EMNLP - arXivDaily 期刊&会议

2109.06349 2021-09-15 cs.CL cs.LG

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip Yu

Comments Accepted by EMNLP 2021 main conference

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

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

Alex Jones, William Yang Wang, Kyle Mahowald

Comments 15 pages, 8 figures, EMNLP 2021

2109.06316 2021-09-15 cs.CL

Learning Constraints and Descriptive Segmentation for Subevent Detection

Haoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth

Comments EMNLP 2021

2109.06283 2021-09-15 cs.CL

Graph Algorithms for Multiparallel Word Alignment

Ayyoob Imani, Masoud Jalili Sabet, Lütfi Kerem Şenel, Philipp Dufter, François Yvon, Hinrich Schütze

Comments EMNLP 2021

2109.05897 2021-09-15 cs.CL cs.IR cs.LG

Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework

Abhilash Nandy, Soumya Sharma, Shubham Maddhashiya, Kapil Sachdeva, Pawan Goyal, Niloy Ganguly

Comments EMNLP Findings 2021, Long

2109.05704 2021-09-15 cs.CL cs.AI

Mitigating Language-Dependent Ethnic Bias in BERT

Jaimeen Ahn, Alice Oh

Comments 17 pages including references and appendix. To appear in EMNLP 2021 (camera-ready ver.)

2109.05244 2021-09-15 cs.CL cs.AI

Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model

Shaolei Zhang, Yang Feng

Comments Accepted at Findings of EMNLP 2021. 11 pages, 7 figures, 7 tables

2109.03754 2021-09-15 cs.CL cs.AI

Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories

David Wilmot, Frank Keller

Comments Accepted to the EMNLP 2021 Conference as a long-paper, 9 pages, 15 pages with appendices and references, 2 figures, 4 tables

2109.03402 2021-09-15 cs.CL

Mixup Decoding for Diverse Machine Translation

Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

Comments Findings of EMNLP 2021

2108.13934 2021-09-15 cs.CL cs.AI cs.IR

Robust Retrieval Augmented Generation for Zero-shot Slot Filling

Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Alfio Gliozzo

Comments Accepted at EMNLP 2021. arXiv admin note: substantial text overlap with arXiv:2104.08610

2104.08771 2021-09-15 cs.CL

Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation

Mozhdeh Gheini, Xiang Ren, Jonathan May

Comments Accepted to EMNLP 2021 Main Conference

2104.08455 2021-09-15 cs.CL

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding

Nouha Dziri, Andrea Madotto, Osmar Zaiane, Avishek Joey Bose

Comments EMNLP 2021 18 pages

2104.04515 2021-09-15 cs.CL

Connecting Attributions and QA Model Behavior on Realistic Counterfactuals

Xi Ye, Rohan Nair, Greg Durrett

Comments EMNLP 2021

2103.01378 2021-09-15 cs.CL cs.AI cs.LG

Contrastive Explanations for Model Interpretability

Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg

Comments Accepted to EMNLP 2021 as a long paper

2109.06157 2021-09-14 cs.CL

SituatedQA: Incorporating Extra-Linguistic Contexts into QA

Michael J. Q. Zhang, Eunsol Choi

Comments Accepted at EMNLP 2021

2109.06014 2021-09-14 cs.CL

When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection

Aditi Chaudhary, Kayo Yin, Antonios Anastasopoulos, Graham Neubig

Comments Accepted at EMNLP 2021

2109.05925 2021-09-14 cs.CL

Adversarial Examples for Evaluating Math Word Problem Solvers

Vivek Kumar, Rishabh Maheshwary, Vikram Pudi

Comments Accepted at EMNLP Findings 2021

2109.05817 2021-09-14 cs.CL

End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs

Armin Oliya, Amir Saffari, Priyanka Sen, Tom Ayoola

Comments Accepted at EMNLP 2021

2109.05815 2021-09-14 cs.CL

Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media

Shivam Raval, Hooman Sedghamiz, Enrico Santus, Tuka Alhanai, Mohammad Ghassemi, Emmanuele Chersoni

Comments Short paper, EMNLP 2021, Findings

2109.05808 2021-09-14 cs.CL

Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection

Priyanka Sen, Amir Saffari, Armin Oliya

Comments Accepted at EMNLP 2021

2109.05794 2021-09-14 cs.CL cs.AI cs.IR

Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions

Mohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin, Jeffrey Dalton, Mikhail Burtsev

Comments Accepted in EMNLP 2021

2109.05793 2021-09-14 cs.CL

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models

Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen

Comments Accepted by EMNLP 2021 (Main Conference)

2109.05772 2021-09-14 cs.CL

Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages

Antonis Maronikolakis, Philipp Dufter, Hinrich Schütze

Comments Accepted at EMNLP 2021 Findings

2109.05771 2021-09-14 cs.CL

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

Ananya B. Sai, Tanay Dixit, Dev Yashpal Sheth, Sreyas Mohan, Mitesh M. Khapra

Comments Accepted at EMNLP 2021. See https://iitmnlp.github.io/EvalEval/ for our templates and code

2109.05748 2021-09-14 cs.LG cs.CL

GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks

Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi

Comments In EMNLP 2021

2109.05716 2021-09-14 cs.CL

MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu

Comments Accepted by EMNLP 2021

2109.05687 2021-09-14 cs.CL cs.AI

Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning

Runxin Xu, Fuli Luo, Zhiyuan Zhang, Chuanqi Tan, Baobao Chang, Songfang Huang, Fei Huang

Comments Accepted as a long paper to EMNLP 2021 Main Conference

2109.05644 2021-09-14 cs.CL

SHAPE: Shifted Absolute Position Embedding for Transformers

Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui

Comments EMNLP 2021 (short paper, main conference)

2109.05620 2021-09-14 cs.CL

RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models

Bill Yuchen Lin, Wenyang Gao, Jun Yan, Ryan Moreno, Xiang Ren

Comments Accepted to EMNLP 2021 as a short paper. Project website: https://inklab.usc.edu/rockner/

2109.05487 2021-09-14 cs.CL

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang

Comments EMNLP 2021