EMNLP - arXivDaily 期刊&会议

2110.14694 2021-10-29 cs.CL cs.AI cs.LG

Towards Realistic Single-Task Continuous Learning Research for NER

Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta

Comments 11 pages, 2 figures, Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) (short paper), November 2021

2110.14091 2021-10-28 cs.CL cs.AI

Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories

Wenlin Yao, Xiaoman Pan, Lifeng Jin, Jianshu Chen, Dian Yu, Dong Yu

Comments 11 pages. Accepted to the main conference of EMNLP 2021 (long paper)

2110.13691 2021-10-27 cs.CL cs.AI

An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling

Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Xianchao Zhang

Comments 11 pages, 2 figures, Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) (long paper), November 2021

2110.13505 2021-10-27 cs.CL

Part & Whole Extraction: Towards A Deep Understanding of Quantitative Facts for Percentages in Text

Lei Fang, Jian-Guang Lou

Comments rejected by EMNLP 2020

2109.11888 2021-10-27 cs.CL

Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text

Jekaterina Novikova

Comments Accepted to W-NUT @ EMNLP 2021 (upd: correction in Table 3)

2110.12765 2021-10-26 cs.CL cs.AI

"So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy

Anirudh Mittal, Pranav Jeevan, Prerak Gandhi, Diptesh Kanojia, Pushpak Bhattacharyya

Comments Accepted at EMNLP 2021 Main Conference (short papers); 4 pages, 1 figure, 3 tables

2110.12383 2021-10-26 cs.CL

Automated Extraction of Sentencing Decisions from Court Cases in the Hebrew Language

Mohr Wenger, Tom Kalir, Noga Berger, Carmit Chalamish, Renana Keydar, Gabriel Stanovsky

Comments Accepted to the Natural Legal Language Processing workshop (NLLP 2021), colocated with EMNLP 2021

2110.12349 2021-10-26 cs.AI cs.CL

Think about it! Improving defeasible reasoning by first modeling the question scenario

Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Peter Clark, Yiming Yang, Eduard Hovy

Comments EMNLP 2021

2110.12199 2021-10-26 cs.CL

PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation

Long Doan, Linh The Nguyen, Nguyen Luong Tran, Thai Hoang, Dat Quoc Nguyen

Comments To appear in Proceedings of EMNLP 2021 (main conference). The first three authors contribute equally to this work

2110.11624 2021-10-26 cs.CL cs.AI cs.CV

SciCap: Generating Captions for Scientific Figures

Ting-Yao Hsu, C. Lee Giles, Ting-Hao 'Kenneth' Huang

Comments To Appear in EMNLP 2021 Findings. The dataset is available at: https://github.com/tingyaohsu/SciCap

2109.04513 2021-10-26 cs.CL

Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach

Koren Lazar, Benny Saret, Asaf Yehudai, Wayne Horowitz, Nathan Wasserman, Gabriel Stanovsky

Comments Accepted to EMNLP 2021 (Main Conference)

2103.14930 2021-10-26 cs.AI

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings

Kai Wang, Yu Liu, Dan Lin, Quan Z. Sheng

Comments Accepted for publication at the Findings of EMNLP 2021

2110.11934 2021-10-25 cs.CL

Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts

Allen Kim, Charuta Pethe, Naoya Inoue, Steve Skiena

Comments Accepted for Findings of EMNLP 2021

2110.11589 2021-10-25 cs.CL

Text Counterfactuals via Latent Optimization and Shapley-Guided Search

Quintin Pope, Xiaoli Z. Fern

Comments 9 pages, 2 figures, 3 tables. Accepted at EMNLP 2021

2109.13238 2021-10-25 cs.CL cs.AI cs.CV

Visually Grounded Reasoning across Languages and Cultures

Fangyu Liu, Emanuele Bugliarello, Edoardo Maria Ponti, Siva Reddy, Nigel Collier, Desmond Elliott

