Chinese Texts

no code implementations LT4HALA (LREC) 2022 Yutong Shen, Jiahuan Li, ShuJian Huang, Yi Zhou, Xiaopeng Xie, Qinxin Zhao

Although SikuRoberta significantly boosts performance on WSG and POS tasks on ancient Chinese texts, the lack of labeled data still limits the performance of the model.

Data Augmentation Language Modelling +3

Limited Out-of-Context Knowledge Reasoning in Large Language Models

no code implementations11 Jun 2024 Peng Hu, Changjiang Gao, Ruiqi Gao, Jiajun Chen, ShuJian Huang

Using this dataset, we evaluated the LLaMA2-13B-chat model and discovered that its proficiency in this aspect is limited, regardless of whether the knowledge is trained in a separate or adjacent training settings.

Transfer Learning

Extroversion or Introversion? Controlling The Personality of Your Large Language Models

1 code implementation7 Jun 2024 Yanquan Chen, Zhen Wu, Junjie Guo, ShuJian Huang, Xinyu Dai

Our investigation revealed a hierarchy of effectiveness in control: Prompt > SFT > RLHF > Continual Pre-train.

Text Generation

Why Not Transform Chat Large Language Models to Non-English?

1 code implementation22 May 2024 Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Xinglin Lyu, Min Zhang, Jiajun Chen, Hao Yang, ShuJian Huang

For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.

Knowledge Distillation

The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights

1 code implementation2 May 2024 Wenhao Zhu, ShuJian Huang, Fei Yuan, Cheng Chen, Jiajun Chen, Alexandra Birch

In this paper, we explore how broadly this method can be applied by examining its effects in reasoning with executable code and reasoning with common sense.

Common Sense Reasoning Translation

Enforcing Paraphrase Generation via Controllable Latent Diffusion

1 code implementation13 Apr 2024 Wei Zou, Ziyuan Zhuang, ShuJian Huang, Jia Liu, Jiajun Chen

Paraphrase generation aims to produce high-quality and diverse utterances of a given text.

Paraphrase Generation

Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly

1 code implementation6 Apr 2024 Changjiang Gao, Hongda Hu, Peng Hu, Jiajun Chen, Jixing Li, ShuJian Huang

In this paper, we propose CLiKA, a systematic framework to assess the cross-lingual knowledge alignment of LLMs in the Performance, Consistency and Conductivity levels, and explored the effect of multilingual pretraining and instruction tuning on the degree of alignment.

EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling

1 code implementation21 Mar 2024 Shimao Zhang, Yu Bao, ShuJian Huang

However, a fixed temperature parameter is used in most cases, which may not always be an optimal choice for balancing generation quality and diversity.

MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation

no code implementations14 Mar 2024 Jiahuan Li, Shanbo Cheng, ShuJian Huang, Jiajun Chen

Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT), yet they suffer from high computational cost and latency.

Knowledge Distillation Machine Translation +1

Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models

no code implementations7 Mar 2024 Changjiang Gao, Jixing Li, Jiajun Chen, ShuJian Huang

Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension.

Sentence

Diffusion Language Models Are Versatile Protein Learners

no code implementations28 Feb 2024 Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, ShuJian Huang, Quanquan Gu

This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences.

Protein Language Model

Cobra Effect in Reference-Free Image Captioning Metrics

no code implementations18 Feb 2024 Zheng Ma, Changxin Wang, Yawen Ouyang, Fei Zhao, Jianbing Zhang, ShuJian Huang, Jiajun Chen

If a certain metric has flaws, it will be exploited by the model and reflected in the generated sentences.

Image Captioning

Question Translation Training for Better Multilingual Reasoning

1 code implementation15 Jan 2024 Wenhao Zhu, ShuJian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch

A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training.

Mathematical Reasoning Translation

Multi-Candidate Speculative Decoding

1 code implementation12 Jan 2024 Sen yang, ShuJian Huang, Xinyu Dai, Jiajun Chen

One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model.

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization

1 code implementation12 Jan 2024 Shuaijie She, Wei Zou, ShuJian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

To enhance reasoning abilities in non-dominant languages, we propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO), aiming to align the reasoning processes in other languages with the dominant language.

Mathematical Reasoning

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation

1 code implementation12 Jan 2024 Xu Huang, Zhirui Zhang, Xiang Geng, Yichao Du, Jiajun Chen, ShuJian Huang

This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task.

Machine Translation Translation

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

1 code implementation14 Nov 2023 Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, ShuJian Huang

Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies.

Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models

no code implementations13 Nov 2023 Shuaijie She, ShuJian Huang, Xingyun Wang, Yanke Zhou, Jiajun Chen

For answering the factual questions, which is more challenging, the average error rate of all evaluated LLMs is 36. 1%.

Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention

1 code implementation29 Oct 2023 Changjiang Gao, ShuJian Huang, Jixing Li, Jiajun Chen

Recent large language models (LLMs) have revealed strong abilities to understand natural language.

IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems

1 code implementation17 Oct 2023 Xu Huang, Zhirui Zhang, Ruize Gao, Yichao Du, Lemao Liu, Gouping Huang, Shuming Shi, Jiajun Chen, ShuJian Huang

We present IMTLab, an open-source end-to-end interactive machine translation (IMT) system platform that enables researchers to quickly build IMT systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.

Machine Translation Translation

Dynamic Demonstrations Controller for In-Context Learning

1 code implementation30 Sep 2023 Fei Zhao, Taotian Pang, Zhen Wu, Zheng Ma, ShuJian Huang, Xinyu Dai

Previous studies have revealed that ICL is sensitive to the selection and the ordering of demonstrations.

In-Context Learning Language Modelling +1

Only 5\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation

no code implementations25 Sep 2023 Zihan Liu, Zewei Sun, Shanbo Cheng, ShuJian Huang, Mingxuan Wang

Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information.

Dimensionality Reduction Machine Translation +1

Extrapolating Large Language Models to Non-English by Aligning Languages

2 code implementations9 Aug 2023 Wenhao Zhu, Yunzhe Lv, Qingxiu Dong, Fei Yuan, Jingjing Xu, ShuJian Huang, Lingpeng Kong, Jiajun Chen, Lei LI

We start from targeting individual languages by performing cross-lingual instruction-tuning (CoIT) on LLaMA, i. e. tuning it with translation task data and cross-lingual general task data to obtain cross-lingual models (x-LLaMAs), and formulate underlying scaling laws to investigate the advantages of using scalable translation data.

Translation

Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models

1 code implementation6 Aug 2023 Zheng Ma, Mianzhi Pan, Wenhan Wu, Kanzhi Cheng, Jianbing Zhang, ShuJian Huang, Jiajun Chen

Experiments on our proposed datasets demonstrate that popular VLMs underperform in the food domain compared with their performance in the general domain.

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training

no code implementations6 Jul 2023 Yiming Yan, Tao Wang, Chengqi Zhao, ShuJian Huang, Jiajun Chen, Mingxuan Wang

In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems.

Machine Translation Sentence +1

INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation

1 code implementation10 Jun 2023 Wenhao Zhu, Jingjing Xu, ShuJian Huang, Lingpeng Kong, Jiajun Chen

We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parameters.

Machine Translation Translation

Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

no code implementations24 May 2023 Jiahuan Li, Hao Zhou, ShuJian Huang, Shanbo Cheng, Jiajun Chen

Secondly, we find that LLMs' ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages.

Language Modelling Translation

Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation

no code implementations31 Mar 2023 Min Liu, Yu Bao, Chengqi Zhao, ShuJian Huang

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks.

Knowledge Distillation Machine Translation +1

kNN-BOX: A Unified Framework for Nearest Neighbor Generation

1 code implementation27 Feb 2023 Wenhao Zhu, Qianfeng Zhao, Yunzhe Lv, ShuJian Huang, Siheng Zhao, Sizhe Liu, Jiajun Chen

Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT).

Machine Translation Paraphrase Generation +4

CoP: Factual Inconsistency Detection by Controlling the Preference

1 code implementation3 Dec 2022 Shuaijie She, Xiang Geng, ShuJian Huang, Jiajun Chen

To separate the preference for factual consistency, we propose an unsupervised framework named CoP by controlling the preference of the generation model with the help of prompt.

Abstractive Text Summarization

Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators

1 code implementation11 Nov 2022 Xinyou Wang, Zaixiang Zheng, ShuJian Huang

Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding.

Decoder Machine Translation +1

What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation

1 code implementation8 Nov 2022 Wenhao Zhu, ShuJian Huang, Yunzhe Lv, Xin Zheng, Jiajun Chen

kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus.

Domain Adaptation NMT +1

Structure-Unified M-Tree Coding Solver for MathWord Problem

1 code implementation22 Oct 2022 Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, ShuJian Huang, Jiajun Chen

As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years.

