Gated Linear Attention Transformers with Hardware-Efficient Training S Yang*, B Wang*, Y Shen, R Panda, Y Kim ICML 2024, 2023 | 42 | 2023 |
Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks S Yang, K Tu ACL 2022, 2021 | 38 | 2021 |
Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing C Lou, S Yang, K Tu ACL 2022, 2022 | 36 | 2022 |
Hierarchically Gated Recurrent Neural Network for Sequence Modeling Z Qin*, S Yang*, Y Zhong NeurIPS 2023 Spotlight, 2023 | 35 | 2023 |
Neural Bi-Lexicalized PCFG Induction S Yang, Y Zhao, K Tu ACL 2021, 2021 | 20 | 2021 |
Second-order unsupervised neural dependency parsing S Yang, Y Jiang, W Han, K Tu COLING 2020, 2020 | 19 | 2020 |
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols S Yang, Y Zhao, K Tu NAACL 2021, 2021 | 18 | 2021 |
Hgrn2: Gated linear rnns with state expansion Z Qin, S Yang, W Sun, X Shen, D Li, W Sun, Y Zhong COLM 2024, 2024 | 14 | 2024 |
Headed-span-based projective dependency parsing S Yang, K Tu ACL 2022, 2021 | 10 | 2021 |
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs S Yang*, W Liu*, K Tu NAACL 2022, 2022 | 6 | 2022 |
Combining (second-order) graph-based and headed-span-based projective dependency parsing S Yang, K Tu Findings of ACL 2022, 2021 | 6 | 2021 |
FLA: A Triton-based library for hardware-efficient implementations of linear attention mechanism S Yang*, Y Zhang* https://github.com/sustcsonglin/flash-linear-attention, 2024 | 4 | 2024 |
Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks Z Yan, S Yang, W Liu, K Tu EMNLP 2023, 2023 | 4 | 2023 |
Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars S Yang, RP Levy, Y Kim ACL 2023, 2022 | 3 | 2022 |
Don’t Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span Selection S Yang, K Tu ACL 2023, 2023 | 2 | 2023 |
Semantic dependency parsing with edge GNNs S Yang, K Tu Findings of the Association for Computational Linguistics: EMNLP 2022, 6096-6102, 2022 | 2 | 2022 |
Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling W Liu, S Yang, K Tu Findings of the ACL 2023, 918-931, 2023 | 1 | 2023 |
Improving Span Representation by Efficient Span-Level Attention P Ji, S Yang, K Tu EMNLP 2023 Findings, 2023 | 1 | 2023 |
Parallelizing Linear Transformers with the Delta Rule over Sequence Length S Yang, B Wang, Y Zhang, Y Shen, Y Kim arXiv preprint arXiv:2406.06484, 2024 | | 2024 |
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions W Liu*, S Yang*, Y Kim, K Tu Findings of EMNLP 2023, 2023 | | 2023 |