每日论文速递：自然语言处理相关（11月5日更新版）-技术圈

出品 | 深度学习这件小事公众号

如需转载，请联系后台授权

自然语言处理（11月5日更新版）

[1] Reducing the impact of out of vocabulary words in the translation of natural language questions into SPARQL queries

作者 | Manuel A. Borroto Santana, Francesco Ricca, Bernardo Cuteri

链接 | https://arxiv.org/abs/2111.03000

备注 | 17 pages, 2 figures. This work constitutes a draft pending submission to a journal

[2] Unsupervised and Distributional Detection of Machine-Generated Text

作者 | Matthias Gallé, Jos Rozen, Germán Kruszewski, Hady Elsahar

链接 | https://arxiv.org/abs/2111.02878

备注 | 10 pages

[3] A text autoencoder from transformer for fast encoding language representation

作者 | Tan Huang

链接 | https://arxiv.org/abs/2111.02844

备注 | 8 pages, 8 figures. arXiv admin note: text overlap with arXiv:2004.08097 by other authors

[4] Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

作者 | Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, Bo Li

链接 | https://arxiv.org/abs/2111.02840

备注 | Oral Presentation in NeurIPS 2021 (Datasets and Benchmarks Track). 24 pages, 4 figures, 12 tables

[5] Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

作者 | Kevin Eloff, Arnu Pretorius, Okko Räsänen, Herman A. Engelbrecht, Herman Kamper

链接 | https://arxiv.org/abs/2111.02827

备注 | 12 pages, 6 figures, 3 tables; under review as a conference paper at ICLR 2022

[6] Medicines Question Answering System, MeQA

作者 | Jesús Santamaría

链接 | https://arxiv.org/abs/2111.02760

[7] A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding

作者 | Yingzhi Wang, Abdelmoumene Boumadane, Abdelwahab Heba

链接 | https://arxiv.org/abs/2111.02735

备注 | 5 pages, 2 figures

[8] CoreLM: Coreference-aware Language Model Fine-Tuning

作者 | Nikolaos Stylianou, Ioannis Vlahavas

链接 | https://arxiv.org/abs/2111.02687

备注 | 12 pages, 2 figures, Accepted at Fourth Workshop on Computational Models of Reference, Anaphora and Coreference

[9] Response Generation with Context-Aware Prompt Learning

作者 | Xiaodong Gu, Kang Min Yoo, Sang-Woo Lee

链接 | https://arxiv.org/abs/2111.02643

[10] Lexically Aware Semi-Supervised Learning for OCR Post-Correction

作者 | Shruti Rijhwani, Daisy Rosenblum, Antonios Anastasopoulos, Graham Neubig

链接 | https://arxiv.org/abs/2111.02622

备注 | Accepted to the Transactions of the Association for Computational Linguistics (TACL)

[11] On Semantic Cognition, Inductive Generalization, and Language Models

作者 | Kanishka Misra

链接 | https://arxiv.org/abs/2111.02603

备注 | Accepted at AAAI 2022 Doctoral Consortium

[12] Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues

作者 | Mehrad Moradshahi, Victoria Tsai, Giovanni Campagna, Monica S. Lam

链接 | https://arxiv.org/abs/2111.02574

备注 | 12 pages, 2 figures

[13] CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

作者 | Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Christopher Meek, Ahmed Hassan Awadallah, Jianfeng Gao

链接 | https://arxiv.org/abs/2111.02570

备注 | NeurIPS 2021 Datasets and Benchmarks Track

[14] Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot

作者 | Juraj Juraska, Kevin K. Bowden, Lena Reed, Vrindavan Harrison, Wen Cui, Omkar Patil, Rishi Rajasekaran, Angela Ramirez, Cecilia Li, Eduardo Zamora, Phillip Lee, Jeshwanth Bheemanpally, Rohan Pandey, Adwait Ratnaparkhi, Marilyn Walker

链接 | https://arxiv.org/abs/2111.02519

备注 | Accepted to EMNLP 2021 System Demonstrations

[15] Benchmarking Multimodal AutoML for Tabular Data with Text Fields

作者 | Xingjian Shi, Jonas Mueller, Nick Erickson, Mu Li, Alexander J. Smola

链接 | https://arxiv.org/abs/2111.02705

备注 | Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks 2021

[16] Voice Conversion Can Improve ASR in Very Low-Resource Settings

作者 | Matthew Baas, Herman Kamper

链接 | https://arxiv.org/abs/2111.02674

备注 | 5 page, 4 tables, 2 figures. Submitted to ICASSP 2022

[17] Speech recognition for air traffic control via feature learning and end-to-end training

作者 | Peng Fan, Dongyue Guo, Yi Lin, Bo Yang, Jianwei Zhang

链接 | https://arxiv.org/abs/2111.02654

备注 | Submitted to IEEE ICASSP 2022

技术交流群邀请函


△长按添加小助手扫描二维码添加小助手微信（ID : HIT_NLP）
请备注：姓名-学校/公司-研究方向-城市（如：小事-浙大-对话系统-北京）即可申请加入深度学习/机器学习等技术交流群

—完—

为您推荐
每日论文速递：计算机视觉相关（11月4日版）
每日论文速递：自然语言处理相关（11月3日版）
每日论文速递：自然语言处理相关（11月2日版）
每日论文速递：自然语言处理相关（11月1日版）
每日论文速递：自然语言处理相关（10月29日版）