Math

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective

no code implementations18 Oct 2022 Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, ShuJian Huang, Xinyu Dai, Jiajun Chen

In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.

Image Captioning Sentence

A Numerical Reasoning Question Answering System with Fine-grained Retriever and the Ensemble of Multiple Generators for FinQA

no code implementations17 Jun 2022 Bin Wang, Jiangzhou Ju, Yunlin Mao, Xin-yu Dai, ShuJian Huang, Jiajun Chen

Here, we propose a numerical reasoning question answering system to answer numerical reasoning questions among financial text and table data sources, consisting of a retriever module, a generator module, and an ensemble module.

Question Answering

Analyzing the Intensity of Complaints on Social Media

1 code implementation Findings (NAACL) 2022 Ming Fang, Shi Zong, Jing Li, Xinyu Dai, ShuJian Huang, Jiajun Chen

Furthermore, we conduct a comprehensive linguistic analysis around complaints, including the connections between complaints and sentiment, and a cross-lingual comparison for complaints expressions used by Chinese and English speakers.

$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation

1 code implementation5 Apr 2022 Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI

Recently, parallel text generation has received widespread attention due to its success in generation efficiency.

Text Generation

Non-Parametric Online Learning from Human Feedback for Neural Machine Translation

1 code implementation23 Sep 2021 Dongqi Wang, Haoran Wei, Zhirui Zhang, ShuJian Huang, Jun Xie, Jiajun Chen

We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected translations are used to improve the neural machine translation (NMT) system.

Machine Translation NMT +1

Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation

1 code implementation Findings (EMNLP) 2021 Xin Zheng, Zhirui Zhang, ShuJian Huang, Boxing Chen, Jun Xie, Weihua Luo, Jiajun Chen

Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.

Machine Translation NMT +3

Energy-based Unknown Intent Detection with Data Manipulation

2 code implementations Findings (ACL) 2021 Yawen Ouyang, Jiasheng Ye, Yu Chen, Xinyu Dai, ShuJian Huang, Jiajun Chen

Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.

Intent Detection

Adaptive Nearest Neighbor Machine Translation

3 code implementations ACL 2021 Xin Zheng, Zhirui Zhang, Junliang Guo, ShuJian Huang, Boxing Chen, Weihua Luo, Jiajun Chen

On four benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively filter out the noises in retrieval results and significantly outperforms the vanilla kNN-MT model.

Machine Translation NMT +2

DirectQE: Direct Pretraining for Machine Translation Quality Estimation

no code implementations15 May 2021 Qu Cui, ShuJian Huang, Jiahuan Li, Xiang Geng, Zaixiang Zheng, Guoping Huang, Jiajun Chen

However, we argue that there are gaps between the predictor and the estimator in both data quality and training objectives, which preclude QE models from benefiting from a large number of parallel corpora more directly.

Machine Translation Translation

Dual Side Deep Context-aware Modulation for Social Recommendation

1 code implementation16 Mar 2021 Bairan Fu, Wenming Zhang, GuangNeng Hu, Xinyu Dai, ShuJian Huang, Jiajun Chen

Specifically, we first proposed a novel graph neural network to model the social relation and collaborative relation, and on top of high-order relations, a dual side deep context-aware modulation is introduced to capture the friends' information and item attraction.

Graph Neural Network Relation

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation

1 code implementation LREC 2022 Wenhao Zhu, ShuJian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen

Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.

Autonomous Vehicles Domain Adaptation +3

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction

no code implementations COLING 2020 Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, ShuJian Huang, Tong Xiao, Jingbo Zhu

Our experiments show that this simple method does not hamper the performance of similar language pairs and achieves an accuracy of 13. 64~55. 53% between English and four distant languages, i. e., Chinese, Japanese, Vietnamese and Thai.

Dimensionality Reduction Self-Learning

Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification

no code implementations1 Nov 2020 Chengcan Ying, Zhen Wu, Xinyu Dai, ShuJian Huang, Jiajun Chen

In this paper, we propose a novel joint model, Opinion Transmission Network (OTN), to exploit the potential bridge between ALSC and AOWE to achieve the goal of facilitating them simultaneously.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Non-linear Learning for Statistical Machine Translation

no code implementations IJCNLP 2015 Shujian Huang, Huadong Chen, Xin-yu Dai, Jia-Jun Chen

The linear combination assumes that all the features are in a linear relationship and constrains that each feature interacts with the rest features in an linear manner, which might limit the expressive power of the model and lead to a under-fit model on the current data.

Machine Translation Translation

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