Ta-Chung Chi

36 papers A* 4B 1C 1Journal 21Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward.
CoRR
Dipendra Misra, Aldo Pacchiano, Ta-Chung Chi, Ge Gao
2025 J jnl
A State-of-the-Art SQL Reasoning Model using RLVR.
CoRR
Alnur Ali, Ashutosh Baheti, Jonathan Chang, Ta-Chung Chi, Brandon Cui, Andrew Drozdov, Jonathan Frankle, Abhay Gupta, Pallavi Koppol, Sean Kulinski, Jonathan Li, Dipendra Misra, Krista Opsahl-Ong, Jose Javier Gonzalez Ortiz, Matei Zaharia, Yue Zhang
2024 — conf
Advancing Regular Language Reasoning in Linear Recurrent Neural Networks.
NAACL (Short Papers)
Ting-Han Fan, Ta-Chung Chi, Alexander Rudnicky
2024 — conf
Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation.
NAACL-HLT (Findings)
Ta-Chung Chi, Ting-Han Fan, Alexander Rudnicky
2024 — —
Toward Length-Extrapolatable Transformers
Ta-Chung Chi
2023 J jnl
Advancing Regular Language Reasoning in Linear Recurrent Neural Networks.
CoRR
Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky
2023 J jnl
Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation.
CoRR
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky
2023 — conf
Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis.
ACL (1)
Ta-Chung Chi, Ting-Han Fan, Alexander Rudnicky, Peter J. Ramadge
2023 — conf
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings.
ACL (2)
Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander Rudnicky, Peter J. Ramadge
2023 J jnl
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings.
CoRR
Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander I. Rudnicky, Peter J. Ramadge
2023 — conf
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification.
ACL (1)
Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang
2023 J jnl
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification.
CoRR
Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang
2023 J jnl
Structured Dialogue Discourse Parsing.
CoRR
Ta-Chung Chi, Alexander I. Rudnicky
2023 — conf
Transformer Working Memory Enables Regular Language Reasoning And Natural Language Length Extrapolation.
EMNLP (Findings)
Ta-Chung Chi, Ting-Han Fan, Alexander Rudnicky, Peter J. Ramadge
2023 J jnl
Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation.
CoRR
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky, Peter J. Ramadge
2022 A* conf
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation.
NeurIPS
Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander Rudnicky
2022 J jnl
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation.
CoRR
Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander I. Rudnicky
2022 J jnl
On Task-Adaptive Pretraining for Dialogue Response Selection.
CoRR
Tzu-Hsiang Lin, Ta-Chung Chi, Anna Rumshisky
2022 J jnl
Receptive Field Alignment Enables Transformer Length Extrapolation.
CoRR
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky
2022 B conf
Structured Dialogue Discourse Parsing.
SIGDIAL
Ta-Chung Chi, Alexander I. Rudnicky
2022 A* conf
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator.
ICML
Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky, Peter J. Ramadge
2022 J jnl
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator.
CoRR
Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky, Peter J. Ramadge
2021 J jnl
Are you doing what I say? On modalities alignment in ALFRED.
CoRR
Ting-Rui Chiang, Yi-Ting Yeh, Ta-Chung Chi, Yau-Shian Wang
2021 — conf
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection.
EMNLP (1)
Ta-Chung Chi, Alexander I. Rudnicky
2021 J jnl
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection.
CoRR
Ta-Chung Chi, Alexander I. Rudnicky
2020 J jnl
Automatic Speech Verification Spoofing Detection.
CoRR
Shentong Mo, Haofan Wang, Pinxu Ren, Ta-Chung Chi
2020 A* conf
Just Ask: An Interactive Learning Framework for Vision and Language Navigation.
AAAI
Ta-Chung Chi, Minmin Shen, Mihail Eric, Seokhwan Kim, Dilek Hakkani-Tür
2019 J jnl
Just Ask: An Interactive Learning Framework for Vision and Language Navigation.
CoRR
Ta-Chung Chi, Mihail Eric, Seokhwan Kim, Minmin Shen, Dilek Hakkani-Tür
2018 J jnl
BCWS: Bilingual Contextual Word Similarity.
CoRR
Ta-Chung Chi, Ching-Yen Shih, Yun-Nung Chen
2018 A* conf
CLUSE: Cross-Lingual Unsupervised Sense Embeddings.
EMNLP
Ta-Chung Chi, Yun-Nung Chen
2018 J jnl
CLUSE: Cross-Lingual Unsupervised Sense Embeddings.
CoRR
Ta-Chung Chi, Yun-Nung Chen
2018 J jnl
xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks.
CoRR
Ting-Yun Chang, Ta-Chung Chi, Shang-Chi Tsai, Yun-Nung Chen
2017 J jnl
Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding.
CoRR
Po-Chun Chen, Ta-Chung Chi, Shang-Yu Su, Yun-Nung Chen
2017 C conf
Dynamic time-aware attention to speaker roles and contexts for spoken language understanding.
ASRU
Po-Chun Chen, Ta-Chung Chi, Shang-Yu Su, Yun-Nung Chen
2017 — conf
Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning.
IJCNLP(2)
Ta-Chung Chi, Po-Chun Chen, Shang-Yu Su, Yun-Nung Chen
2017 J jnl
Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning.
CoRR
Ta-Chung Chi, Po-Chun Chen, Shang-Yu Su, Yun-Nung Chen