{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/natural-language-understanding/papers/13","list_of":"/task/natural-language-understanding","task":"Natural Language Understanding","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":20,"rows_per_page":100,"rows":[1201,1300],"of":1978,"counts":{"archive_papers_tagged":1978,"with_a_code_link":809,"where_syntology_ran_a_sample":185,"not_listed_spam_title":0,"listed":1978,"listed_where_code_ran":185,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":155,"every_run_a_failure_of_syntologys_instrument":30,"listed_with_a_run_with_no_instrument_failure":155,"listed_every_run_a_failure_of_syntologys_instrument":30,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/natural-language-understanding","prev":"/task/natural-language-understanding/papers/12","next":"/task/natural-language-understanding/papers/14","papers":[{"url":null,"slug":"how-robust-is-gpt-3-5-to-predecessors-a","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","date":"2023-03-01","arxiv_id":"2303.00293","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-natural-language-understanding","title":"Understanding Natural Language Understanding Systems. A Critical Analysis","date":"2023-03-01","arxiv_id":"2303.04229","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-multimodal-multitask-multilingual","title":"Few-shot Multimodal Multitask Multilingual Learning","date":"2023-02-19","arxiv_id":"2303.12489","repositories_listed":0,"syntology":null},{"url":null,"slug":"bag-of-tricks-for-effective-language-model","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","date":"2023-02-18","arxiv_id":"2302.09268","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-prompt-generation-for-semi","title":"Scalable Prompt Generation for Semi-supervised Learning with Language Models","date":"2023-02-18","arxiv_id":"2302.09236","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-of-bias-terms-in-dot-product-attention","title":"Role of Bias Terms in Dot-Product Attention","date":"2023-02-16","arxiv_id":"2302.08626","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-learning-an-adversarial-process-of-two","title":"EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance","date":"2023-02-08","arxiv_id":"2302.03896","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-natural-language-understanding-with","title":"Reliable Natural Language Understanding with Large Language Models and Answer Set Programming","date":"2023-02-07","arxiv_id":"2302.03780","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impacts-of-unanswerable-questions-on-the","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","date":"2023-01-31","arxiv_id":"2302.00094","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-use-probing-to-better-understand-fine","title":"Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?","date":"2023-01-27","arxiv_id":"2301.11688","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-taxonomic-and-thematic-embeddings-for","title":"Probing Taxonomic and Thematic Embeddings for Taxonomic Information","date":"2023-01-25","arxiv_id":"2301.10656","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cohesive-distillation-architecture-for","title":"A Cohesive Distillation Architecture for Neural Language Models","date":"2023-01-12","arxiv_id":"2301.08130","repositories_listed":0,"syntology":null},{"url":null,"slug":"counteracts-testing-stereotypical","title":"Counteracts: Testing Stereotypical Representation in Pre-trained Language Models","date":"2023-01-11","arxiv_id":"2301.04347","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-semantic-representations-combined","title":"Leveraging Semantic Representations Combined with Contextual Word Representations for Recognizing Textual Entailment in Vietnamese","date":"2023-01-01","arxiv_id":"2301.00422","repositories_listed":0,"syntology":null},{"url":null,"slug":"serengeti-massively-multilingual-language","title":"SERENGETI: Massively Multilingual Language Models for Africa","date":"2022-12-21","arxiv_id":"2212.10785","repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-language-understanding-for","title":"Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction","date":"2022-12-21","arxiv_id":"2212.10728","repositories_listed":0,"syntology":null},{"url":null,"slug":"measure-more-question-more-experimental","title":"Measure More, Question More: Experimental Studies on Transformer-based Language Models and Complement Coercion","date":"2022-12-20","arxiv_id":"2212.10536","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi3nlu-a-multilingual-multi-intent-multi","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","date":"2022-12-20","arxiv_id":"2212.10455","repositories_listed":0,"syntology":null},{"url":null,"slug":"quirk-or-palmer-a-comparative-study-of-modal","title":"Quirk or Palmer: A Comparative Study of Modal Verb Frameworks with Annotated Datasets","date":"2022-12-20","arxiv_id":"2212.10152","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-feature-memory-augmented-transformers","title":"Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification","date":"2022-12-16","arxiv_id":"2212.13898","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-massively-multilingual-natural-language","title":"The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition","date":"2022-12-13","arxiv_id":"2212.06346","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuation-kd-improved-knowledge","title":"Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization","date":"2022-12-12","arxiv_id":"2212.05998","repositories_listed":0,"syntology":null},{"url":null,"slug":"modern-french-poetry-generation-with-roberta","title":"Modern French Poetry Generation with RoBERTa and GPT-2","date":"2022-12-06","arxiv_id":"2212.02911","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuse-and-adapt-investigating-the-use-of-pre","title":"Fuse and Adapt: Investigating the Use of Pre-Trained Self-Supervising Learning Models in Limited Data NLU problems","date":"2022-12-02","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"x-pudu-at-semeval-2022-task-6-multilingual-1","title":"X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection","date":"2022-11-30","arxiv_id":"2211.16883","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-learning-for-joint-intent-and-slot","title":"Zero-Shot Learning for Joint Intent and Slot Labeling","date":"2022-11-29","arxiv_id":"2212.07922","repositories_listed":0,"syntology":null},{"url":null,"slug":"awte-bert-attending-to-wordpiece-tokenization","title":"ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling","date":"2022-11-27","arxiv_id":"2211.14829","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-representations-for-low","title":"Bidirectional Representations for Low Resource Spoken Language Understanding","date":"2022-11-24","arxiv_id":"2211.14320","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-specific-deontic-modality-detection-in","title":"Agent-Specific Deontic Modality Detection in Legal Language","date":"2022-11-23","arxiv_id":"2211.12752","repositories_listed":0,"syntology":null},{"url":null,"slug":"embracing-ambiguity-improving-similarity","title":"Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge","date":"2022-11-20","arxiv_id":"2211.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-did-you-tweet-from-inferring-the-origin","title":"Where did you tweet from? Inferring the origin locations of tweets based on contextual information","date":"2022-11-18","arxiv_id":"2211.16506","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-knowledge-enhanced-pre-trained-1","title":"A Survey of Knowledge Enhanced Pre-trained Language Models","date":"2022-11-11","arxiv_id":"2211.05994","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-structure-matters-most-in-most","title":"Local Structure Matters Most in Most Languages","date":"2022-11-09","arxiv_id":"2211.05025","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturaladversaries-can-naturalistic","title":"NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?","date":"2022-11-08","arxiv_id":"2211.04364","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-evaluation-of-a-spoken-dialogue","title":"End-to-End Evaluation of a Spoken Dialogue System for Learning Basic Mathematics","date":"2022-11-07","arxiv_id":"2211.03511","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","repositories_listed":0,"syntology":null},{"url":null,"slug":"web-api-based-chatbot-generation-with","title":"Web-API-Based Chatbot Generation with Analysis and Expansion for Training Sentences","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ew-tune-a-framework-for-privately-fine-tuning","title":"Privately Fine-Tuning Large Language Models with Differential Privacy","date":"2022-10-26","arxiv_id":"2210.15042","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-slot-type-attentions-to-improve","title":"Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling","date":"2022-10-19","arxiv_id":"2210.10227","repositories_listed":0,"syntology":null},{"url":null,"slug":"team-flow-at-drc2022-pipeline-system-for","title":"Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue","date":"2022-10-18","arxiv_id":"2210.09518","repositories_listed":0,"syntology":null},{"url":null,"slug":"textual-entailment-recognition-with-semantic","title":"Textual Entailment Recognition with Semantic Features from Empirical Text Representation","date":"2022-10-18","arxiv_id":"2210.09723","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-roles-of-text-in-text-games-1","title":"Revisiting the Roles of \"Text\" in Text Games","date":"2022-10-15","arxiv_id":"2210.08384","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-language-representation-models-think-in","title":"Can Language Representation Models Think in Bets?","date":"2022-10-14","arxiv_id":"2210.07519","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-extraction-a-survey","title":"Event Extraction: A Survey","date":"2022-10-07","arxiv_id":"2210.03419","repositories_listed":0,"syntology":null},{"url":null,"slug":"join-chain-network-a-logical-reasoning-view","title":"Join-Chain Network: A Logical Reasoning View of the Multi-head Attention in Transformer","date":"2022-10-06","arxiv_id":"2210.02729","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-will-change-things-an-empirical-study-on","title":"Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification","date":"2022-10-06","arxiv_id":"2210.02857","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-prior-bias-and-choice-paralysis","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","date":"2022-10-03","arxiv_id":"2210.01258","repositories_listed":0,"syntology":null},{"url":"/paper/a-transformer-based-threshold-free-framework-1","slug":"a-transformer-based-threshold-free-framework-1","title":"A Transformer-based Threshold-Free Framework for Multi-Intent NLU","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-korean-linguistic-resource-for-nlu","title":"Building Korean Linguistic Resource for NLU Data Generation of Banking App CS Dialog System","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"competence-based-question-generation","title":"Competence-based Question Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-meta-learning-help-mbert-for-few-shot","title":"Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eventbert-incorporating-event-based-semantics","title":"EventBERT: Incorporating Event-based Semantics for Natural Language Understanding","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-commonsense-contingent-reasoning-by","title":"Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-event-temporal-relation","title":"Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-reading-fast-and-slow-when-do-models-1","title":"Machine Reading, Fast and Slow: When Do Models “Understand” Language?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parazh-22m-a-large-scale-chinese-parabank-via","title":"ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/rsgt-relational-structure-guided-temporal","slug":"rsgt-relational-structure-guided-temporal","title":"RSGT: Relational Structure Guided Temporal Relation Extraction","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"textgraphs-16-natural-language-premise","title":"TextGraphs-16 Natural Language Premise Selection Task: Zero-Shot Premise Selection with Prompting Generative Language Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"to-what-extent-do-natural-language","title":"To What Extent Do Natural Language Understanding Datasets Correlate to Logical Reasoning? A Method for Diagnosing Logical Reasoning.","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialog-acts-for-task-driven-embodied-agents","title":"Dialog Acts for Task-Driven Embodied Agents","date":"2022-09-26","arxiv_id":"2209.12953","repositories_listed":0,"syntology":null},{"url":null,"slug":"representing-affect-information-in-word","title":"Representing Affect Information in Word Embeddings","date":"2022-09-21","arxiv_id":"2209.10583","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-offline-reinforcement-learning-help","title":"Can Offline Reinforcement Learning Help Natural Language Understanding?","date":"2022-09-15","arxiv_id":"2212.03864","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-reading-fast-and-slow-when-do-models","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","date":"2022-09-15","arxiv_id":"2209.07430","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-and-effective-gradient-based-tuning-of","title":"Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models","date":"2022-09-10","arxiv_id":"2209.04683","repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-aware-syntax-tree-based-data","title":"Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding","date":"2022-09-06","arxiv_id":"2209.02267","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialog-acts-for-task-driven-embodied-agents-1","title":"Dialog Acts for Task Driven Embodied Agents","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-semantic-understanding-with-self","title":"Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization","date":"2022-09-01","arxiv_id":"2209.00278","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-contrastive-co-training-for-event","title":"Distilling Multi-Scale Knowledge for Event Temporal Relation Extraction","date":"2022-09-01","arxiv_id":"2209.00568","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-knowledge-prompt-pre-training-for","title":"Unified Knowledge Prompt Pre-training for Customer Service Dialogues","date":"2022-08-31","arxiv_id":"2208.14652","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-and-evaluating-personalized-models-1","title":"Exploring and Evaluating Personalized Models for Code Generation","date":"2022-08-29","arxiv_id":"2208.13928","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-the-intent-landscape-of-real-world","title":"Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers","date":"2022-08-26","arxiv_id":"2208.12886","repositories_listed":0,"syntology":null},{"url":null,"slug":"shortcut-learning-of-large-language-models-in","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","date":"2022-08-25","arxiv_id":"2208.11857","repositories_listed":0,"syntology":null},{"url":null,"slug":"clower-a-pre-trained-language-model-with","title":"CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations","date":"2022-08-23","arxiv_id":"2208.10844","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-task-oriented-dialogue-models-for","title":"Adapting