no code implementations • EMNLP 2020 • Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren
The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp.
no code implementations • 2 Feb 2024 • Xisen Jin, Xiang Ren
We propose a partially interpretable forecasting model based on the observation that changes in pre-softmax logit scores of pretraining examples resemble that of online learned examples, which performs decently on BART but fails on T5 models.
no code implementations • 25 May 2023 • Genta Indra Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro
Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time.
1 code implementation • 19 Dec 2022 • Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, Pengxiang Cheng
In this paper, we study the problem of merging individual models built on different training data sets to obtain a single model that performs well both across all data set domains and can generalize on out-of-domain data.
no code implementations • NAACL 2022 • Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew Arnold, Xiang Ren
We evaluate PTLM's ability to adapt to new corpora while retaining learned knowledge in earlier corpora.
1 code implementation • Findings (EMNLP) 2021 • Xisen Jin, Bill Yuchen Lin, Mohammad Rostami, Xiang Ren
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence.
1 code implementation • NeurIPS 2021 • Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, Xiang Ren
However, such a regularization technique lacks flexibility and coverage, since only importance scores towards a pre-defined list of features are adjusted, while more complex human knowledge such as feature interaction and pattern generalization can hardly be incorporated.
no code implementations • 1 Jan 2021 • Xisen Jin, Francesco Barbieri, Leonardo Neves, Xiang Ren
Prediction bias in machine learning models, referring to undesirable model behaviors that discriminates inputs mentioning or produced by certain group, has drawn increasing attention from the research community given its societal impact.
no code implementations • NAACL 2021 • Xisen Jin, Francesco Barbieri, Brendan Kennedy, Aida Mostafazadeh Davani, Leonardo Neves, Xiang Ren
Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution.
1 code implementation • NeurIPS 2021 • Xisen Jin, Arka Sadhu, Junyi Du, Xiang Ren
We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities.
3 code implementations • ACL 2020 • Brendan Kennedy, Xisen Jin, Aida Mostafazadeh Davani, Morteza Dehghani, Xiang Ren
Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways.
2 code implementations • EMNLP 2020 • Xisen Jin, Junyi Du, Arka Sadhu, Ram Nevatia, Xiang Ren
To study this human-like language acquisition ability, we present VisCOLL, a visually grounded language learning task, which simulates the continual acquisition of compositional phrases from streaming visual scenes.
2 code implementations • ICLR 2020 • Xisen Jin, Zhongyu Wei, Junyi Du, xiangyang xue, Xiang Ren
Human and metrics evaluation on both LSTM models and BERT Transformer models on multiple datasets show that our algorithms outperform prior hierarchical explanation algorithms.
2 code implementations • 11 Apr 2019 • Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren
The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp.
2 code implementations • 31 Aug 2018 • Xisen Jin, Wenqiang Lei, Zhaochun Ren, Hongshen Chen, Shangsong Liang, Yihong Zhao, Dawei Yin
However, the \emph{expensive nature of state labeling} and the \emph{weak interpretability} make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from manually annotated corpora, where the human annotation is expensive for training; for generating responses in non-task-oriented dialogues, most of existing work neglects the explicit state tracking due to the unlimited number of dialogue states.
1 code implementation • ACL 2018 • Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, Dawei Yin
Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility.