语言大模型 / LLM - arXivDaily 专题

2209.12412 2022-09-27 cs.LG cs.AI 62%

DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning

Simeon Adebola, Satvik Sharma, Kaushik Shivakumar

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

2209.08206 2022-09-20 cs.CL cs.LG 62%

Selective Token Generation for Few-shot Natural Language Generation

Daejin Jo, Taehwan Kwon, Eun-Sol Kim, Sungwoong Kim

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

Comments COLING 2022

2205.09328 2022-09-19 cs.LG cs.AI 62%

TransTab: Learning Transferable Tabular Transformers Across Tables

Zifeng Wang, Jimeng Sun

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

Comments NeurIPS 2022

2103.06459 2022-09-16 cs.CL cs.AI 62%

Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

Linlin Liu, Thien Hai Nguyen, Shafiq Joty, Lidong Bing, Luo Si

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

Comments Accepted by COLING 2022

2209.06243 2022-09-15 cs.CL cs.LG 62%

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task

Ricardo Rei, Marcos Treviso, Nuno M. Guerreiro, Chrysoula Zerva, Ana C. Farinha, Christine Maroti, José G. C. de Souza, Taisiya Glushkova, Duarte M. Alves, Alon Lavie, Luisa Coheur, André F. T. Martins

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

Comments WMT 2022 Quality Estimation shared task

2209.05707 2022-09-14 cs.CL cs.LG 62%

Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale

Daniel DiPietro, Vivek Hazari, Soroush Vosoughi

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

Comments 10 pages, 4 figures

2203.09343 2022-08-17 cs.CV cs.AI cs.LG 62%

CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation

Renhao Wang, Hang Zhao, Yang Gao

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

Comments Accepted to ECCV 2022

2110.02711 2022-08-12 cs.CV cs.AI cs.LG 62%

DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation

Gwanghyun Kim, Taesung Kwon, Jong Chul Ye

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

Comments Accepted to CVPR 2022

2208.02189 2022-08-04 eess.AS cs.CL cs.LG cs.SD 62%

A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Qibing Bai, Tom Ko, Yu Zhang

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

Comments Accepted by INTERSPEECH 2022

2208.01182 2022-08-03 cs.LG cs.AI cs.CY 62%

Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning

Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio, Laura Cruz, Kerrie Douglas, Andrew Lan, Christopher Brinton

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

Comments 10 pages, CIKM 2022

2204.03958 2022-08-01 cs.CL cs.AI 62%

Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation

Shumpei Inoue, Tsungwei Liu, Nguyen Hong Son, Minh-Tien Nguyen

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

Comments This paper was accepted by 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022). It includes 10 pages, 2 figures

2206.02368 2022-07-28 cs.CL cs.LG 62%

Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation

Pengzhi Gao, Zhongjun He, Hua Wu, Haifeng Wang

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

Comments NAACL 2022 main conference

2207.10551 2022-07-22 cs.LG cs.CL 62%

Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?

Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q. Tran, Dani Yogatama, Donald Metzler

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

2207.09150 2022-07-20 cs.CL cs.AI 62%

On the Usability of Transformers-based models for a French Question-Answering task

Oralie Cattan, Christophe Servan, Sophie Rosset

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

Comments French compact model paper: FrALBERT, Accepted to RANLP 2021

2207.06000 2022-07-14 cs.CL cs.LG cs.SD eess.AS 62%

Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS

Yookyung Shin, Younggun Lee, Suhee Jo, Yeongtae Hwang, Taesu Kim

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

Comments Accepted to Interspeech 2022

2207.04043 2022-07-11 cs.CL cs.CY cs.LG 62%

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

Mirac Suzgun, Luke Melas-Kyriazi, Suproteem K. Sarkar, Scott Duke Kominers, Stuart M. Shieber

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

Comments Website: https://patentdataset.org/, GitHub Repository: https://github.com/suzgunmirac/hupd, Hugging Face Datasets: https://huggingface.co/datasets/HUPD/hupd

