 The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in
TransformersInternational Conference on Learning Representations (ICLR), 2022 |
 Decoupled Context Processing for Context Augmented Language ModelingNeural Information Processing Systems (NeurIPS), 2022 |
 Understanding and Improving Zero-shot Multi-hop Reasoning in Generative
Question AnsweringInternational Conference on Computational Linguistics (COLING), 2022 |
 Generative Language Models for Paragraph-Level Question GenerationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Retrieval Augmented Visual Question Answering with Outside KnowledgeConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Measuring and Narrowing the Compositionality Gap in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 A Unified Encoder-Decoder Framework with Entity MemoryConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question
AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 MuRAG: Multimodal Retrieval-Augmented Generator for Open Question
Answering over Images and TextConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Recitation-Augmented Language ModelsInternational Conference on Learning Representations (ICLR), 2022 |
 Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple
TasksAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 DecAF: Joint Decoding of Answers and Logical Forms for Question
Answering over Knowledge BasesInternational Conference on Learning Representations (ICLR), 2022 |
 FiD-Light: Efficient and Effective Retrieval-Augmented Text GenerationAnnual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2022 |
 Variational Open-Domain Question AnsweringInternational Conference on Machine Learning (ICML), 2022 |
 Generate rather than Retrieve: Large Language Models are Strong Context
GeneratorsInternational Conference on Learning Representations (ICLR), 2022 |
 Adapting Pretrained Text-to-Text Models for Long Text SequencesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Generating Persuasive Responses to Customer Reviews with Multi-Source
Prior Knowledge in E-commerceInternational Conference on Information and Knowledge Management (CIKM), 2022 |
 Domain-Specific NER via Retrieving Correlated SamplesInternational Conference on Computational Linguistics (COLING), 2022 |
 Z-Code++: A Pre-trained Language Model Optimized for Abstractive
SummarizationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Learning New Skills after Deployment: Improving open-domain
internet-driven dialogue with human feedbackAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Efficient Long-Text Understanding with Short-Text ModelsTransactions of the Association for Computational Linguistics (TACL), 2022 |
 Claim-Dissector: An Interpretable Fact-Checking System with Joint
Re-ranking and Veracity PredictionAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 RealTime QA: What's the Answer Right Now?Neural Information Processing Systems (NeurIPS), 2022 |
 Retrieval-Augmented Transformer for Image CaptioningInternational Conference on Content-Based Multimedia Indexing (CBMI), 2022 |
 Re2G: Retrieve, Rerank, GenerateNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 DocPrompting: Generating Code by Retrieving the DocsInternational Conference on Learning Representations (ICLR), 2022 |
 A Survey on Table Question Answering: Recent AdvancesChina Conference on Knowledge Graph and Semantic Computing (CKGSC), 2022 |
 INSCIT: Information-Seeking Conversations with Mixed-Initiative
InteractionsTransactions of the Association for Computational Linguistics (TACL), 2022 |
 QA Is the New KR: Question-Answer Pairs as Knowledge BasesAAAI Conference on Artificial Intelligence (AAAI), 2022 |
 Forecasting Future World Events with Neural NetworksNeural Information Processing Systems (NeurIPS), 2022 |
 OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking
ExperienceACM Transactions on the Web (TWEB), 2022 |
 LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning
TasksNeural Information Processing Systems (NeurIPS), 2022 |
 REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual
Question AnsweringNeural Information Processing Systems (NeurIPS), 2022 |
 kNN-Prompt: Nearest Neighbor Zero-Shot InferenceConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Optimizing Test-Time Query Representations for Dense RetrievalAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Training Language Models with Memory AugmentationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 QAMPARI: An Open-domain Question Answering Benchmark for Questions with
Many Answers from Multiple ParagraphsIEEE Games Entertainment Media Conference (GEM), 2022 |
 Generating Natural Language Proofs with Verifier-Guided SearchConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
