Table of Contents

• Unsupervised Term Extraction for Highly Technical DomainsFrancesco Fusco, Peter W. J. Staar, Diego Antognini. 1-8 [doi]
• DynaMaR: Dynamic Prompt with Mask Token RepresentationXiaodi Sun, Sunny Rajagopalan, Priyanka Nigam, Weiyi Lu, Yi Xu, Iman Keivanloo, Belinda Zeng, Trishul Chilimbi. 9-17 [doi]
• A Hybrid Approach to Cross-lingual Product Review SummarizationSaleh Soltan, Victor Soto, Ke Tran, Wael Hamza. 18-28 [doi]
• Augmenting Operations Research with Auto-Formulation of Optimization Models From Problem DescriptionsRindra Ramamonjison, Haley Li, Timothy T. Yu, Shiqi He, Vishnu Rengan, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang 0004. 29-62 [doi]
• Knowledge Distillation based Contextual Relevance Matching for E-commerce Product SearchZiyang Liu, Chaokun Wang, Hao Feng, Lingfei Wu, Liqun Yang. 63-76 [doi]
• Accelerating the Discovery of Semantic Associations from Medical Literature: Mining Relations Between Diseases and SymptomsAlberto Purpura, Francesca Bonin, Joao H. Bettencourt-Silva. 77-89 [doi]
• PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstandingUma-Naresh Niranjan, Ziyan Jiang, Ankit Ankit, Sungjin Lee, Jie Hao, Xing Fan, Chenlei Guo. 90-98 [doi]
• Machine translation impact in E-commerce multilingual searchBryan Zhang, Amita Misra. 99-109 [doi]
• Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value ExtractionYifan Ding, Yan Liang 0004, Nasser Zalmout, Xian Li, Christan Grant, Tim Weninger. 110 [doi]
• Consultation Checklists: Standardising the Human Evaluation of Medical Note GenerationAleksandar Savkov, Francesco Moramarco, Alex Papadopoulos-Korfiatis, Mark Perera, Anya Belz, Ehud Reiter. 111-120 [doi]
• Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?Quynh Do, Judith Gaspers, Daniil Sorokin, Patrick Lehnen. 121-127 [doi]
• Knowledge Distillation Transfer Sets and their Impact on Downstream NLU TasksCharith Peris, Lizhen Tan, Thomas Gueudré, Turan Gojayev, Pan Wei, Gokmen Oz. 128-137 [doi]
• Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in NLU of Intra-Sentential Code-Switching Chatbot InteractionsMaia Aguirre, Manex Serras, Laura García-Sardiña, Jacobo Lopez-Fernandez, Ariane Méndez, Arantza del Pozo. 138-144 [doi]
• Calibrating Imbalanced Classifiers with Focal Loss: An Empirical StudyCheng Wang 0002, Jorge Balazs, György Szarvas, Patrick Ernst, Lahari Poddar, Pavel Danchenko. 145-153 [doi]
• Unsupervised training data re-weighting for natural language understanding with local distribution approximationJose Garrido Ramas, Dieu-Thu Le, Bei Chen, Manoj Kumar, Kay Rottmann. 154-160 [doi]
• Cross-Encoder Data Annotation for Bi-Encoder Based Product MatchingJustin Chiu, Keiji Shinzato. 161-168 [doi]
• Deploying a Retrieval based Response Model for Task Oriented DialoguesLahari Poddar, György Szarvas, Cheng Wang 0002, Jorge Balazs, Pavel Danchenko, Patrick Ernst. 169-178 [doi]
• Tackling Temporal Questions in Natural Language Interface to DatabasesNgoc Phuoc An Vo, Octavian Popescu, Irene Manotas, Vadim Sheinin. 179-187 [doi]
• Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ RetrievalAsha Vishwanathan, Rajeev Unnikrishnan Warrier, Gautham Vadakkekara Suresh, Chandra Shekhar Kandpal. 188-197 [doi]
• Iterative Stratified Testing and Measurement for Automated Model UpdatesElizabeth Dekeyser, Nicholas Comment, Shermin Pei, Rajat Kumar, Shruti Rai, Fengtao Wu, Lisa A. Haverty, Kanna Shimizu. 198-205 [doi]
• SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked ContentApurva Gandhi, Ryan Serrao, Biyi Fang, Gilbert Antonius, Jenna Hong, Tra My Nguyen, Sheng Yi, Ehi Nosakhare, Irene Shaffer, Soundararajan Srinivasan. 206-217 [doi]
• Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog SystemsElla Rabinovich, Matan Vetzler, David Boaz, Vineet Kumar, Gaurav Pandey 0001, Ateret Anaby-Tavor. 218-225 [doi]
• CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent DiscoveryQian Cao, Deyi Xiong, Qinlong Wang, Xia Peng. 226-236 [doi]
• Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear ProgrammingLitton J. Kurisinkel, Nancy Chen. 237-243 [doi]
• Grafting Pre-trained Models for Multimodal Headline GenerationLingfeng Qiao, Chen Wu, Ye Liu, Haoyuan Peng, Di Yin, Bo Ren 0002. 244-253 [doi]
• Semi-supervised Adversarial Text Generation based on Seq2Seq modelsHieu Le, Dieu-Thu Le, Verena Weber, Chris Church, Kay Rottmann, Melanie Bradford, Peter Chin 0001. 254-262 [doi]
• Is it out yet? Automatic Future Product Releases Extraction from Web DataGilad Fuchs, Ido Ben-Shaul, Matan Mandelbrod. 263-271 [doi]
• Automatic Scene-based Topic Channel Construction System for E-CommercePeng Lin, Yanyan Zou, Lingfei Wu, Mian Ma, Zhuoye Ding, Bo Long. 272-284 [doi]
• SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial ScaleRaphael Tang, Karun Kumar, Gefei Yang, Akshat Pandey, Yajie Mao, Vladislav Belyaev, Madhuri Emmadi, G. Craig Murray, Ferhan Ture, Jimmy Lin. 285-293 [doi]
• Controlled Language Generation for Language Learning ItemsKevin Stowe, Debanjan Ghosh, Mengxuan Zhao. 294-305 [doi]
• Improving Text-to-SQL Semantic Parsing with Fine-grained Query UnderstandingJun Wang, Patrick Ng, Alexander Hanbo Li, Jiarong Jiang, Zhiguo Wang, Bing Xiang, Ramesh Nallapati, Sudipta Sengupta. 306-312 [doi]
• Unsupervised Dense Retrieval for Scientific ArticlesDan Li, Vikrant Yadav, Zubair Afzal, George Tsatsaronis 0001. 313-321 [doi]
• Learning Geolocations for Cold-Start and Hard-to-Resolve Addresses via Deep Metric LearningGovind, Saurabh Sohoney. 322-331 [doi]
• Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical NetworksArijit Sehanobish, Kawshik Kannan, Nabila Abraham, Anasuya Das, Benjamin Odry. 332-347 [doi]
• Named Entity Recognition in Industrial Tables using Tabular Language ModelsAneta Koleva, Martin Ringsquandl, Mark Buckley, Rakebul Hasan, Volker Tresp. 348-356 [doi]
• Reinforced Question Rewriting for Conversational Question AnsweringZhiYu Chen, Jie Zhao, Anjie Fang, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi. 357-370 [doi]
• Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample SelectionStefan Schroedl, Manoj Kumar, Kiana Hajebi, Morteza Ziyadi, Sriram Venkatapathy, Anil Ramakrishna, Rahul Gupta 0001, Pradeep Natarajan. 371-378 [doi]
• Improving Precancerous Case Characterization via Transformer-based Ensemble LearningYizhen Zhong, Jiajie Xiao, Thomas Vetterli, Mahan Matin, Ellen Loo, Jimmy Lin, Richard Bourgon, Ofer Shapira. 379-389 [doi]
• Developing Prefix-Tuning Models for Hierarchical Text ClassificationLei Chen, Hou Wei Chou, Xiaodan Zhu. 390-397 [doi]
• PAIGE: Personalized Adaptive Interactions Graph Encoder for Query Rewriting in Dialogue SystemsDaniel Bis, Saurabh Gupta, Jie Hao, Xing Fan, Chenlei Guo. 398-408 [doi]
• Fast Vocabulary Transfer for Language Model CompressionLeonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo Torroni. 409-416 [doi]
• Multimodal Context CarryoverPrashan Wanigasekara, Nalin Gupta, Fan Yang, Emre Barut, Zeynab Raeesy, Kechen Qin, Stephen Rawls, Xinyue Liu, Chengwei Su, Spurthi Sandiri. 417-428 [doi]
• Distilling Multilingual Transformers into CNNs for Scalable Intent ClassificationBesnik Fetahu, Akash Veeragouni, Oleg Rokhlenko, Shervin Malmasi. 429-439 [doi]
• Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service SupportStephen Obadinma, Faiza Khan Khattak, Shirley Wang, Tania Sidhorn, Elaine Lau, Sean Robertson, Jingcheng Niu, Winnie Au, Alif Munim, Karthik Raja K. Bhaskar. 440-450 [doi]
• Zero-Shot Dynamic Quantization for Transformer InferenceYousef El-Kurdi, Jerry Quinn, Avi Sil. 451-457 [doi]
• Fact Checking Machine Generated Text with Dependency TreesAlex Estes, Nikhita Vedula, Marcus D. Collins, Matt Cecil, Oleg Rokhlenko. 458-466 [doi]
• Prototype-Representations for Training Data Filtering in Weakly-Supervised Information ExtractionNasser Zalmout, Xian Li. 467-474 [doi]
• CGF: Constrained Generation Framework for Query Rewriting in Conversational AIJie Hao, Yang Liu, Xing Fan, Saurabh Gupta, Saleh Soltan, Rakesh Chada, Pradeep Natarajan, Chenlei Guo, Gökhan Tür. 475-483 [doi]
• Entity-level Sentiment Analysis in Contact Center Telephone ConversationsXue-Yong Fu, Cheng Chen, Md. Tahmid Rahman Laskar, Shayna Gardiner, Pooja Hiranandani, Shashi Bhushan TN. 484-491 [doi]
• QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage DistillationKrishna Srinivasan, Karthik Raman 0001, Anupam Samanta, Lingrui Liao, Luca Bertelli, Michael Bendersky. 492-501 [doi]
• Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual AssistantsCheng Qian, Haode Qi, Gengyu Wang, Ladislav Kunc, Saloni Potdar. 502-511 [doi]
• PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt LearningZeyang Lei, Chao Zhang, Xinchao Xu, WenQuan Wu, Zheng-Yu Niu, Hua Wu 0003, Haifeng Wang 0001, Yi Yang, Shuanglong Li. 512-520 [doi]
• Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search ClassificationJai Gupta, Yi Tay, Chaitanya Kamath, Vinh Tran 0002, Donald Metzler, Shailesh Bavadekar, Mimi Sun, Evgeniy Gabrilovich. 521-530 [doi]
• Full-Stack Information Extraction System for Cybersecurity IntelligenceYoungja Park, Taesung Lee. 531-539 [doi]
• Deploying Unified BERT Moderation Model for E-Commerce ReviewsRavindra Nayak, Nikesh Garera. 540-547 [doi]
• SimANS: Simple Ambiguous Negatives Sampling for Dense Text RetrievalKun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan. 548-559 [doi]
• Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-trainingTaolin Zhang, Junwei Dong, Jianing Wang, Chengyu Wang 0001, Ang Wang, Yinghui Liu, Jun Huang 0007, Yong Li, Xiaofeng He. 560-570 [doi]
• A Stacking-based Efficient Method for Toxic Language Detection on Live Streaming ChatYuto Oikawa, Yuki Nakayama, Koji Murakami. 571-578 [doi]
• End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and EnglishAbhinav Goyal 0003, Anupam Singh, Nikesh Garera. 579-586 [doi]
• PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled DistillationLianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin. 587-595 [doi]
• A Comprehensive Evaluation of Biomedical Entity-centric SearchElena Tutubalina, Zulfat Miftahutdinov, Vladimir Muravlev, Anastasia Shneyderman. 596-605 [doi]
• Domain Adaptation of Machine Translation with CrowdworkersMakoto Morishita, Jun Suzuki, Masaaki Nagata. 606-618 [doi]
• Biomedical NER for the Enterprise with Distillated BERN2 and the Kazu FrameworkWonjin Yoon, Richard Jackson, Elliot Ford, Vladimir Poroshin, Jaewoo Kang. 619-626 [doi]
• Large-scale Machine Translation for Indian Languages in E-commerce under Low Resource ConstraintsAmey Patil, Nikesh Garera. 627-634 [doi]
• Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry DatasetAnton Eklund, Mona Forsman. 635-643 [doi]