Jungo Kasai

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation EMNLP 2025 A Call for Clarity in Beam Search: How It Works and When It Stops COLING 2024 FOLIO: Natural Language Reasoning with First-Order Logic EMNLP 2024 Summarization-Based Document IDs for Generative Retrieval with Language Models EMNLP 2024 Batch Prompting: Efficient Inference with Large Language Model APIs EMNLP 2023 BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting ACL 2023 Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models EMNLP 2023 NarrowBERT: Accelerating Masked Language Model Pretraining and Inference ACL 2023 One Embedder, Any Task: Instruction-Finetuned Text Embeddings ACL 2023 RealTime QA: What's the Answer Right Now? NeurIPS 2023 Selective Annotation Makes Language Models Better Few-Shot Learners ICLR 2023 TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering ICCV 2023 ABC: Attention with Bounded-memory Control ACL 2022 Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand NAACL 2022 GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation EMNLP 2022 How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers EMNLP 2022 MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages NAACL 2022 NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics NAACL 2022 Transparent Human Evaluation for Image Captioning NAACL 2022 Twist Decoding: Diverse Generators Guide Each Other EMNLP 2022 Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation ICLR 2021 Findings of the 2021 Conference on Machine Translation (WMT21) EMNLP 2021 Finetuning Pretrained Transformers into RNNs EMNLP 2021 One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval NeurIPS 2021 Probing Across Time: What Does RoBERTa Know and When? EMNLP 2021 XOR QA: Cross-lingual Open-Retrieval Question Answering NAACL 2021 Non-autoregressive Machine Translation with Disentangled Context Transformer ICML 2020 Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations EMNLP 2019 Low-resource Deep Entity Resolution with Transfer and Active Learning ACL 2019 Low-Resource Parsing with Crosslingual Contextualized Representations CoNLL 2019 Polyglot Contextual Representations Improve Crosslingual Transfer NAACL 2019 ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks AAAI 2019 Syntax-aware Neural Semantic Role Labeling with Supertags NAACL 2019 End-to-End Graph-Based TAG Parsing with Neural Networks NAACL 2018 Robust Multilingual Part-of-Speech Tagging via Adversarial Training NAACL 2018 TAG Parsing with Neural Networks and Vector Representations of Supertags EMNLP 2017