EMNLP - arXivDaily 期刊&会议

2109.06952 2021-09-16 cs.CL cs.SD eess.AS

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech

Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, Fadi Biadsy

Comments Accepted to EMNLP 2021

2109.06950 2021-09-16 cs.CL

Automatically Exposing Problems with Neural Dialog Models

Dian Yu, Kenji Sagae

Journal ref EMNLP 2021

2109.06939 2021-09-16 cs.CL cs.AI

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders

Han He, Jinho D. Choi

Comments Accepted to EMNLP 2021: The 2021 Conference on Empirical Methods in Natural Language Processing

2109.06912 2021-09-16 eess.AS cs.CL cs.SD

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

Changhan Wang, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Ann Lee, Peng-Jen Chen, Jiatao Gu, Juan Pino

Comments Accepted to EMNLP 2021 Demo

2109.06896 2021-09-16 cs.CL cs.AI

Decision-Focused Summarization

Chao-Chun Hsu, Chenhao Tan

Comments 16 pages, 10 figures, EMNLP 2021, code is available at https://github.com/ChicagoHAI/decsum

2109.05958 2021-09-16 cs.CL cs.AI

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations

Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar

Comments Accepted to BlackboxNLP Workshop at EMNLP 2021

2109.05602 2021-09-16 cs.CL

Good-Enough Example Extrapolation

Jason Wei

Comments Camera-ready for EMNLP 2021 main conference. V2 is corrected with SMOTE citation and model setup language is clarified

2108.12848 2021-09-16 cs.CL

Span Fine-tuning for Pre-trained Language Models

Rongzhou Bao, Zhuosheng Zhang, Hai Zhao

Comments Accepted by EMNLP 2021 Finding(early version)

2108.04990 2021-09-16 cs.CL

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi

Comments EMNLP-BlackboxNLP, 2021

2103.15429 2021-09-16 cs.LG cs.CL

Efficient Explanations from Empirical Explainers

Robert Schwarzenberg, Nils Feldhus, Sebastian Möller

Comments Accepted to the EMNLP 2021 Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)

2103.11070 2021-09-16 cs.CL

Attribute Alignment: Controlling Text Generation from Pre-trained Language Models

Dian Yu, Zhou Yu, Kenji Sagae

Journal ref EMNLP 2021 Findings

2102.12459 2021-09-16 cs.CL cs.LG

When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute

Tao Lei

Journal ref EMNLP 2021

2010.01678 2021-09-16 cs.CL cs.PL

Optimal Neural Program Synthesis from Multimodal Specifications

Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett

Comments Findings of EMNLP 2021

2109.06860 2021-09-15 cs.CL cs.AI cs.CV

Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning

Da Yin, Liunian Harold Li, Ziniu Hu, Nanyun Peng, Kai-Wei Chang

Comments EMNLP 2021. Code and data are available at https://github.com/WadeYin9712/GD-VCR

2109.06835 2021-09-15 cs.CL

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

Marzena Karpinska, Nader Akoury, Mohit Iyyer

Comments EMNLP 2021 (20 pages)

2109.06798 2021-09-15 cs.CL

Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction

Mahsa Yarmohammadi, Shijie Wu, Marc Marone, Haoran Xu, Seth Ebner, Guanghui Qin, Yunmo Chen, Jialiang Guo, Craig Harman, Kenton Murray, Aaron Steven White, Mark Dredze, Benjamin Van Durme

Comments EMNLP 2021

2109.06747 2021-09-15 cs.CL

Adaptive Information Seeking for Open-Domain Question Answering

Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng

Comments Accepted at EMNLP 2021

2109.06704 2021-09-15 cs.CL

KFCNet: Knowledge Filtering and Contrastive Learning Network for Generative Commonsense Reasoning

Haonan Li, Yeyun Gong, Jian Jiao, Ruofei Zhang, Timothy Baldwin, Nan Duan

Comments Accepted to EMNLP 2021 Findings

2109.06627 2021-09-15 cs.CV cs.CL cs.LG

Scalable Font Reconstruction with Dual Latent Manifolds

Nikita Srivatsan, Si Wu, Jonathan T. Barron, Taylor Berg-Kirkpatrick

Comments EMNLP 2021

2109.06605 2021-09-15 cs.CL

MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model

Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai, Desmond Elliott

Comments Findings of EMNLP 2021

2109.06598 2021-09-15 cs.CL cs.AI

Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP

Anna Rogers, Tim Baldwin, Kobi Leins

Comments Findings of EMNLP 2021

2109.06527 2021-09-15 cs.CL

Learning Bill Similarity with Annotated and Augmented Corpora of Bills

Jiseon Kim, Elden Griggs, In Song Kim, Alice Oh

Comments Accepted at EMNLP 2021(Long paper)

2109.06524 2021-09-15 cs.CL

Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks

Yao Qiu, Jinchao Zhang, Jie Zhou

Comments Accepted as a long paper at EMNLP 2021 (Main Conference)

2109.06508 2021-09-15 cs.CL

Tribrid: Stance Classification with Neural Inconsistency Detection

Song Yang, Jacopo Urbani

Comments Accepted at EMNLP 2021

2109.06481 2021-09-15 cs.CL cs.AI

AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate

Jongyoon Song, Sungwon Kim, Sungroh Yoon

Comments Accepted by EMNLP 2021

2109.06480 2021-09-15 cs.AI cs.CL

Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

Comments EMNLP 2021

2109.06437 2021-09-15 cs.CL

Uncovering Implicit Gender Bias in Narratives through Commonsense Inference

Tenghao Huang, Faeze Brahman, Vered Shwartz, Snigdha Chaturvedi

Comments Accepted at Findings of EMNLP 2021

2109.06415 2021-09-15 cs.CL cs.AI

Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Xuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li, Li Lin, Lijie Wen, Philip S. Yu

Comments In EMNLP 2021 as a long paper. Code and data available at https://github.com/THU-BPM/GradLRE

2109.06400 2021-09-15 cs.CV cs.CL

Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding

Daizong Liu, Xiaoye Qu, Pan Zhou

Comments Accepted as a long paper in the main conference of EMNLP 2021

2109.06398 2021-09-15 cs.CV cs.CL

Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos

Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou

Comments Accepted as a long paper in the main conference of EMNLP 2021