语言大模型 / LLM

Leveraging Knowledge Graph Embeddings to Enhance Contextual Representations for Relation Extraction

Fréjus A. A. Laleye, Loïc Rakotoson, Sylvain Massip

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Comments 15 pages, 1 figures, The 17th International Conference on Document Analysis and Recognition

Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate

Michela Lorandi, Anya Belz

专题命中 预训练与数据 ：prompting(abstract)；分类 cs.CL、cs.AI

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Seungju Han, Jack Hessel, Nouha Dziri, Yejin Choi, Youngjae Yu

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments ICCV 2023, Project page: https://seungjuhan.me/champagne

GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking

Jiaqi Bai, Hongcheng Guo, Jiaheng Liu, Jian Yang, Xinnian Liang, Zhao Yan, Zhoujun Li

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments CIKM 2023

Gloss Alignment Using Word Embeddings

Harry Walsh, Ozge Mercanoglu Sincan, Ben Saunders, Richard Bowden

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments 4 pages, 4 figures, 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies

Ke Chen, Yusong Wu, Haohe Liu, Marianna Nezhurina, Taylor Berg-Kirkpatrick, Shlomo Dubnov

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 16 pages, 3 figures, 2 tables, demo page: https://musicldm.github.io/

How User Language Affects Conflict Fatality Estimates in ChatGPT

Daniel Kazenwadel, Christoph V. Steinert

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments †both authors contributed equally

Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks

João A. Leite, Carolina Scarton, Diego F. Silva

专题命中 预训练与数据 ：prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted to RANLP 2023

A Neural-Symbolic Approach Towards Identifying Grammatically Correct Sentences

Nicos Isaak

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 3 figures, 3 tables

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, Kai-Wei Chang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 22 pages. Accepted at ICCV 2023

Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification

Dmitry Karpov, Mikhail Burtsev

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI

Less is More: Selective Layer Finetuning with SubTuning

Gal Kaplun, Andrey Gurevich, Tal Swisa, Mazor David, Shai Shalev-Shwartz, Eran Malach

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation

Seugnjun Lee, Hyeonseok Moon, Chanjun Park, Heuiseok Lim

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted for Data-centric Machine Learning Research (DMLR) Workshop at ICML 2023

How About Kind of Generating Hedges using End-to-End Neural Models?

Alafate Abulimiti, Chloé Clavel, Justine Cassell

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks

Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.LG

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese

Takuro Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita, Yasuhiro Sogawa

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at ACL SRW 2023

DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling

Yuchen Zhuang, Yue Yu, Lingkai Kong, Xiang Chen, Chao Zhang

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted by KDD 2023 research track

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolai Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua, Tomas Pfister

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ACL 2023

Generating Synthetic Datasets by Interpolating along Generalized Geodesics

Jiaojiao Fan, David Alvarez-Melis

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Journal ref Conference on Uncertainty in Artificial Intelligence (UAI) 2023

Cliff-Learning

Tony T. Wang, Igor Zablotchi, Nir Shavit, Jonathan S. Rosenfeld

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.AI、cs.LG

Comments 16 pages; v2 updates: improved layout, added acknowledgements

Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers

Félix Gaschi, Patricio Cerda, Parisa Rastin, Yannick Toussaint

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Explanation Graph Generation via Generative Pre-training over Synthetic Graphs

Han Cui, Shangzhan Li, Yu Zhang, Qi Shi

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ACL23-Findings

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Vivien Cabannes, Bobak T. Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Journal ref Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023

End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization

Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments Accepted at ICML 2023

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

Boris Knyazev, Doha Hwang, Simon Lacoste-Julien

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments ICML 2023, camera ready (7 tables with extra results added), code and models are at https://github.com/SamsungSAILMontreal/ghn3

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam Klivans

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.AI、cs.LG

Comments 24 pages, 11 figures

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL 2023 Findings

Slide, Constrain, Parse, Repeat: Synchronous SlidingWindows for Document AMR Parsing

Sadhana Kumaravel, Tahira Naseem, Ramon Fernandez Astudillo, Radu Florian, Salim Roukos

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Diversity-Aware Coherence Loss for Improving Neural Topic Models

Raymond Li, Felipe González-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.LG

Comments Minor Fixes, 11 pages, Camera-Ready for ACL 2023 (Short Paper)

Skill-Based Reinforcement Learning with Intrinsic Reward Matching

Ademi Adeniji, Amber Xie, Pieter Abbeel

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 16 pages