Task-Oriented Dialogue Models for Email Conversations","date":"2022-08-19","arxiv_id":"2208.09439","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-hierarchical-multi-task","title":"Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding","date":"2022-08-19","arxiv_id":"2208.09129","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-transfer-learning-for-low-resource","title":"Effective Transfer Learning for Low-Resource Natural Language Understanding","date":"2022-08-19","arxiv_id":"2208.09180","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeperdive-the-unreasonable-effectiveness-of","title":"DeeperDive: The Unreasonable Effectiveness of Weak Supervision in Document Understanding A Case Study in Collaboration with UiPath Inc","date":"2022-08-17","arxiv_id":"2208.08000","repositories_listed":0,"syntology":null},{"url":null,"slug":"shortcutlens-a-visual-analytics-approach-for","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","date":"2022-08-17","arxiv_id":"2208.08010","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-model-of-classification-and","title":"A Hybrid Model of Classification and Generation for Spatial Relation Extraction","date":"2022-08-15","arxiv_id":"2208.06961","repositories_listed":0,"syntology":null},{"url":null,"slug":"doro-disambiguation-of-referred-object-for","title":"DoRO: Disambiguation of referred object for embodied agents","date":"2022-07-28","arxiv_id":"2207.14205","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-planning-in-open-ended-dialogue-using","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","date":"2022-07-25","arxiv_id":"2208.02294","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-bagging-methods-for-language-models","title":"Analyzing Bagging Methods for Language Models","date":"2022-07-19","arxiv_id":"2207.09099","repositories_listed":0,"syntology":null},{"url":null,"slug":"moec-mixture-of-expert-clusters","title":"MoEC: Mixture of Expert Clusters","date":"2022-07-19","arxiv_id":"2207.09094","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-cross-lingual-transferability-of-3","title":"On the cross-lingual transferability of multilingual prototypical models across NLU tasks","date":"2022-07-19","arxiv_id":"2207.09157","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-spoken-language-understanding-3","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","date":"2022-07-17","arxiv_id":"2207.08179","repositories_listed":0,"syntology":null},{"url":null,"slug":"forming-trees-with-treeformers","title":"Forming Trees with Treeformers","date":"2022-07-14","arxiv_id":"2207.06960","repositories_listed":0,"syntology":null},{"url":null,"slug":"chat-to-design-ai-assisted-personalized","title":"Chat-to-Design: AI Assisted Personalized Fashion Design","date":"2022-07-03","arxiv_id":"2207.01058","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dog-is-passing-over-the-jet-a-text","title":"A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-concept-of-knowledge-based-question","title":"A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-babi-unlocking-babis-potential-with","title":"Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-learning-of-multiple-nlp-tasks-via","title":"Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERT","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-semi-supervised-consistency","title":"Efficient Semi-supervised Consistency Training for Natural Language Understanding","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-self-attention-with-knowledge","title":"Enhancing Self-Attention with Knowledge-Assisted Attention Maps","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-transformers-for-conversational","title":"Lightweight Transformers for Conversational AI","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"m-networks-adapting-the-triplet-networks-for","title":"m-Networks: Adapting the Triplet Networks for Acronym Disambiguation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rgl-a-simple-yet-effective-relation-graph-1","title":"RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"strategies-to-improve-few-shot-learning-for","title":"Strategies to Improve Few-shot Learning for Intent Classification and Slot-Filling","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"yes-no-or-idk-the-challenge-of-unanswerable","title":"Yes, No or IDK: The Challenge of Unanswerable Yes/No Questions","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-pre-trained-transformers-via-low","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","date":"2022-06-30","arxiv_id":"2206.15014","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-it-possible-not-to-cheat-on-the-turing","title":"Not Cheating on the Turing Test: Towards Grounded Language Learning in Artificial Intelligence","date":"2022-06-29","arxiv_id":"2206.14672","repositories_listed":0,"syntology":null}],"record_sha256":"e3854ead179f46fb962db62837218650c967758d2c7d44ee120f25bf71218666","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}