ACL - arXivDaily 期刊&会议

2205.06644 2022-05-16 cs.CL

Controlling Translation Formality Using Pre-trained Multilingual Language Models

Elijah Rippeth, Sweta Agrawal, Marine Carpuat

Comments 9 pages, 2 figures, IWSLT22 camera-ready (system paper @ ACL-IWSLT Shared Task on Formality Control for Spoken Language Translation)

2205.06135 2022-05-13 cs.CL cs.LG

Fair NLP Models with Differentially Private Text Encoders

Gaurav Maheshwari, Pascal Denis, Mikaela Keller, Aurélien Bellet

Comments submitted to: ACL-ARR 2022 (February) - https://openreview.net/forum?id=BVgNSki6q1c

2205.06130 2022-05-13 cs.CL

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models

Kabir Ahuja, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury

Comments ACL 2022

2205.05990 2022-05-13 cs.CL

Controlling Formality in Low-Resource NMT with Domain Adaptation and Re-Ranking: SLT-CDT-UoS at IWSLT2022

Sebastian T. Vincent, Loïc Barrault, Carolina Scarton

Comments 8 pages, 10 figures, IWSLT22 camera-ready (system paper @ ACL-IWSLT Shared Task on Formality Control for Spoken Language Translation)

2205.05593 2022-05-12 cs.CL

Identifying Moments of Change from Longitudinal User Text

Adam Tsakalidis, Federico Nanni, Anthony Hills, Jenny Chim, Jiayu Song, Maria Liakata

Comments Preprint accepted for publication in ACL 2022

2205.05137 2022-05-12 cs.CL cs.LG

Sibylvariant Transformations for Robust Text Classification

Fabrice Harel-Canada, Muhammad Ali Gulzar, Nanyun Peng, Miryung Kim

Comments 9 pages, Findings of ACL 2022

2205.05124 2022-05-12 cs.CL cs.AI cs.LG

Extracting Latent Steering Vectors from Pretrained Language Models

Nishant Subramani, Nivedita Suresh, Matthew E. Peters

Comments Accepted to ACL2022 Findings; 16 pages (9 pages plus references and appendices); Code: https://github.com/nishantsubramani/steering_vectors; Some text overlap with arXiv:2008.09049

2205.05093 2022-05-12 cs.CL cs.AI

Richer Countries and Richer Representations

Kaitlyn Zhou, Kawin Ethayarajh, Dan Jurafsky

Comments Camera Ready for ACL 2022 (Findings)

2205.05092 2022-05-12 cs.CL cs.AI

Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words

Kaitlyn Zhou, Kawin Ethayarajh, Dallas Card, Dan Jurafsky

Comments Camera Ready for ACL 2022 (Main Conference)

2205.04651 2022-05-11 cs.CL

ParaCotta: Synthetic Multilingual Paraphrase Corpora from the Most Diverse Translation Sample Pair

Alham Fikri Aji, Tirana Noor Fatyanosa, Radityo Eko Prasojo, Philip Arthur, Suci Fitriany, Salma Qonitah, Nadhifa Zulfa, Tomi Santoso, Mahendra Data

Comments 10 pages, 3 figures, 6 tables. Accepted at PACLIC 2021. (ACL Anthology link: https://aclanthology.org/2021.paclic-1.56/)

2205.04605 2022-05-11 cs.LG cs.CL

Sentence-level Privacy for Document Embeddings

Casey Meehan, Khalil Mrini, Kamalika Chaudhuri

Comments Presented at ACL 2022 main conference

2205.03766 2022-05-11 cs.CL

Scheduled Multi-task Learning for Neural Chat Translation

Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou

Comments Accepted at ACL 2022 as a long paper of the main conference. Code and data: https://github.com/XL2248/SML

2110.08542 2022-05-11 cs.CL

Hey AI, Can You Solve Complex Tasks by Talking to Agents?

Tushar Khot, Kyle Richardson, Daniel Khashabi, Ashish Sabharwal

Comments Accepted to Findings of ACL 2022

2109.03264 2022-05-11 cs.CL cs.LG cs.SD eess.AS

Text-Free Prosody-Aware Generative Spoken Language Modeling

Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Morgane Rivière, Abdelrahman Mohamed, Emmanuel Dupoux, Wei-Ning Hsu

Comments ACL 2022

2101.00204 2022-05-11 cs.CL

BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla

Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Kazi Samin, Md Saiful Islam, Anindya Iqbal, M. Sohel Rahman, Rifat Shahriyar

Comments Findings of North American Chapter of the Association for Computational Linguistics, NAACL 2022 (camera-ready)

2205.04404 2022-05-10 cs.CL cs.AI cs.CV cs.MM cs.SI

TeamX@DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification

Rabindra Nath Nandi, Firoj Alam, Preslav Nakov

Comments Accepted at DravidianLangTech-ACL2022 (Colocated with ACL-2022). disinformation, misinformation, factuality, harmfulness, fake news, propaganda, multimodality, text, images, videos, network structure, temporality

2205.04402 2022-05-10 cs.CL cs.CV cs.MM cs.SI

Detecting the Role of an Entity in Harmful Memes: Techniques and Their Limitations

Rabindra Nath Nandi, Firoj Alam, Preslav Nakov

Comments Accepted at CONSTRAINT 2022 (Colocated with ACL-2022), disinformation, misinformation, factuality, harmfulness, fake news, propaganda, multimodality, text, images, videos, network structure, temporality

2205.04120 2022-05-10 cs.SD cs.CL eess.AS

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang

Comments ACL 2022 camera ready

2205.04093 2022-05-10 cs.CL

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer

Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann, Soujanya Poria

Comments Accepted to ACL 2022

2205.04067 2022-05-10 cs.CL

Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

Minhan Xu, Yu Hong

Comments Accepted at ACL 2022

2203.04651 2022-05-10 cs.CL

Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang

Daphna Keidar, Andreas Opedal, Zhijing Jin, Mrinmaya Sachan

Comments Accepted as a main conference paper at ACL 2022. Fixed typos and added references

2109.07958 2022-05-10 cs.CL cs.AI cs.CY cs.LG

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Stephanie Lin, Jacob Hilton, Owain Evans

Comments ACL 2022 (main conference); the TruthfulQA benchmark and evaluation code is available at https://github.com/sylinrl/TruthfulQA

2110.07415 2022-05-09 cs.CL

PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction

Vipul Rathore, Kartikeya Badola, Mausam, Parag Singla

Comments Accepted to ACL (main) 2022 as a short paper

2108.05921 2022-05-09 cs.CL cs.CY

Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate

Hannah Rose Kirk, Bertram Vidgen, Paul Röttger, Tristan Thrush, Scott A. Hale

Journal ref 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)

2205.02460 2022-05-06 cs.LG

KGTuner: Efficient Hyper-parameter Search for Knowledge Graph Learning

Yongqi Zhang, Zhanke Zhou, Quanming Yao, Yong Li

Comments Accepted to ACL 2022 (long paper)

2110.07518 2022-05-06 cs.CL cs.AI

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

Megan Ung, Jing Xu, Y-Lan Boureau

Comments Accepted at ACL 2022

2108.00573 2022-05-06 cs.CL cs.AI

MuSiQue: Multihop Questions via Single-hop Question Composition

Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

Comments Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2022

2205.02014 2022-05-05 cs.CL cs.AI cs.LG

On Continual Model Refinement in Out-of-Distribution Data Streams

Bill Yuchen Lin, Sida Wang, Xi Victoria Lin, Robin Jia, Lin Xiao, Xiang Ren, Wen-tau Yih

Comments Accepted to ACL 2022; Project website: https://cmr-nlp.github.io/

2205.01941 2022-05-05 cs.CL

Lexical Knowledge Internalization for Neural Dialog Generation

Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao

Comments To appear at ACL 2022 main conference

2205.01883 2022-05-05 cs.CV cs.CL

All You May Need for VQA are Image Captions

Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

Comments 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)