2206.15147 2022-07-04 cs.CL cs.AI 62%

esCorpius: A Massive Spanish Crawling Corpus

Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé, David Griol, Zoraida Callejas

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

Comments esCorpius is available on https://huggingface.co/datasets/LHF/escorpius

2206.14982 2022-07-01 cs.CL cs.AI 62%

Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations

Akiko Eriguchi, Shufang Xie, Tao Qin, Hany Hassan Awadalla

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

Comments NAACL 2022

2206.14318 2022-06-30 cs.CL cs.LG eess.AS 62%

Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding

Pu Wang, Hugo Van hamme

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

Comments Accepted by Interspeech 2022

2204.09606 2022-06-29 cs.CL cs.CR cs.LG cs.SD eess.AS 62%

Detecting Unintended Memorization in Language-Model-Fused ASR

W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews

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

Comments Interspeech 2022

2206.10139 2022-06-22 cs.LG cs.AI 62%

Insights into Pre-training via Simpler Synthetic Tasks

Yuhuai Wu, Felix Li, Percy Liang

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

Comments 30 pages

2112.02845 2022-06-13 cs.LG cs.AI cs.MA 62%

Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

Linghui Meng, Muning Wen, Yaodong Yang, Chenyang Le, Xiyun Li, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Bo Xu

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

Comments 17 pages, 6 figures

2206.04571 2022-06-10 cs.CL cs.LG cs.SD eess.AS 62%

Revisiting End-to-End Speech-to-Text Translation From Scratch

Biao Zhang, Barry Haddow, Rico Sennrich

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

Comments ICML

2205.15509 2022-06-01 cs.CV cs.AI cs.CL 62%

ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts

Bingqian Lin, Yi Zhu, Zicong Chen, Xiwen Liang, Jianzhuang Liu, Xiaodan Liang

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

Comments Accepted to CVPR 2022

2205.14728 2022-06-01 cs.CL cs.LG 62%

L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library

Raviraj Joshi

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

2104.08661 2022-05-31 cs.CL cs.AI 62%

Explaining Answers with Entailment Trees

Bhavana Dalvi, Peter Jansen, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter Clark

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

Comments published in EMNLP 2021

2205.06457 2022-05-27 cs.CL cs.AI 62%

ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation

Long Phan, Hieu Tran, Hieu Nguyen, Trieu H. Trinh

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

Comments NAACL SRW 2022. arXiv admin note: text overlap with arXiv:2110.04257

2105.08840 2022-05-26 cs.CL cs.LG 62%

Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model

Yunhao Yang, Zhaokun Xue

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

Comments Accepted to Intelligent Systems Conference 2022

2101.00433 2022-05-26 cs.CL cs.AI cs.HC 62%

Modeling Disclosive Transparency in NLP Application Descriptions

Michael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, William Yang Wang

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

Comments To appear at EMNLP 2021. 15 pages, 10 figures, 7 tables

Journal ref Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp 2023-2037

2205.10764 2022-05-24 cs.CV cs.AI cs.CL cs.CY 62%

Evidence for Hypodescent in Visual Semantic AI

Robert Wolfe, Mahzarin R. Banaji, Aylin Caliskan

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

Comments To be published at ACM FAccT 2022

1. 预训练与数据 12534 篇

DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning

Selective Token Generation for Few-shot Natural Language Generation

TransTab: Learning Transferable Tabular Transformers Across Tables

Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task

Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale

CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation

DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation

A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning

Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation

Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation

Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?

On the Usability of Transformers-based models for a French Question-Answering task

Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

esCorpius: A Massive Spanish Crawling Corpus

Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations

Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding

Detecting Unintended Memorization in Language-Model-Fused ASR

Insights into Pre-training via Simpler Synthetic Tasks

Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

Revisiting End-to-End Speech-to-Text Translation From Scratch

ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts

L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library

Explaining Answers with Entailment Trees

ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation

Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model

Modeling Disclosive Transparency in NLP Application Descriptions

Evidence for Hypodescent in Visual Semantic AI