[ad_1]
Between the principle convention and the not too long ago inaugurated ACL Proceedings, Amazon researchers have greater than 65 papers at this 12 months’s assembly of the Affiliation for Computational Linguistics (ACL).
Computerized speech recognition
Masked audio textual content encoders are efficient multi-modal rescorers*
Jason Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati
Code technology
A static analysis of code completion by giant language fashions
Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng LI, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, Bing Xiang
Multitask pretraining with structured information for text-to-SQL technology
Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma
Code switching
Code-switched textual content synthesis in unseen language pairs*
I-Hung Hsu, Avik Ray, Shubham Garg, Nanyun Peng, Jing Huang
CoMix: Information transformers to code-mix utilizing POS construction and phonetics*
Gaurav Arora, Srujana Merugu, Vivek Sembium
Continuous studying
Characterizing and measuring linguistic dataset drift
Tyler A. Chang, Kishaloy Halder, Neha Anna John, Yogarshi Vyas, Yassine Benajiba, Miguel Ballesteros, Dan Roth
Knowledge-/table-to-text functions
An inside desk retriever for sturdy desk query answering
Weizhe Lin, Rexhina Blloshmi, Invoice Byrne, Adrià de Gispert, Gonzalo Iglesias
Few-shot data-to-text technology by way of unified illustration and multi-source studying
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, JIE MA, Patrick Ng, Zhiguo Wang, Bonan Min, William Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang
Enhancing cross-task generalization of unified table-to-text fashions with compositional job configurations*
Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Wang, Zhiheng Huang
LI-RAGE: Late interplay retrieval augmented technology with express indicators for open-domain desk query answering
Weizhe Lin, Rexhina Blloshmi, Invoice Byrne, Adrià de Gispert, Gonzalo Iglesias
Dialogue
Diable: Environment friendly dialogue state monitoring as operations on tables*
Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Lluis Marquez
NatCS: Eliciting pure buyer assist dialogues
James Gung, Emily Moeng, Wesley Rose, Arshit Gupta, Yi Zhang, Saab Mansour
Schema-guided consumer satisfaction modeling for task-oriented dialogues
Yue Feng, Yunlong Jiao, Animesh Prasad, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai
Towards extra correct and generalizable analysis metrics for task-oriented dialogs
Abi Komma, Nagesh Panyam, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas, Aram Galstyan
Explainable AI
Environment friendly Shapley values estimation by amortization for textual content classification
Alan Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang
Few shot rationale technology utilizing self-training with twin lecturers*
Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, Gyuri Szarvas, Sharanya Eswaran
Data extraction
An AMR-based hyperlink prediction method for document-level occasion argument extraction
Yuqing Yang, Qipeng Guo, Xiangkun Hu, Yue Zhang, Qipeng Guo, Zheng Zhang
AVEN-GR: Attribute worth extraction and normalization utilizing product graphs
Donato Crisostomi, Thomas Ricatte
Massive scale generative multimodal attribute extraction for e-commerce attributes
Anant Khandelwal, Completely satisfied Mittal, Shreyas Sunil Kulkarni, Deepak Gupta
ParaAMR: A big-scale syntactically various paraphrase dataset by AMR back-translation
Kuan-Hao Huang, Varun Iyer, I-Hung Hsu, Anoop Kumar, Kai-Wei Chang, Aram Galstyan
Weakly supervised hierarchical multi-task classification of buyer questions
Jitenkumar Rana, Promod Yenigalla, Chetan Aggarwal, Sandeep Mukku, Manan Soni, Rashmi Patange
WebIE: Trustworthy and sturdy info extraction on the internet
Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni
Data retrieval
CUPID: Curriculum studying primarily based real-time prediction utilizing distillation
Arindam Bhattacharya, Ankith M S, Ankit Gandhi, Vijay Huddar, Atul Saroop, Rahul Bhagat
Direct reality retrieval from information graphs with out entity linking
Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang
Language modeling
Adaptation approaches for nearest neighbor language fashions*
Rishabh Bhardwaj, George Polovets, Monica Sunkara
CONTRACLM: Contrastive studying for causal language mannequin
Nihal Jain, Dejiao Zhang, Wasi Ahmad, Zijian Wang, Feng Nan, Xiaopeng LI, Ming Tan, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
Managed textual content technology with hidden illustration transformations*
Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, Emilio Ferrara
KILM: Information injection into encoder-decoder language fashions
Yan XU, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür
ReAugKD: Retrieval-augmented information distillation for pre-trained language fashions
Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen
Recipes for sequential pre-training of multilingual encoder and seq2seq fashions*
Saleh Soltan, Andy Rosenbaum, Tobias Falke, Qin Lu, Anna Rumshisky, Wael Hamza
Rethinking the function of scale for in-context studying: An interpretability-based case examine at 66 billion scale
Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal, Sravan Bodapati, Katrin Kirchhoff, Dan Roth
Machine studying
Mitigating the burden of redundant datasets by way of batch-wise distinctive samples and frequency-aware losses
Donato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Alessandro Manzotti, Enrico Palumbo, Kay Rottmann, Davide Bernardi
Machine translation
RAMP: Retrieval and attribute-marking enhanced prompting for attribute-controlled translation
Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nădejde
Multimodal fashions
Benchmarking diverse-modal entity linking with generative fashions*
Sijia Wang, Alexander Li, Henry Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Grasp, JIE MA, William Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng
Generate then choose: Open-ended visible query answering guided by world information*
Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henry Zhu, Yuhao Zhang, Alexander Hanbo Li, William Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang
KG-FLIP: Information-guided fashion-domain language-image pre-training for e-commerce
Qinjin Jia, Yang Liu, Shaoyuan Xu, Huidong Liu, Daoping Wu, Jinmiao Fu, Roland Vollgraf, Bryan Wang
Resolving ambiguities in text-to-image generative fashions
Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta
Translation-enhanced multilingual text-to-image technology
Yaoyiran Li, Ching-Yun (Frannie) Chang, Stephen Rawls, Ivan Vulić, Anna Korhonen
Unsupervised melody-to-lyric technology
Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Chenyang Tao, Gunnar Sigurdsson, Wenbo Zhao, Tagyoung Chung, Jing Huang, Violet Peng
Pure-language processing
Multi-VALUE: A framework for cross-dialectal English NLP
Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang
vONTSS: vMF primarily based semi-supervised neural matter modeling with optimum transport*
Weijie Xu, Xiaoyu Jiang, Srinivasan Sengamedu, “SHS”, Francis Iannacci, Jinjin Zhao
Pure-language understanding
ECG-QALM: Entity-controlled artificial textual content technology utilizing contextual Q&A for NER*
Karan Aggarwal, Henry Jin, Aitzaz Ahmad
Entity contrastive studying in a large-scale digital assistant system
Jonathan Rubin, Jason Crowley, George Leung, Morteza Ziyadi, Maria Minakova
EPIC: Multi-perspective annotation of a corpus of irony
Simona Frenda, Alessandro Pedrani, Valerio Basile, Soda Marem Lo, Alessandra Teresa Cignarella, Raffaella Panizzon, Cristina Marco, Bianca Scarlini, Viviana Patti, Cristina Bosco, Davide Bernardi
Measuring and mitigating native instability in deep neural networks*
Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan
Lowering cohort bias in pure language understanding programs with focused self-training scheme
Thu Le, Gabriela Cortes Hernandez, Bei Chen, Melanie Bradford
Privateness
Controlling the extraction of memorized knowledge from giant language fashions by way of prompt-tuning
Mustafa Ozdayi, Charith Peris, Jack G. M. FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta
Question rewriting
Context-aware question rewriting for bettering customers’ search expertise on e-commerce web sites
Simiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao
Unified contextual question rewriting
Yingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Vasudevan, Kellen Gillespie, Zeynab Raeesy, Sawyer Shen, Edward Guo, Gokhan Tur
Query answering
Correct coaching of web-based query answering programs with suggestions from ranked customers
Liang Wang, Ivano Lauriola, Alessandro Moschitti
Context-aware transformer pre-training for reply sentence choice
Luca Di Liello, Siddhant Garg, Alessandro Moschitti
Cross-Lingual Information Distillation for reply sentence choice in low-resource languages*
Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti
Exploiting summary that means illustration for open-domain query answering*
Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, Yue Zhang
Hybrid hierarchical retrieval for open-domain query answering*
Manoj Ghuhan Arivazhagan, Lan Liu, Peng Qi, Xinchi Chen, William Wang, Zhiheng Huang
Studying reply technology utilizing supervision from computerized query answering evaluators
Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti
RobustQA: Benchmarking the robustness of area adaptation for open-domain query answering*
Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Wang, Zhiheng Huang, Bing Xiang, Dan Roth
Reasoning
FolkScope: Intention information graph development for e-commerce commonsense discovery*
Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Tune, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin
SCOTT: Self-consistent chain-of-thought distillation
Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren
Self-learning
Constrained coverage optimization for managed self-learning in conversational AI programs
Mohammad Kachuee, Sungjin Lee
Scalable and protected remediation of faulty actions in self-learning conversational programs
Sarthak Ahuja, Mohammad Kachuee, Fateme Sheikholeslami, Weiqing Liu, Jae Do
Semantic parsing
An empirical evaluation of leveraging information for low-resource task-oriented semantic parsing*
Mayank Kulkarni, Aoxiao Zhong, Nicolas Guenon Des Mesnards, Sahar Movaghati, Mukund Harakere, He Xie, Jianhua Lu
XSEMPLR: Cross-lingual semantic parsing in a number of pure languages and that means representations
Yusen Zhang, Jun Wang, Zhiguo Wang, Rui Zhang
Spoken-language understanding
Regression-free mannequin updates for spoken language understanding
Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi
Sharing encoder representations throughout languages, domains and duties in large-scale spoken language understanding
Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Satya Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev, Mariusz Momotko, Denis Romasanta Rodriguez, Austin Doolittle, Kartik Balasubramaniam, Wael Hamza, Fabian Triefenbach, Patrick Lehnen
Poisonous-language classification
QCon at SemEval-2023 Process 10: Knowledge augmentation and mannequin ensembling for detection of on-line sexism
Wes Feely, Prabhakar Gupta, Manas Mohanty, Tim Chon, Tuhin Kundu, Vijit Singh, Sandeep Atluri, Tanya Roosta, Viviane Ghaderi, Peter Schulam, Heba Elfardy
In direction of constructing a strong toxicity predictor
Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Yanjun (Jane) Qi
*Accepted to ACL Findings
[ad_2]