Comments EMNLP 2021; Fangyu and Emanuele contributed equally; MaRVL website: https://marvl-challenge.github.io

2101.01881 2021-10-25 cs.CV cs.LG

MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding

Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, Hamed Firooz

Comments Accepted to EMNLP 2021 Findings

2110.11207 2021-10-22 cs.CL cs.AI

Topic-Guided Abstractive Multi-Document Summarization

Peng Cui, Le Hu

Comments accepted at findings of EMNLP 2021

2110.10963 2021-10-22 cs.AI cs.CL cs.LG cs.RO

Neuro-Symbolic Reinforcement Learning with First-Order Logic

Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar, Alexander Gray

Comments EMNLP 2021 (main conference)

2110.10834 2021-10-22 cs.CL cs.AI cs.CV cs.LG

Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization

Adyasha Maharana, Mohit Bansal

Comments EMNLP 2021 (16 pages)

2110.10778 2021-10-22 cs.CL

Contrastive Document Representation Learning with Graph Attention Networks

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

Comments Findings of EMNLP 2021

2110.10668 2021-10-22 cs.CL

Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer

Eleftheria Briakou, Sweta Agrawal, Joel Tetreault, Marine Carpuat

Comments EMNLP 2021

2110.10472 2021-10-22 cs.CL

Multilingual Unsupervised Neural Machine Translation with Denoising Adapters

Ahmet Üstün, Alexandre Bérard, Laurent Besacier, Matthias Gallé

Comments Accepted as a long paper to EMNLP 2021

2110.10328 2021-10-22 cs.CL cs.CV

R$^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning

Yunbin Tu, Liang Li, Chenggang Yan, Shengxiang Gao, Zhengtao Yu

Comments Accepted by EMNLP 2021

2110.10319 2021-10-22 cs.CL cs.CY cs.IR cs.LG

LMSOC: An Approach for Socially Sensitive Pretraining

Vivek Kulkarni, Shubhanshu Mishra, Aria Haghighi

Comments Camera ready version. Accepted to EMNLP 2021 Findings. Code for reproducing the experiments can be found at: https://github.com/twitter-research/lmsoc

2110.06388 2021-10-22 cs.CL cs.AI cs.LG

HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization

Ye Liu, Jian-Guo Zhang, Yao Wan, Congying Xia, Lifang He, Philip S. Yu

Comments EMNLP 2021 (short paper)

2108.06130 2021-10-22 cs.CL cs.IR

Semantic Answer Similarity for Evaluating Question Answering Models

Julian Risch, Timo Möller, Julian Gutsch, Malte Pietsch

Comments Trained model: https://huggingface.co/deepset/gbert-large-sts

Journal ref MRQA@EMNLP 2021

2010.10216 2021-10-22 cs.CL cs.AI

Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions

Biswesh Mohapatra, Gaurav Pandey, Danish Contractor, Sachindra Joshi

Comments Accepted in the Findings of EMNLP 2021

2008.09150 2021-10-22 cs.CL cs.AI cs.CV

VisualSem: A High-quality Knowledge Graph for Vision and Language

Houda Alberts, Teresa Huang, Yash Deshpande, Yibo Liu, Kyunghyun Cho, Clara Vania, Iacer Calixto

Comments Accepted for publication at the 1st Multilingual Representation Learning workshop (MRL 2021) co-located with EMNLP 2021. 15 pages, 8 figures, 6 tables

2110.09915 2021-10-20 cs.CL cs.AI cs.LG

Entity Relation Extraction as Dependency Parsing in Visually Rich Documents

Yue Zhang, Bo Zhang, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao

Comments Accepted to EMNLP 2021 (main conference)

2110.09779 2021-10-20 cs.CL

Open-domain clarification question generation without question examples

Julia White, Gabriel Poesia, Robert Hawkins, Dorsa Sadigh, Noah Goodman

Comments EMNLP 2021