语言大模型 / LLM - arXivDaily 专题

2110.15723 2021-11-01 cs.CL cs.AI cs.LG 67%

SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation

Tuan Nguyen, Hanh Pham, Truong Bui, Tan Nguyen, Duc Luong, Phong Nguyen

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

2109.15159 2021-10-01 cs.CL cs.AI cs.LG 67%

Focused Contrastive Training for Test-based Constituency Analysis

Benjamin Roth, Erion Çano

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

Comments 4 tables, 19 references

2109.06324 2021-09-15 cs.CL cs.AI cs.LG 67%

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space

Alex Jones, William Yang Wang, Kyle Mahowald

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

Comments 15 pages, 8 figures, EMNLP 2021

2109.04319 2021-09-10 cs.CL cs.AI cs.LG 67%

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

Massimo Nicosia, Zhongdi Qu, Yasemin Altun

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

Comments Accepted to EMNLP 2021 (Findings)

2103.08001 2021-07-21 cs.LG cs.AI cs.CL 67%

Claim Verification using a Multi-GAN based Model

Amartya Hatua, Arjun Mukherjee, Rakesh M. Verma

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

Comments Paper is submitted at LDK 2021 3rd Conference on Language, Data and Knowledge

2107.06383 2021-07-15 cs.CV cs.AI cs.CL cs.LG 67%

How Much Can CLIP Benefit Vision-and-Language Tasks?

Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer

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

Comments 14 pages

2106.11740 2021-06-28 cs.CL cs.AI cs.LG 67%

LV-BERT: Exploiting Layer Variety for BERT

Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng

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

Comments Accepted to Findings of ACL 2021. The code and pre-trained models are available at https://github.com/yuweihao/LV-BERT

2106.11097 2021-06-22 cs.CV 67%

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

Han Fang, Pengfei Xiong, Luhui Xu, Yu Chen

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

2105.00059 2021-05-04 cs.CL cs.AI cs.LG 67%

An analysis of full-size Russian complexly NER labelled corpus of Internet user reviews on the drugs based on deep learning and language neural nets

Alexander Sboev, Sanna Sboeva, Ivan Moloshnikov, Artem Gryaznov, Roman Rybka, Alexander Naumov, Anton Selivanov, Gleb Rylkov, Viacheslav Ilyin

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

2005.05298 2021-04-12 cs.CL cs.AI cs.LG 67%

SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching

Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Jianfeng Gao

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

Comments 18 pages; To appear at TACL; Project Website: https://aka.ms/soloist

2102.07662 2021-02-16 cs.IR cs.AI cs.CL cs.LG 67%

Overview of the TREC 2020 deep learning track

Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos

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

Comments arXiv admin note: substantial text overlap with arXiv:2003.07820

2102.02201 2021-02-12 cs.CL cs.AI cs.LG 67%

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data

Peter Hase, Mohit Bansal

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

Comments 25 pages, 20 figures

2101.10524 2021-01-29 cs.CL cs.AI cs.LG 67%

El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta

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

Journal ref EACL 2021

1910.07117 2021-01-19 cs.CL cs.AI cs.LG 67%

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng

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

Journal ref EACL 2021

2012.07652 2020-12-15 cs.CL cs.AI cs.LG 67%

Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance

Aditya Pal, Abhijit Mustafi

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

Comments 5 pages, 3 figures

2012.01687 2020-12-04 cs.CL cs.AI cs.LG 67%

Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition

Genta Indra Winata, Guangsen Wang, Caiming Xiong, Steven Hoi

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

2010.02693 2020-11-03 cs.CL cs.AI cs.LG 67%

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling

Di Wu, Liang Ding, Fan Lu, Jian Xie

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

Comments To appear in the the main conference of EMNLP 2020

2010.13641 2020-10-27 cs.CL cs.AI cs.LG 67%

Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

Timo Schick, Helmut Schmid, Hinrich Schütze

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

Comments To appear at COLING 2020

2005.00558 2020-09-29 cs.CL cs.AI cs.LG 67%

POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training

Yizhe Zhang, Guoyin Wang, Chunyuan Li, Zhe Gan, Chris Brockett, Bill Dolan

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

Comments EMNLP 2020 long paper

2009.11278 2020-09-24 cs.CV cs.AI cs.CL cs.LG 67%

X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

Jaemin Cho, Jiasen Lu, Dustin Schwenk, Hannaneh Hajishirzi, Aniruddha Kembhavi

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

Comments EMNLP 2020

2008.01392 2020-08-05 cs.CV 67%

Learning Visual Representations with Caption Annotations

Mert Bulent Sariyildiz, Julien Perez, Diane Larlus

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments Accepted to the 2020 European Conference on Computer Vision

2004.03561 2020-06-01 cs.CL cs.AI cs.LG 67%

Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering

Changmao Li, Jinho D. Choi

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

Comments Accepted by the Annual Conference of the Association for Computational Linguistics, ACL 2020

2005.01278 2020-05-05 cs.CL cs.AI cs.LG 67%

A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect

Zhiqiang Zhan, Zifeng Hou, Yang Zhang

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

2004.14973 2020-05-04 cs.CV cs.AI cs.CL cs.LG 67%

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web

Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh, Dhruv Batra

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

2004.04959 2020-04-13 cs.MM cs.IR 67%

Stacked Convolutional Deep Encoding Network for Video-Text Retrieval

Rui Zhao, Kecheng Zheng, Zheng-jun Zha

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments 6 pages

2002.02511 2020-02-10 cs.CL cs.AI cs.LG 67%

Introducing Aspects of Creativity in Automatic Poetry Generation

Brendan Bena, Jugal Kalita

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

Comments 10 pages, 10 figures, 4 tables, ICON-2019

2002.00744 2020-02-04 cs.CL cs.AI cs.LG 67%

PEL-BERT: A Joint Model for Protocol Entity Linking

Shoubin Li, Wenzao Cui, Yujiang Liu, Xuran Ming, Jun Hu, YuanzheHu, Qing Wang

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

1908.06066 2019-12-04 cs.CV 67%

Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training

Gen Li, Nan Duan, Yuejian Fang, Ming Gong, Daxin Jiang, Ming Zhou

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments accepted by AAAI-2020. arXiv admin note: text overlap with arXiv:1909.11740 by other authors

1909.00505 2019-09-15 cs.CL cs.AI cs.LG 67%

Commonsense Knowledge Mining from Pretrained Models

Joshua Feldman, Joe Davison, Alexander M. Rush

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

1809.06709 2019-01-16 cs.CL cs.AI cs.IR cs.LG 67%

Document Informed Neural Autoregressive Topic Models with Distributional Prior

Pankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze

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

Comments AAAI2019. arXiv admin note: substantial text overlap with arXiv:1808.03793

1. 预训练与数据 12486 篇

SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation

Focused Contrastive Training for Test-based Constituency Analysis

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

Claim Verification using a Multi-GAN based Model

How Much Can CLIP Benefit Vision-and-Language Tasks?

LV-BERT: Exploiting Layer Variety for BERT

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

An analysis of full-size Russian complexly NER labelled corpus of Internet user reviews on the drugs based on deep learning and language neural nets

SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching

Overview of the TREC 2020 deep learning track

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data

El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance

Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling

Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training

X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

Learning Visual Representations with Caption Annotations

Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering

A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web

Stacked Convolutional Deep Encoding Network for Video-Text Retrieval

Introducing Aspects of Creativity in Automatic Poetry Generation

PEL-BERT: A Joint Model for Protocol Entity Linking

Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training

Commonsense Knowledge Mining from Pretrained Models

Document Informed Neural Autoregressive Topic Models with Distributional Prior