Table of Contents

• Frontmatter [doi]
• CWSeg: An Efficient and General Approach to Chinese Word SegmentationDedong Li, Rui Zhao, Fei Tan. 1-10 [doi]
• "Knowledge is Power": Constructing Knowledge Graph of Abdominal Organs and Using Them for Automatic Radiology Report GenerationKaveri Kale, Pushpak Bhattacharyya, Aditya Shetty, Milind Gune, Kush Shrivastava, Rustom Lawyer, Spriha Biswas. 11-24 [doi]
• Hunt for Buried Treasures: Extracting Unclaimed Embodiments from Patent SpecificationsChikara Hashimoto, Gautam Kumar, Shuichiro Hashimoto, Jun Suzuki. 25-36 [doi]
• MathPrompter: Mathematical Reasoning using Large Language ModelsShima Imani, Liang Du, Harsh Shrivastava 0001. 37-42 [doi]
• Constrained Policy Optimization for Controlled Self-Learning in Conversational AI SystemsMohammad Kachuee, Sungjin Lee. 43-52 [doi]
• pNLP-Mixer: an Efficient all-MLP Architecture for LanguageFrancesco Fusco, Damian Pascual, Peter W. J. Staar, Diego Antognini. 53-60 [doi]
• Extracting Text Representations for Terms and Phrases in Technical DomainsFrancesco Fusco, Diego Antognini. 61-70 [doi]
• CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image RetrievalJiapeng Wang, Chengyu Wang 0001, Xiaodan Wang, Jun Huang 0007, Lianwen Jin. 71-80 [doi]
• KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerceQinjin Jia, Yang Liu, Daoping Wu, Shaoyuan Xu, Huidong Liu, Jinmiao Fu, Roland Vollgraf, Bryan Wang. 81-88 [doi]
• Domain-specific transformer models for query translationMandar Kulkarni, Nikesh Garera, Anusua Trivedi. 89-95 [doi]
• Label efficient semi-supervised conversational intent classificationMandar Kulkarni, Kyung Kim, Nikesh Garera, Anusua Trivedi. 96-102 [doi]
• xPQA: Cross-Lingual Product Question Answering in 12 LanguagesXiaoyu Shen, Akari Asai, Bill Byrne, Adrià de Gispert. 103-115 [doi]
• Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News DetectionBeizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, ZhengJia Wang, Zhiwei Jin. 116-125 [doi]
• AVEN-GR: Attribute Value Extraction and Normalization using product GRaphsThomas Ricatte, Donato Crisostomi. 126-133 [doi]
• GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language ModelShicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang. 134-148 [doi]
• FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge GraphXiaodan Wang, Chengyu Wang 0001, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao. 149-158 [doi]
• Entity Contrastive Learning in a Large-Scale Virtual Assistant SystemJonathan Rubin, Jason Crowley, George Leung, Morteza Ziyadi, Maria Minakova. 159-171 [doi]
• Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce CatalogKewei Cheng, Xian Li, Zhengyang Wang, Chenwei Zhang, Binxuan Huang, Yifan Ethan Xu, Xin Luna Dong, Yizhou Sun. 172-185 [doi]
• Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented DialogsAbishek Komma, Nagesh Panyam Chandrasekarasastry, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas, Aram Galstyan. 186-195 [doi]
• Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial ReportsChuang Liu, Junzhuo Li, Deyi Xiong. 196-207 [doi]
• KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model ApplicationsHwaran Lee, Seokhee Hong 0002, Joonsuk Park, Takyoung Kim, Gunhee Kim, Jung-Woo Ha. 208-224 [doi]
• Improving Knowledge Production Efficiency With Question Answering on ConversationChanglin Yang, Siye Liu, Sen Hu, Wangshu Zhang, Teng Xu, Jing Zheng. 225-234 [doi]
• Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware LossesDonato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Kay Rottmann, Alessandro Manzotti, Enrico Palumbo, Davide Bernardi. 235-247 [doi]
• Distilled Language Models are economically efficient for the enterprise. ...mostlyKristen Howell, Gwen Christian, Pavel Fomitchov, Gitit Kehat, Julianne Marzulla, Leanne Rolston, Jadin Tredup, Ilana Zimmerman, Ethan Selfridge, Joseph Bradley. 248-267 [doi]
• Application-Agnostic Language Modeling for On-Device ASRMarkus Nußbaum-Thom, Lyan Verwimp, Youssef Oualil. 268-275 [doi]
• Building Accurate Low Latency ASR for Streaming Voice Search in E-commerceAbhinav Goyal 0003, Nikesh Garera. 276-283 [doi]
• PLAtE: A Large-scale Dataset for List Page Web ExtractionAidan San, Yuan Zhuang, Jan Bakus, Colin Lockard, David M. Ciemiewicz, Sandeep Atluri, Kevin Small, Yangfeng Ji, Heba Elfardy. 284-294 [doi]
• Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference SpeedBingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang 0001, Ziheng Wu, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen Chen, Jun Huang 0007. 295-304 [doi]
• Large Scale Generative Multimodal Attribute Extraction for E-commerce AttributesAnant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni, Deepak Gupta. 305-312 [doi]
• Consistent Text Categorization using Data Augmentation in e-CommerceNoa Avigdor, Guy Horowitz, Ariel Raviv, Stav Yanovsky Daye. 313-321 [doi]
• An efficient method for Natural Language Querying on Structured DataHanoz Bhathena, Aviral Joshi, Prateek Singh. 322-331 [doi]
• Boosting Transformers and Language Models for Clinical Prediction in ImmunotherapyZekai Chen, Mariann Micsinai Balan, Kevin Brown. 332-340 [doi]
• EvolveMT: an Ensemble MT Engine Improving Itself with Usage OnlyKamer Ali Yüksel, Ahmet Gunduz, Mohamed Al-Badrashiny, Hassan Sawaf. 341-346 [doi]
• A Static Evaluation of Code Completion by Large Language ModelsHantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng Li, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta. 347-360 [doi]
• Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational SystemsSarthak Ahuja, Mohammad Kachuee, Fatemeh Sheikholeslami, Weiqing Liu, Jaeyoung Do. 361-367 [doi]
• MobileNMT: Enabling Translation in 15MB and 30msYe-Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu. 368-378 [doi]
• Multi-doc Hybrid Summarization via Salient Representation LearningMin Xiao. 379-389 [doi]
• SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy LabelsZhenting Qi, Xiaoyu Tan, Chao Qu, Yinghui Xu, Yuan Qi. 390-403 [doi]
• Chemical Language Understanding BenchmarkYunsoo Kim, Hyuk Ko, Jane Lee, Hyun Young Heo, Jinyoung Yang, SungSoo Lee, Kyu-Hwang Lee. 404-411 [doi]
• HyperT5: Towards Compute-Efficient Korean Language ModelingDongju Park, Soonwon Ka, Kang Min Yoo, Gichang Lee, Jaewook Kang. 412-424 [doi]
• Semantic Ambiguity Detection in Sentence Classification using Task-Specific EmbeddingsJong-Myoung Kim, Young-Jun Lee, Sangkeun Jung, Ho-Jin Choi. 425-437 [doi]
• Reliable and Interpretable Drift Detection in Streams of Short TextsElla Rabinovich, Matan Vetzler, Samuel Ackerman, Ateret Anaby-Tavor. 438-446 [doi]
• Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language UnderstandingJonathan J. Hüser, Judith Gaspers, Thomas Gueudré, Chandana Satya Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev. 447-456 [doi]
• Annotating Research Infrastructure in Scientific Papers: An NLP-driven ApproachSeyed Amin Tabatabaei, Georgios Cheirmpos, Marius A. Doornenbal, Alberto Zigoni, Véronique Moore, Georgios Tsatsaronis. 457-463 [doi]
• Event-Centric Query Expansion in Web SearchYanan Zhang, Weijie Cui, Yangfan Zhang, Xiaoling Bai, Zhe Zhang, Jin Ma, Xiang Chen, Tianhua Zhou. 464-475 [doi]
• Transferable and Efficient: Unifying Dynamic Multi-Domain Product CategorizationShansan Gong, Zelin Zhou, Shuo Wang, Fengjiao Chen, Xiujie Song, Xuezhi Cao, Yunsen Xian, Kenny Q. Zhu. 476-486 [doi]
• DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program InductionPaul Darm, Antonio Valerio Miceli Barone, Shay B. Cohen, Annalisa Riccardi. 487-499 [doi]
• BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early ExitingWei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang. 500-509 [doi]
• K-pop and fake facts: from texts to smart alerting for maritime securityMaxime Prieur, Souhir Gahbiche, Guillaume Gadek, Sylvain Gatepaille, Kilian Vasnier, Valerian Justine. 510-517 [doi]
• Evaluating Embedding APIs for Information RetrievalEhsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-Hermelo, Mehdi Rezagholizadeh, Jimmy Lin. 518-526 [doi]
• Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing PlatformMateusz Wójcik, Witold Kosciukiewicz, Mateusz Baran, Tomasz Kajdanowicz, Adam Gonczarek. 527-537 [doi]
