语言大模型 / LLM

Towards the Generation of Musical Explanations with GPT-3

Stephen James Krol, Maria Teresa Llano, Jon McCormack

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Journal ref Artificial Intelligence in Music, Sound, Art and Design - 11th International Conference, EvoMUSART 2022, Held as Part of EvoStar 2022

TAG: Toward Accurate Social Media Content Tagging with a Concept Graph

Jiuding Yang, Weidong Guo, Bang Liu, Yakun Yu, Chaoyue Wang, Jinwen Luo, Linglong Kong, Di Niu, Zhen Wen

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted by ACM SIGKDD 2022

Lightweight Cross-Lingual Sentence Representation Learning

Zhuoyuan Mao, Prakhar Gupta, Pei Wang, Chenhui Chu, Martin Jaggi, Sadao Kurohashi

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments ACL 2021 main conference; modified Eq. (2)

Progressive Class Semantic Matching for Semi-supervised Text Classification

Hai-Ming Xu, Lingqiao Liu, Ehsan Abbasnejad

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments NAACL2022 (oral)

Transformers as Neural Augmentors: Class Conditional Sentence Generation via Variational Bayes

M. Şafak Bilici, Mehmet Fatih Amasyali

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

KERMIT -- A Transformer-Based Approach for Knowledge Graph Matching

Sven Hertling, Jan Portisch, Heiko Paulheim

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments accepted at the DeepOntoNLP Workshop at the ESWC 2022

Vision-Language Pre-Training for Boosting Scene Text Detectors

Sibo Song, Jianqiang Wan, Zhibo Yang, Jun Tang, Wenqing Cheng, Xiang Bai, Cong Yao

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by CVPR 2022

Probing Script Knowledge from Pre-Trained Models

Zijian Jin, Xingyu Zhang, Mo Yu, Lifu Huang

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Generative Pre-Trained Transformers for Biologically Inspired Design

Qihao Zhu, Xinyu Zhang, Jianxi Luo

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted by the 34th ASME IDETC-CIE International Conference on Design Theory & Methodology

Multilingual Molecular Representation Learning via Contrastive Pre-training

Zhihui Guo, Pramod Sharma, Andy Martinez, Liang Du, Robin Abraham

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ACL 2022 main conference

Question rewriting? Assessing its importance for conversational question answering

Gonçalo Raposo, Rui Ribeiro, Bruno Martins, Luísa Coheur

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Submitted manuscript (not anonymized) accepted to the 44th European Conference on Information Retrieval (ECIR) 2022. This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in Advances in Information Retrieval, and is available online at https://doi.org/10.1007/978-3-030-99739-7_23

LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond

Daniel Loureiro, Alípio Mário Jorge, Jose Camacho-Collados

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to Artificial Intelligence Journal (AIJ)

Journal ref Artificial Intelligence Volume 305, April 2022, 103661

Visualizing the Relationship Between Encoded Linguistic Information and Task Performance

Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Findings of ACL 2022

Interpretability of Fine-grained Classification of Sadness and Depression

Tiasa Singha Roy, Priyam Basu, Aman Priyanshu, Rakshit Naidu

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments 4 pages, 3 figures

Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers

Christopher Schröder, Andreas Niekler, Martin Potthast

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments ACL 2022 Findings

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Vishal Dey, Raghu Machiraju, Xia Ning

专题命中 知识编辑与模型理解 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments This manuscript has been accepted at ACS Omega

Journal ref ACS Omega 2022

When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing

Chao-Han Huck Yang, Jun Qi, Samuel Yen-Chi Chen, Yu Tsao, Pin-Yu Chen

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ICASSP 2022

Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles

Boshko Koloski, Timen Stepišnik-Perdih, Marko Robnik-Šikonja, Senja Pollak, Blaž Škrlj

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations

Minhao Jiang, Xiangchen Song, Jieyu Zhang, Jiawei Han

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments WWW 2022

Active Multi-Task Representation Learning

Yifang Chen, Simon S. Du, Kevin Jamieson

专题命中 知识编辑与模型理解 ：pretraining(abstract)；分类 cs.AI、cs.LG

PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World

Rowan Zellers, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Aniruddha Kembhavi, Ali Farhadi, Yejin Choi

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments ACL 2021 camera ready, project page at https://rowanzellers.com/piglet/

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation

Jixuan Wang, Kuan-Chieh Wang, Frank Rudzicz, Michael Brudno

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2021

Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition

Yiming Wang, Jinyu Li, Heming Wang, Yao Qian, Chengyi Wang, Yu Wu

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at IEEE ICASSP 2022. 5 pages, 1 figure

Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections

Victor S. Bursztyn, Jennifer Healey, Vishwa Vinay

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the NeurIPS 2021 Workshop on Machine Learning for Creativity and Design

Interpretable Privacy Preservation of Text Representations Using Vector Steganography

Geetanjali Bihani

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at AAAI 2022 Doctoral Consortium

VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

Qibin Chen, Jeremy Lacomis, Edward J. Schwartz, Graham Neubig, Bogdan Vasilescu, Claire Le Goues

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted by ICSE 2022

TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect

Abir Messaoudi, Ahmed Cheikhrouhou, Hatem Haddad, Nourchene Ferchichi, Moez BenHajhmida, Abir Korched, Malek Naski, Faten Ghriss, Amine Kerkeni

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.LG

Commit2Vec: Learning Distributed Representations of Code Changes

Rocìo Cabrera Lozoya, Arnaud Baumann, Antonino Sabetta, Michele Bezzi

专题命中 知识编辑与模型理解 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments A previous version of this paper had the following title: "patch2vec: Distributed Representation of Code Changes"; we updated the title to distinguish it from another pre-existing approach with the same name. An improved version of this work appeared in Springer Nature Computer Science, 2021 (https://doi.org/10.1007/s42979-021-00566-z)

Journal ref SN Computer Science volume 2, Article number: 150 (2021)

A text autoencoder from transformer for fast encoding language representation

Tan Huang

专题命中 知识编辑与模型理解 ：language model(abstract)；分类 cs.CL、cs.AI

Comments 8 pages, 8 figures. arXiv admin note: text overlap with arXiv:2004.08097 by other authors

Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach

Divish Rengasamy, Jimiama M. Mase, Mercedes Torres Torres, Benjamin Rothwell, David A. Winkler, Grazziela P. Figueredo

专题命中 知识编辑与模型理解 ：post-training(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 11 figures, 8 tables