{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"1609.01454","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","created":"2016-09-06","cited_by_count":137},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"1909.02188","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","created":"2019-09-05","cited_by_count":107},{"id":"1907.00390","title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","created":"2019-06-30","cited_by_count":85},{"id":"2004.14353","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","created":"2020-04-29","cited_by_count":83},{"id":"2304.11384","title":"Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning","created":"2023-04-22","cited_by_count":72},{"id":"2010.03880","title":"A Co-Interactive Transformer for Joint Slot Filling and Intent Detection","created":"2020-10-08","cited_by_count":61},{"id":"2106.00641","title":"SpanNER: Named Entity Re-/Recognition as Span Prediction","created":"2021-06-01","cited_by_count":55},{"id":"1812.10235","title":"A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling","created":"2018-12-26","cited_by_count":53},{"id":"2103.03095","title":"A Survey on Spoken Language Understanding: Recent Advances and New Frontiers","created":"2021-03-04","cited_by_count":53},{"id":"2011.00564","title":"Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey","created":"2020-11-01","cited_by_count":51},{"id":"2212.09541","title":"Positive-incentive Noise","created":"2022-12-19","cited_by_count":39},{"id":"2306.07651","title":"Variational Positive-incentive Noise: How Noise Benefits Models","created":"2023-06-13","cited_by_count":38},{"id":"2104.05763","title":"Few-shot Intent Classification and Slot Filling with Retrieved Examples","created":"2021-04-12","cited_by_count":35},{"id":"1909.06937","title":"CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding","created":"2019-09-16","cited_by_count":34},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34},{"id":"2412.10817","title":"Enhance Vision-Language Alignment with Noise","created":"2024-12-14","cited_by_count":34},{"id":"2106.01925","title":"GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling","created":"2021-06-03","cited_by_count":33},{"id":"2408.09929","title":"Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise","created":"2024-08-19","cited_by_count":25},{"id":"2010.05256","title":"Few-shot Learning for Multi-label Intent Detection","created":"2020-10-11","cited_by_count":20},{"id":"2311.09008","title":"End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions","created":"2023-11-15","cited_by_count":17},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15},{"id":"2401.03804","title":"TeleChat Technical Report","created":"2024-01-08","cited_by_count":15},{"id":"2505.19024","title":"Learn Beneficial Noise as Graph Augmentation","created":"2025-05-25","cited_by_count":15},{"id":"2210.10375","title":"Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs","created":"2022-10-19","cited_by_count":14},{"id":"2509.16738","title":"Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning","created":"2025-09-20","cited_by_count":14},{"id":"2108.08042","title":"Joint Multiple Intent Detection and Slot Filling via Self-distillation","created":"2021-08-18","cited_by_count":12},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12},{"id":"2109.08890","title":"Towards Joint Intent Detection and Slot Filling via Higher-order Attention","created":"2021-09-18","cited_by_count":11},{"id":"2407.02783","title":"52B to 1T: Lessons Learned via Tele-FLM Series","created":"2024-07-03","cited_by_count":11},{"id":"2108.11711","title":"SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling","created":"2021-08-26","cited_by_count":10},{"id":"2210.10369","title":"Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling","created":"2022-10-19","cited_by_count":10},{"id":"2507.18013","title":"Technical Report of TeleChat2, TeleChat2.5 and T1","created":"2025-07-24","cited_by_count":10},{"id":"2511.12917","title":"Explore How to Inject Beneficial Noise in MLLMs","created":"2025-11-17","cited_by_count":10},{"id":"2110.13691","title":"An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling","created":"2021-10-26","cited_by_count":9},{"id":"2204.13021","title":"NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-04-27","cited_by_count":8},{"id":"2112.11953","title":"Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding","created":"2021-12-22","cited_by_count":7},{"id":"2308.14654","title":"Joint Multiple Intent Detection and Slot Filling with Supervised Contrastive Learning and Self-Distillation","created":"2023-08-28","cited_by_count":7},{"id":"2312.05741","title":"MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention","created":"2023-12-10","cited_by_count":7},{"id":"2403.04481","title":"ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent","created":"2024-03-07","cited_by_count":7},{"id":"2511.07911","title":"Rectified Noise: A Generative Model Using Positive-incentive Noise","created":"2025-11-11","cited_by_count":7},{"id":"2106.07343","title":"Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling","created":"2021-05-25","cited_by_count":6},{"id":"2411.07152","title":"HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals","created":"2024-11-11","cited_by_count":6},{"id":"2509.05602","title":"Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation","created":"2025-09-06","cited_by_count":6},{"id":"2511.07934","title":"Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers","created":"2025-11-11","cited_by_count":6},{"id":"2305.13298","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","created":"2023-05-22","cited_by_count":5},{"id":"2310.10184","title":"Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition","created":"2023-10-16","cited_by_count":5},{"id":"2403.17536","title":"ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler","created":"2024-03-26","cited_by_count":5},{"id":"2404.15219","title":"Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel","created":"2024-04-23","cited_by_count":5},{"id":"2102.10905","title":"Joint Intent Detection And Slot Filling Based on Continual Learning Model","created":"2021-02-22","cited_by_count":4},{"id":"2507.12820","title":"Emotional Support with LLM-based Empathetic Dialogue Generation","created":"2025-07-17","cited_by_count":4},{"id":"1505.00862","title":"Classifying and Ranking Microblogging Hashtags with News Categories","created":"2015-05-05","cited_by_count":3},{"id":"2210.03337","title":"A Unified Framework for Multi-intent Spoken Language Understanding with prompting","created":"2022-10-07","cited_by_count":3},{"id":"2211.12220","title":"A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding","created":"2022-11-22","cited_by_count":3},{"id":"2403.10894","title":"Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization","created":"2024-03-16","cited_by_count":3},{"id":"2103.02878","title":"An Emotion-controlled Dialog Response Generation Model with Dynamic Vocabulary","created":"2021-03-04","cited_by_count":2},{"id":"2312.13495","title":"Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling","created":"2023-12-21","cited_by_count":2},{"id":"2402.18258","title":"A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames","created":"2024-02-28","cited_by_count":2},{"id":"2406.01213","title":"Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognition","created":"2024-06-03","cited_by_count":2},{"id":"1505.00863","title":"A Feature-based Classification Technique for Answering Multi-choice World History Questions","created":"2015-05-05","cited_by_count":1},{"id":"2511.19005","title":"Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding","created":"2025-11-24","cited_by_count":1}],"next_cursor":null}