语言大模型 / LLM - arXivDaily 专题

2110.08370 2022-03-16 cs.CL 57%

Training Dynamics for Text Summarization Models

Tanya Goyal, Jiacheng Xu, Junyi Jessy Li, Greg Durrett

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

Comments ACL 2022 Findings

2203.05794 2022-03-14 cs.CL 57%

BERTopic: Neural topic modeling with a class-based TF-IDF procedure

Maarten Grootendorst

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

Comments BERTopic has a python implementation, see https://github.com/MaartenGr/BERTopic

2203.04837 2022-03-10 eess.AS cs.CL cs.CY 57%

'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube

Krithika Ramesh, Ashiqur R. KhudaBukhsh, Sumeet Kumar

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

Comments This paper got accepted at AAAI 2022, AI for Social Impact track

2203.00286 2022-03-03 cs.CL 57%

"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction

Yong Dai, Linyang Li, Cong Zhou, Zhangyin Feng, Enbo Zhao, Xipeng Qiu, Piji Li, Duyu Tang

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

Comments Short paper in Findings of ACL 2022

2202.12801 2022-02-28 cs.CL 57%

On the data requirements of probing

Zining Zhu, Jixuan Wang, Bai Li, Frank Rudzicz

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

Comments Findings of ACL 2022

2202.12246 2022-02-25 cs.CL 57%

Neural reality of argument structure constructions

Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, Yang Xu

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

Comments ACL 2022 (Long Paper)

2102.11582 2022-01-31 cs.LG stat.ML 57%

Deep Deterministic Uncertainty: A Simple Baseline

Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal

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

2201.10262 2022-01-26 cs.CL 57%

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language

Mael Jullien, Marco Valentino, Andre Freitas

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

2103.12676 2022-01-05 eess.SP cs.LG stat.ML 57%

Self-supervised representation learning from 12-lead ECG data

Temesgen Mehari, Nils Strodthoff

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

Comments 15 pages, 12 figures, matches published version, code available under https://github.com/hhi-aml/ecg-selfsupervised

Journal ref Comput. Biol. Med. 141 (2022) 105114

2111.09296 2021-12-17 cs.CL cs.SD eess.AS 57%

XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

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

2104.05240 2021-12-15 cs.CL 57%

Factual Probing Is [MASK]: Learning vs. Learning to Recall

Zexuan Zhong, Dan Friedman, Danqi Chen

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

Comments NAACL 2021. The code is publicly available at https://github.com/princeton-nlp/OptiPrompt

2112.04814 2021-12-10 q-bio.BM cs.LG 57%

Multimodal Pre-Training Model for Sequence-based Prediction of Protein-Protein Interaction

Yang Xue, Zijing Liu, Xiaomin Fang, Fan Wang

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

Comments MLCB 2021 Spotlight

2112.04087 2021-12-09 cs.AI 57%

Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training

Ganqiang Ye, Wen Zhang, Zhen Bi, Chi Man Wong, Chen Hui, Huajun Chen

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

Comments Accepted to IJCKG 2021

2112.04014 2021-12-09 cs.LG cs.CV 57%

Unsupervised Representation Learning via Neural Activation Coding

Yookoon Park, Sangho Lee, Gunhee Kim, David M. Blei

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

Comments Published in International Conference on Machine Learning (ICML), 2021

2112.03340 2021-12-08 cs.CV cs.LG 57%

Label Hallucination for Few-Shot Classification

Yiren Jian, Lorenzo Torresani

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

Comments Accepted by AAAI 2022. Code is available: https://github.com/yiren-jian/LabelHalluc

2109.09784 2021-12-07 cs.CL 57%

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

Meng Cao, Yue Dong, Jackie Chi Kit Cheung

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

2111.15340 2021-12-01 cs.CV cs.LG 57%

MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning

Sara Atito, Muhammad Awais, Ammarah Farooq, Zhenhua Feng, Josef Kittler

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

1909.00204 2021-11-22 cs.CL 57%

NEZHA: Neural Contextualized Representation for Chinese Language Understanding

Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen, Qun Liu

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

2111.08400 2021-11-17 cs.CL cs.SD eess.AS 57%

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

Yi-Chang Chen, Chun-Yen Cheng, Chien-An Chen, Ming-Chieh Sung, Yi-Ren Yeh

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

2108.02923 2021-11-09 cs.CV cs.CL 57%

StrucTexT: Structured Text Understanding with Multi-Modal Transformers

Yulin Li, Yuxi Qian, Yuchen Yu, Xiameng Qin, Chengquan Zhang, Yan Liu, Kun Yao, Junyu Han, Jingtuo Liu, Errui Ding

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

Comments ACM Multimedia 2021. 9 pages

2111.00808 2021-11-02 cs.CL 57%

Unsupervised Discovery of Unaccusative and Unergative Verbs

Sharid Loáiciga, Luca Bevacqua, Christian Hardmeier

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

2110.10778 2021-10-22 cs.CL 57%

Contrastive Document Representation Learning with Graph Attention Networks

Peng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang, Bing Xiang

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

Comments Findings of EMNLP 2021

2110.07310 2021-10-15 cs.CL 57%

Solving Aspect Category Sentiment Analysis as a Text Generation Task

Jian Liu, Zhiyang Teng, Leyang Cui, Hanmeng Liu, Yue Zhang

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

Comments EMNLP 2021 main conference

2105.11314 2021-10-15 cs.CL 57%

RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model

Milan Straka, Jakub Náplava, Jana Straková, David Samuel

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

Comments Published in TSD 2021

2110.06376 2021-10-14 cs.CL 57%

ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality

Marianna Apidianaki, Aina Garí Soler

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

Comments Accepted to BlackboxNLP 2021

2104.07388 2021-10-14 eess.AS cs.LG cs.SD eess.SP 57%

Conditional independence for pretext task selection in Self-supervised speech representation learning

Salah Zaiem, Titouan Parcollet, Slim Essid

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

Comments 5 pages, Accepted for presentation at Interspeech2021

2109.09161 2021-10-12 cs.CL eess.AS 57%

Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition

Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin

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

2109.08565 2021-09-20 cs.CL 57%

Exploring Multitask Learning for Low-Resource AbstractiveSummarization

Ahmed Magooda, Mohamed Elaraby, Diane Litman

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

Comments To appear in proceedings of EMNLP 2021 (https://2021.emnlp.org/)

2105.06965 2021-09-16 cs.CL 57%

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction

Shauli Ravfogel, Grusha Prasad, Tal Linzen, Yoav Goldberg

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

Comments Equal contribution by SR and GP. Accepted in CoNLL 2021

2104.08455 2021-09-15 cs.CL 57%

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding

Nouha Dziri, Andrea Madotto, Osmar Zaiane, Avishek Joey Bose

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

Comments EMNLP 2021 18 pages

1. 知识编辑与模型理解 7596 篇

Training Dynamics for Text Summarization Models

BERTopic: Neural topic modeling with a class-based TF-IDF procedure

'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube

"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction

On the data requirements of probing

Neural reality of argument structure constructions

Deep Deterministic Uncertainty: A Simple Baseline

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language

Self-supervised representation learning from 12-lead ECG data

XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Factual Probing Is [MASK]: Learning vs. Learning to Recall

Multimodal Pre-Training Model for Sequence-based Prediction of Protein-Protein Interaction

Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training

Unsupervised Representation Learning via Neural Activation Coding

Label Hallucination for Few-Shot Classification

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning

NEZHA: Neural Contextualized Representation for Chinese Language Understanding

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

StrucTexT: Structured Text Understanding with Multi-Modal Transformers

Unsupervised Discovery of Unaccusative and Unergative Verbs

Contrastive Document Representation Learning with Graph Attention Networks

Solving Aspect Category Sentiment Analysis as a Text Generation Task

RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model

ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality

Conditional independence for pretext task selection in Self-supervised speech representation learning

Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition

Exploring Multitask Learning for Low-Resource AbstractiveSummarization

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding