语言大模型 / LLM - arXivDaily 专题

2102.10601 2021-02-23 cs.CL cs.AI 62%

Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT

Muhammad Noor Fakhruzzaman, Sie Wildan Gunawan

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments 10 pages

2102.09928 2021-02-22 eess.AS cs.CL cs.LG cs.SD 62%

Do End-to-End Speech Recognition Models Care About Context?

Lasse Borgholt, Jakob Drachmann Havtorn, Željko Agić, Anders Søgaard, Lars Maaløe, Christian Igel

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Published in the proceedings of INTERSPEECH 2020, pp. 4352-4356

2101.06829 2021-02-22 cs.CL cs.AI 62%

Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models

Tianxing He, Bryan McCann, Caiming Xiong, Ehsan Hosseini-Asl

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Journal ref EACL 2021

2102.08036 2021-02-17 cs.CL cs.LG 62%

Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet

M. Onat Topal, Anil Bas, Imke van Heerden

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted as oral presentation to ICIDAAI 2021 - Short Paper

2102.00466 2021-02-02 cs.CL cs.AI 62%

Adversarial Contrastive Pre-training for Protein Sequences

Matthew B. A. McDermott, Brendan Yap, Harry Hsu, Di Jin, Peter Szolovits

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

2102.00290 2021-02-02 cs.CL cs.LG 62%

Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks

Maurício Gruppi, Sibel Adalı, Pin-Yu Chen

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Published at AAAI-2021

2003.02245 2021-02-02 cs.CL cs.LG 62%

Data Augmentation using Pre-trained Transformer Models

Varun Kumar, Ashutosh Choudhary, Eunah Cho

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments In Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems @ AACL 2020; Code: https://github.com/varinf/TransformersDataAugmentation

2002.10832 2020-12-17 cs.CL cs.CV cs.LG 62%

What BERT Sees: Cross-Modal Transfer for Visual Question Generation

Thomas Scialom, Patrick Bordes, Paul-Alexis Dray, Jacopo Staiano, Patrick Gallinari

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments INLG 2020

2010.07523 2020-12-15 cs.CL cs.AI 62%

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Zhengxuan Wu, Desmond C. Ong

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Journal ref AAAI 2021

2012.03864 2020-12-08 cs.CL cs.AI 62%

Evaluating Cross-Lingual Transfer Learning Approaches in Multilingual Conversational Agent Models

Lizhen Tan, Olga Golovneva

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments 7 pages, 3 figures, 3 Tables. Accepted to be presented at COLING 2020 conference: https://coling2020.org/pages/accepted_papers_industry_track

1909.00333 2020-12-07 cs.CL cs.LG stat.ML 62%

QuASE: Question-Answer Driven Sentence Encoding

Hangfeng He, Qiang Ning, Dan Roth

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

2009.11963 2020-12-03 cs.CL cs.AI 62%

Toward a Thermodynamics of Meaning

Jonathan Scott Enderle

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments To be published in the proceedings of CHR 2020: Workshop on Computational Humanities Research, November 18-20, 2020, Amsterdam, The Netherlands

Journal ref Proceedings of the Workshop on Computational Humanities Research CEUR Vol-2723 (2020) 191-201

2011.13565 2020-11-30 cs.CL cs.AI 62%

Joint Extraction of Entity and Relation with Information Redundancy Elimination

Yuanhao Shen, Jungang Han

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

2011.09448 2020-11-19 cs.CL cs.LG 62%

Palomino-Ochoa at SemEval-2020 Task 9: Robust System based on Transformer for Code-Mixed Sentiment Classification

Daniel Palomino, Jose Ochoa-Luna

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at SemEval-2020, COLING

2011.08543 2020-11-18 cs.LG cs.CL cs.CV 62%

Structural and Functional Decomposition for Personality Image Captioning in a Communication Game

Thu Nguyen, Duy Phung, Minh Hoai, Thien Huu Nguyen

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, EMNLP-Findings 2020

Journal ref EMNLP-Findings 2020

2007.16013 2020-11-11 cs.CL cs.LG stat.ML 62%

Neural Composition: Learning to Generate from Multiple Models

Denis Filimonov, Ravi Teja Gadde, Ariya Rastrow

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Self-Supervised Learning for Speech and Audio Processing Workshop @ NeurIPS 2020

2011.02415 2020-11-05 cs.LG cs.AI cs.SC 62%

A Neuro-Symbolic Method for Solving Differential and Functional Equations

Maysum Panju, Ali Ghodsi

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments 8 pages

2011.01136 2020-11-04 cs.CL cs.LG 62%

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

Ruizhe Li, Xiao Li, Guanyi Chen, Chenghua Lin

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted by COLING 2020, final camera ready version

2010.13816 2020-10-28 cs.CL cs.AI 62%

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction

Xinyao Ma, Maarten Sap, Hannah Rashkin, Yejin Choi

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2020

2001.11316 2020-10-26 cs.LG cs.CL stat.ML 62%

Adversarial Training for Aspect-Based Sentiment Analysis with BERT

Akbar Karimi, Leonardo Rossi, Andrea Prati

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

2010.08542 2020-10-19 cs.CL cs.CR cs.LG 62%

Mischief: A Simple Black-Box Attack Against Transformer Architectures

Adrian de Wynter

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Technical report

2009.13102 2020-10-19 cs.CL cs.LG 62%

Deep Transformers with Latent Depth

Xian Li, Asa Cooper Stickland, Yuqing Tang, Xiang Kong

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

2010.06973 2020-10-15 cs.CL cs.DB cs.LG 62%

Neural Databases

James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Submitted to PVLDB vol 14

2010.05994 2020-10-14 cs.CL cs.LG 62%

Improving Text Generation with Student-Forcing Optimal Transport

Guoyin Wang, Chunyuan Li, Jianqiao Li, Hao Fu, Yuh-Chen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments To appear at EMNLP 2020

2009.13165 2020-09-29 cs.LG cs.AI stat.ML 62%

Quantal synaptic dilution enhances sparse encoding and dropout regularisation in deep networks

Gardave S Bhumbra

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments 23 pages, 8 figures, including Appendix

2009.08257 2020-09-18 cs.CL cs.LG 62%

Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA

Ieva Staliūnaitė, Ignacio Iacobacci

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 8 pages + 2 pages references, 3 tables, 1 figure. Accepted as long paper in EMNLP2020 main conference

2009.06398 2020-09-15 cs.LG cs.AI cs.FL 62%

On Computability, Learnability and Extractability of Finite State Machines from Recurrent Neural Networks

Reda Marzouk

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments Master's thesis

2009.06358 2020-09-15 cs.CL cs.LG stat.ML 62%

Improving Language Generation with Sentence Coherence Objective

Ruixiao Sun, Jie Yang, Mehrdad Yousefzadeh

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 11 pages, 9 figures

2009.04016 2020-09-10 cs.IR cs.CL cs.LG 62%

Brown University at TREC Deep Learning 2019

George Zerveas, Ruochen Zhang, Leila Kim, Carsten Eickhoff

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Journal ref Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC 2019, Gaithersburg, Maryland, USA, November 13-15, 2019. NIST Special Publication 1250, National Institute of Standards and Technology (NIST) 2019

2007.13928 2020-07-29 cs.CV cs.CL cs.LG 62%

Variants of BERT, Random Forests and SVM approach for Multimodal Emotion-Target Sub-challenge

Hoang Manh Hung, Hyung-Jeong Yang, Soo-Hyung Kim, Guee-Sang Lee

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 3 pages, 2 figures

1. 其他LLM 12321 篇

Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT

Do End-to-End Speech Recognition Models Care About Context?

Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models

Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet

Adversarial Contrastive Pre-training for Protein Sequences

Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks

Data Augmentation using Pre-trained Transformer Models

What BERT Sees: Cross-Modal Transfer for Visual Question Generation

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Evaluating Cross-Lingual Transfer Learning Approaches in Multilingual Conversational Agent Models

QuASE: Question-Answer Driven Sentence Encoding

Toward a Thermodynamics of Meaning

Joint Extraction of Entity and Relation with Information Redundancy Elimination

Palomino-Ochoa at SemEval-2020 Task 9: Robust System based on Transformer for Code-Mixed Sentiment Classification

Structural and Functional Decomposition for Personality Image Captioning in a Communication Game

Neural Composition: Learning to Generate from Multiple Models

A Neuro-Symbolic Method for Solving Differential and Functional Equations

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction

Adversarial Training for Aspect-Based Sentiment Analysis with BERT

Mischief: A Simple Black-Box Attack Against Transformer Architectures

Deep Transformers with Latent Depth

Neural Databases

Improving Text Generation with Student-Forcing Optimal Transport

Quantal synaptic dilution enhances sparse encoding and dropout regularisation in deep networks

Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA

On Computability, Learnability and Extractability of Finite State Machines from Recurrent Neural Networks

Improving Language Generation with Sentence Coherence Objective

Brown University at TREC Deep Learning 2019

Variants of BERT, Random Forests and SVM approach for Multimodal Emotion-Target Sub-challenge