 Joint Passage Ranking for Diverse Multi-Answer RetrievalConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Cross-Modal Retrieval Augmentation for Multi-Modal ClassificationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Retrieval Augmentation Reduces Hallucination in ConversationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Designing a Minimal Retrieve-and-Read System for Open-Domain Question
AnsweringNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Static Embeddings as Efficient Knowledge Bases?North American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Hurdles to Progress in Long-form Question AnsweringNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 PAQ: 65 Million Probably-Asked Questions and What You Can Do With ThemTransactions of the Association for Computational Linguistics (TACL), 2021 |
 Decontextualization: Making Sentences Stand-AloneTransactions of the Association for Computational Linguistics (TACL), 2021 |
 Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained
Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL), 2021 |
 Structured Prediction as Translation between Augmented Natural LanguagesInternational Conference on Learning Representations (ICLR), 2021 |
 Rider: Reader-Guided Passage Reranking for Open-Domain Question
AnsweringFindings (Findings), 2021 |
 UnitedQA: A Hybrid Approach for Open Domain Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 |
 NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons
LearnedNeural Information Processing Systems (NeurIPS), 2021 |
 Joint Verification and Reranking for Open Fact Checking Over TablesAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Learning Dense Representations of Phrases at ScaleAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Answering Ambiguous Questions through Generative Evidence Fusion and
Round-Trip PredictionAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Answering Open-Domain Questions of Varying Reasoning Steps from TextConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Open Question Answering over Tables and TextInternational Conference on Learning Representations (ICLR), 2020 |
 RocketQA: An Optimized Training Approach to Dense Passage Retrieval for
Open-Domain Question AnsweringNorth American Chapter of the Association for Computational Linguistics (NAACL), 2020 |
 Answering Complex Open-Domain Questions with Multi-Hop Dense RetrievalInternational Conference on Learning Representations (ICLR), 2020 Wenhan Xiong Xiang Lorraine Li Srini Iyer Jingfei Du Patrick Lewis ...Yashar Mehdad Anuj Kumar Sebastian Riedel Douwe Kiela Barlas Oğuz |
 Generation-Augmented Retrieval for Open-domain Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Cluster-Former: Clustering-based Sparse Transformer for Long-Range
Dependency EncodingFindings (Findings), 2020 |
 Question and Answer Test-Train Overlap in Open-Domain Question Answering
DatasetsConference of the European Chapter of the Association for Computational Linguistics (EACL), 2020 |
 Big Bird: Transformers for Longer SequencesNeural Information Processing Systems (NeurIPS), 2020 |
 BERT-kNN: Adding a kNN Search Component to Pretrained Language Models
for Better QAFindings (Findings), 2020 |
 Dense Passage Retrieval for Open-Domain Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question
AnsweringInternational Conference on Learning Representations (ICLR), 2019 |