• Regression-Free Model Updates for Spoken Language UnderstandingAndrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi. 538-551 [doi]
• Reducing cohort bias in natural language understanding systems with targeted self-training schemeDieu-Thu Le, Gabriela Hernández, Bei Chen, Melanie Bradford. 552-560 [doi]
• Content Moderation for Evolving Policies using Binary Question AnsweringSankha Subhra Mullick, Mohan Bhambhani, Suhit Sinha, Akshat Mathur, Somya Gupta, Jidnya Shah. 561-573 [doi]
• Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product ClassificationTianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao. 574-580 [doi]
• Towards Building a Robust Toxicity PredictorDmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Liutong Zhou, Yanjun Qi. 581-598 [doi]
• AI Coach Assist: An Automated Approach for Call Recommendation in Contact Centers for Agent CoachingMd. Tahmid Rahman Laskar, Cheng Chen, Xue-Yong Fu, Mahsa Azizi, Shashi Bhushan TN, Simon Corston-Oliver. 599-607 [doi]
• Unified Contextual Query RewritingYingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Thanvantri Vasudevan, Kellen Gillespie, Zeynab Raeesy. 608-615 [doi]
• Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce WebsitesSimiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao. 616-628 [doi]
• Federated Learning of Gboard Language Models with Differential PrivacyZheng Xu 0002, Yanxiang Zhang, Galen Andrew, Christopher A. Choquette-Choo, Peter Kairouz, H. Brendan McMahan, Jesse Rosenstock, Yuanbo Zhang. 629-639 [doi]
• RadLing: Towards Efficient Radiology Report UnderstandingRikhiya Ghosh, Oladimeji Farri, Sanjeev Kumar Karn, Manuela Daniela Danu, Ramya Vunikili, Larisa Micu. 640-651 [doi]
• Predicting Customer Satisfaction with Soft Labels for Ordinal ClassificationEtienne Manderscheid, Matthias Lee. 652-659 [doi]
• Accurate Training of Web-based Question Answering Systems with Feedback from Ranked UsersLiang Wang, Ivano Lauriola, Alessandro Moschitti. 660-667 [doi]
• SPM: A Split-Parsing Method for Joint Multi-Intent Detection and Slot FillingSheng Jiang, Su Zhu, Ruisheng Cao, Qingliang Miao, Kai Yu 0004. 668-675 [doi]
• NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksXinpeng Zhang, Ming Tan, Jingfan Zhang, Wei Zhu. 676-686 [doi]
• Search Query Spell Correction with Weak Supervision in E-commerceVishal Kakkar, Chinmay Sharma, Madhura Pande, Surender Kumar. 687-694 [doi]
• "Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image CaptioningAbisek Rajakumar Kalarani, Pushpak Bhattacharyya, Niyati Chhaya, Sumit Shekhar. 695-706 [doi]
• What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging DialogueDeuk Sin Kwon, SunWoo Lee, Ki Hyun Kim, Seojin Lee, Taeyoon Kim, Eric Davis. 707-719 [doi]
• CUPID: Curriculum Learning Based Real-Time Prediction using DistillationArindam Bhattacharya, Ankith M. S, Ankit Gandhi, Vijay Huddar, Atul Saroop, Rahul Bhagat. 720-728 [doi]
• Answering Unanswered Questions through Semantic Reformulations in Spoken QAPedro Faustini, ZhiYu Chen, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi. 729-743 [doi]
• Exploring Zero and Few-shot Techniques for Intent ClassificationSoham Parikh, Mitul Tiwari, Prashil Tumbade, Quaizar Vohra. 744-751 [doi]
• Referring to Screen Texts with Voice AssistantsShruti Bhargava, Anand Dhoot, Ing-Marie Jonsson, Hoang Long Nguyen 0005, Alkesh Patel, Hong Yu, Vincent Renkens. 752-762 [doi]
• Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product SearchZhiYu Chen, Jason Ingyu Choi, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi. 763-771 [doi]
• KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language ModelsZhiwei Jia, Pradyumna Narayana, Arjun R. Akula, Garima Pruthi, Hao Su 0001, Sugato Basu, Varun Jampani. 772-785 [doi]
• Weakly supervised hierarchical multi-task classification of customer questionsJitenkumar Rana, Promod Yenigalla, Chetan Aggarwal, Sandeep Sricharan Mukku, Manan Soni, Rashmi Patange. 786-793 [doi]
• Automated Digitization of Unstructured Medical PrescriptionsMegha Sharma, Tushar Vatsal, Srujana Merugu, Aruna Rajan. 794-805 [doi]