检索结果-内蒙古大学图书馆

Three-dimensional ATUM-SEM reconstruction and analysis of hepatic endoplasmic reticulum-organelle interactions

学校读者我要写书评

暂无评论

Journal of Molecular Cell Biology 2021年第9期13卷 636-645页

作者： Yi Jiang Linlin Li Xi Chen Jiazheng Liu Jingbin Yuan Qiwei Xie Hua Han National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 101408China School of Future Technology University of Chinese Academy of SciencesBeijing 101408China Data Mining Lab Beijing University of TechnologyBeijing 100124China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China

The endoplasmic reticulum(ER)is a contiguous and complicated membrane network in eukaryotic cells,and membrane contact sites(MCSs)between the ER and other organelles perform vital cellular functions,including lipid homeostasis,metabolite exchange,calcium level regulation,and organelle ***,we establish a whole pipeline to reconstruct all ER,mitochondria,lipid droplets,lysosomes,peroxisomes,and nuclei by automated tape-collecting ultramicrotome scanning electron microscopy and deep learning techniques,which generates an unprecedented 3D model for mapping liver ***,the morphology of various organelles and the MCSs between the ER and other organelles are systematically *** found that the ER presents with predominantly flat cisternae and is knitted tightly all throughout the intracellular space and around other *** addition,the ER has a smaller volume-to-membrane surface area ratio than other organelles,which suggests that the ER could be more suited for functions that require a large membrane surface *** data also indicate that ER-mitochondria contacts are particularly abundant,especially for branched *** study provides 3D reconstructions of various organelles in liver samples together with important fundamental information for biochemical and functional studies in the liver.

关键词： 3D reconstruction ATUM-SEM deep learning liver ER MCSs

Target-oriented fine-tuning for zero-resource named entity recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Ying Meng, Fandong Chen, Yufeng Xu, Jinan Zhou, Jie Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Pattern Recognition Center WeChat AI Tencent Inc China

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 data by fine-tuning on different auxiliary tasks. However, how to properly select training data and fine-tuning tasks is still an open problem. In this paper, we tackle the problem by transferring knowledge from three aspects, i.e., domain, language and task, and strengthening connections among them. Specifically, we propose four practical guidelines to guide knowledge transfer and task finetuning. Based on these guidelines, we design a target-oriented fine-tuning (TOF) framework to exploit various data from three aspects in a unified training manner. Experimental results on six benchmarks show that our method yields consistent improvements over baselines in both cross-domain and cross-lingual scenarios. Particularly, we achieve new state-of-theart performance on five benchmarks. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge management

Modeling bilingual conversational characteristics for neural chat translation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Yunlong Meng, Fandong Chen, Yufeng Xu, Jinan Zhou, Jie Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Pattern Recognition Center WeChat AI Tencent Inc China

Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine Translation (NMT), there still remain challenges to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency. In this paper, we aim to promote the translation quality of conversational text by modeling the above properties. Specifically, we design three latent variational modules to learn the distributions of bilingual conversational characteristics. Through sampling from these learned distributions, the latent variables, tailored for role preference, dialogue coherence, and translation consistency, are incorporated into the NMT model for better translation. We evaluate our approach on the benchmark dataset BConTrasT (English-German) and a self-collected bilingual dialogue corpus, named BMELD (English-Chinese). Extensive experiments show that our approach notably boosts the performance over strong baselines by a large margin and significantly surpasses some state-of-the-art context-aware NMT models in terms of BLEU and TER. Additionally, we make the BMELD dataset publicly available for the research community. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

Understanding Translationese in Cross-Lingual Summarization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jiaan Meng, Fandong Liang, Yunlong Zhang, Tingyi Xu, Jiarong Li, Zhixu Zhou, Jie Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Pattern Recognition Center WeChat AI Tencent Inc China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China School of Management Fudan University Shanghai China

Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with target-language summaries are rare. To collect large-scale CLS data, existing datasets typically involve translation in their creation. However, the translated text is distinguished from the text originally written in that language, i.e., translationese. In this paper, we first confirm that different approaches of constructing CLS datasets will lead to different degrees of translationese. Then we systematically investigate how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation;(2) the translationese in training sets would harm model performance in real-world applications;(3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies. Lastly, we give suggestions for future CLS research including dataset and model developments. We hope that our work could let researchers notice the phenomenon of translationese in CLS and take it into account in the future. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

Towards making the most of dialogue characteristics for neural chat translation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Yunlong Zhou, Chulun Meng, Fandong Xu, Jinan Chen, Yufeng Su, Jinsong Zhou, Jie Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University School of Informatics Xiamen University Pattern Recognition Center WeChat AI Tencent Inc China

Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware neural machine translation models, there still remain limitations in current NCT models because the inherent dialogue characteristics of chat, such as dialogue coherence and speaker personality, are neglected. In this paper, we propose to promote the chat translation by introducing the modeling of dialogue characteristics into the NCT model. To this end, we design four auxiliary tasks including monolingual response generation, cross-lingual response generation, next utterance discrimination, and speaker identification. Together with the main chat translation task, we optimize the NCT model through the training objectives of all these tasks. By this means, the NCT model can be enhanced by capturing the inherent dialogue characteristics, thus generating more coherent and speaker-relevant translations. Comprehensive experiments on four language directions (English⇔German and English⇔Chinese) verify the effectiveness and superiority of the proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

A Dual-Space Framework for General Knowledge Distillation of Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Xue Zhang, Songming Liang, Yunlong Meng, Fandong Chen, Yufeng Xu, Jinan Zhou, Jie School of Computer Science and Technology Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing Jiaotong University Beijing100044 China Pattern Recognition Center WeChat AI Tencent Inc China

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output distributions of the teacher model and the student model to transfer more information. However, we reveal that the current white-box KD framework exhibits two limitations: a) bridging probability distributions from different output spaces will limit the similarity between the teacher model and the student model;b) this framework cannot be applied to LLMs with different vocabularies. One of the root causes for these limitations is that the distributions from the teacher and the student for KD are output by different prediction heads, which yield distributions in different output spaces and dimensions. Therefore, in this paper, we propose a dual-space knowledge distillation (DSKD) framework that unifies the prediction heads of the teacher and the student models for KD. Specifically, we first introduce two projectors with ideal initialization to project the teacher/student hidden states into the student/teacher representation spaces. After this, the hidden states from different models can share the same head and unify the output spaces of the distributions. Furthermore, we develop an exact token alignment (ETA) algorithm to align the same tokens in two differently-tokenized sequences. Based on the above, our DSKD framework is a general KD framework that supports both off-policy and on-policy KD, and KD between any two LLMs regardless of their vocabularies. Extensive experiments on instruction-following, mathematical reasoning, and code generation benchmarks show that DSKD significantly outperforms existing methods based on the current white-box KD framework and surpasses other cross-tokenizer KD methods for LLMs with different vocabularies. © 2025, CC BY-NC-ND.

关键词： Distribution functions

Uo-cerpamid at IroSvA: Impostor method adaptation for irony detection IroSvA@IberLEF 2019

学校读者我要写书评

暂无评论

Uo-cerpamid at IroSvA: Impostor method adaptation for irony ...

2019 Iberian Languages Evaluation Forum, IberLEF 2019

作者： Castro, Daniel Benavides, Llinet Center for Pattern Recognition and Data Mining Universidad de Oriente Cuba Universidad de Oriente Cuba

Irony in text allows expressing implicit negative opinions, using a figurative and humorous language. IroSvA is a challenging task proposed this year that allows the evaluation of Irony Detection algorithms in the analysis of short texts for three Spanish language variants (Cuban, Spain and Mexican). Our proposal focuses on the study of three different representations of textual information and similarity measures using a weighted combination of these representations. We use an adaptation of the impostors method for classifying texts in Ironic or Non ironic. We consider the non-ironic texts of the training dataset as the list of impostors. The results achieved are encouraging and the best were obtained for the cuban variant. © 2019 CEUR-WS. All rights reserved.

关键词： Impostor method Irony detection Text similarity

Cerpamidua at MEXA3T 2019: Transition point proposal

学校读者我要写书评

暂无评论

Cerpamidua at MEXA3T 2019: Transition point proposal

2019 Iberian Languages Evaluation Forum, IberLEF 2019

作者： Castro, Daniel Castro Herold, María Fernanda Artigas Bueno, Reynier Ortega Muñoz, Rafael Center for Pattern Recognition and Data Mining Cuba Oriente University Cuba Department of Software and Computing systems Alicante University Spain

Author Profiling is an important field for detection of demographic characteristics of users based on texts written by him. Our main contribution is focused in determining a reduced subset of features that represent frequent lexical words for each profile of Mexican twitters. The new subset of features was obtained considering the frequency of words in a profile (e.g.: students), employing the theory of Transition Points. All the objects are represented in this new feature space conformed by all the reduced subset computed for each class or profile. The classification phase was carried out using Support Vector Machines provided by the Weka platform. The results obtained were good for Gender, but needs more efforts for Location and Occupation, because, the main factor that affects the results correspond to scenarios with unbalanced class distribution that impact the construction of the reduced vocabulary. © 2019 CEUR-WS. All rights reserved.

关键词： Support vector machines

Emotional Conversation Generation with Heterogeneous Graph Neural Network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liang, Yunlong Meng, Fandong Zhang, Ying Chen, Yufeng Xu, Jinan Zhou, Jie Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Pattern Recognition Center WeChat AI Tencent Inc China

The successful emotional conversation system depends on sufficient perception and appropriate expression of emotions. In a real-life conversation, humans firstly instinctively perceive emotions from multi-source information, including the emotion flow hidden in dialogue history, facial expressions, audio, and personalities of speakers. Then, they convey suitable emotions according to their personalities, but these multiple types of information are insufficiently exploited in emotional conversation fields. To address this issue, in this paper, we propose a heterogeneous graph-based model for emotional conversation generation. Firstly, we design a Heterogeneous Graph-Based Encoder to represent the conversation content (i.e., the dialogue history, its emotion flow, facial expressions, audio, and speakers' personalities) with a heterogeneous graph neural network, and then predict suitable emotions for feedback. Secondly, we employ an Emotion-Personality-Aware Decoder to generate a response relevant to the conversation context as well as with appropriate emotions, through taking the encoded graph representations, the predicted emotions by the encoder and the personality of the current speaker as inputs. Experiments on both automatic and human evaluation show that our method can effectively perceive emotions from multi-source knowledge and generate a satisfactory response. Furthermore, based on the up-to-date text generator BART, our model still can achieve consistent improvement, which significantly outperforms some existing state-of-the-art models. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks