no code implementations • IWSLT (ACL) 2022 • Brian Yan, Patrick Fernandes, Siddharth Dalmia, Jiatong Shi, Yifan Peng, Dan Berrebbi, Xinyi Wang, Graham Neubig, Shinji Watanabe
We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems.
no code implementations • 23 May 2023 • Benjamin Muller, John Wieting, Jonathan H. Clark, Tom Kwiatkowski, Sebastian Ruder, Livio Baldini Soares, Roee Aharoni, Jonathan Herzig, Xinyi Wang
Based on these models, we improve the attribution level of a cross-lingual question-answering system.
no code implementations • 23 May 2023 • Jonas Pfeiffer, Francesco Piccinno, Massimo Nicosia, Xinyi Wang, Machel Reid, Sebastian Ruder
Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings.
1 code implementation • 21 May 2023 • Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia
We evaluate a wide spectrum of 16 large language and code models with different prompting strategies like Chain-of-Thoughts and Program-of-Thoughts.
1 code implementation • 20 May 2023 • Liangming Pan, Alon Albalak, Xinyi Wang, William Yang Wang
We also introduce a self-refinement stage, which utilizes the symbolic solver's error messages to revise symbolic formalizations.
1 code implementation • 19 May 2023 • Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin, Mihir Kale, Min Ma, Massimo Nicosia, Shruti Rijhwani, Parker Riley, Jean-Michel A. Sarr, Xinyi Wang, John Wieting, Nitish Gupta, Anna Katanova, Christo Kirov, Dana L. Dickinson, Brian Roark, Bidisha Samanta, Connie Tao, David I. Adelani, Vera Axelrod, Isaac Caswell, Colin Cherry, Dan Garrette, Reeve Ingle, Melvin Johnson, Dmitry Panteleev, Partha Talukdar
We evaluate commonly used models on the benchmark.
no code implementations • 18 May 2023 • Wanrong Zhu, Xinyi Wang, Yujie Lu, Tsu-Jui Fu, Xin Eric Wang, Miguel Eckstein, William Yang Wang
We conduct a series of experiments to compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process.
no code implementations • 12 May 2023 • Zhengqing Yuan, Huiwen Xue, Xinyi Wang, Yongming Liu, Zhuanzhe Zhao, Kun Wang
However, training models on such a large scale is challenging, and finding datasets that match the model's scale is often difficult.
1 code implementation • 11 May 2023 • Xinyi Wang, Zitao Wang, Wei Hu
Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity.
no code implementations • 3 May 2023 • Lora Bailey, Heather Smith Blake, Garner Cochran, Nathan Fox, Michael Levet, Reem Mahmoud, Elizabeth Matson, Inne Singgih, Grace Stadnyk, Xinyi Wang, Alexander Wiedemann
In this paper, we examine the computational complexity of enumeration in certain genome rearrangement models.
no code implementations • 13 Feb 2023 • Zesong Fei, Xinyi Wang, Nan Wu, Jingxuan Huang, J. Andrew Zhang
The air-ground integrated sensing and communications (AG-ISAC) network, which consists of unmanned aerial vehicles (UAVs) and ground terrestrial networks, offers unique capabilities and demands special design techniques.
1 code implementation • 27 Jan 2023 • Xinyi Wang, Wanrong Zhu, Michael Saxon, Mark Steyvers, William Yang Wang
In this study, we aim to examine the in-context learning phenomenon through a Bayesian lens, viewing large language models as topic models that implicitly infer task-related information from demonstrations.
no code implementations • 26 Dec 2022 • Xinyi Wang, Jianteng Peng, Sufang Zhang, Bihui Chen, Yi Wang, Yandong Guo
Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks.
3 code implementations • 22 Nov 2022 • Wenhu Chen, Xueguang Ma, Xinyi Wang, William W. Cohen
By combining PoT with self-consistency decoding, we can achieve SoTA performance on all math problem datasets and near-SoTA performance on financial datasets.
no code implementations • 31 Oct 2022 • Zihao Tang, Xinyi Wang, Lihaowen Zhu, Mariano Cabezas, Dongnan Liu, Michael Barnett, Weidong Cai, Chengyu Wang
Diffusion Weighted Imaging (DWI) is an advanced imaging technique commonly used in neuroscience and neurological clinical research through a Diffusion Tensor Imaging (DTI) model.
no code implementations • 24 Oct 2022 • Xinyi Wang, Mei-jen Lee, Qing Zhao, Lang Tong
We consider novelty detection in time series with unknown and nonparametric probability structures.
no code implementations • 13 Oct 2022 • Jimin Sun, Patrick Fernandes, Xinyi Wang, Graham Neubig
Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022).
no code implementations • 25 Aug 2022 • Xinyi Wang, Simon Yusuf Enoch, Dong Seong Kim
Widely used deep learning models are found to have poor robustness.
1 code implementation • 23 Jul 2022 • Xinyi Wang, Zitao Wang, Weijian Sun, Wei Hu
Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document.
Ranked #22 on Relation Extraction on DocRED
no code implementations • 6 Jul 2022 • Renjie Li, Xinyi Wang, Guan Huang, Wenli Yang, Kaining Zhang, Xiaotong Gu, Son N. Tran, Saurabh Garg, Jane Alty, Quan Bai
Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network.
1 code implementation • 15 Jun 2022 • Renming Liu, Semih Cantürk, Frederik Wenkel, Sarah McGuire, Xinyi Wang, Anna Little, Leslie O'Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek
Graph Neural Networks (GNNs) extend the success of neural networks to graph-structured data by accounting for their intrinsic geometry.
1 code implementation • 10 Jun 2022 • Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations.
1 code implementation • ACL 2022 • Xinyi Wang, Sebastian Ruder, Graham Neubig
The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language.
no code implementations • 11 Mar 2022 • Tiange Xiang, Chaoyi Zhang, Xinyi Wang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai
With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets.
no code implementations • 28 Feb 2022 • Qi Liu, Bo Yang, Zhaojian Wang, Dafeng Zhu, Xinyi Wang, Kai Ma, Xinping Guan
Therefore, federated learning can be exploited to train a collaborative fault diagnosis model.
no code implementations • 16 Dec 2021 • Michael Saxon, Xinyi Wang, Wenda Xu, William Yang Wang
Building natural language inference (NLI) benchmarks that are both challenging for modern techniques, and free from shortcut biases is difficult.
1 code implementation • Findings (EMNLP) 2021 • Xinyi Wang, Yulia Tsvetkov, Sebastian Ruder, Graham Neubig
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models.
1 code implementation • 13 Aug 2021 • Wenhu Chen, Xinyi Wang, William Yang Wang
Lots of facts can evolve with respect to time.
1 code implementation • 26 Jun 2021 • Xinyi Wang, Tiange Xiang, Chaoyi Zhang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai
We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.
no code implementations • 23 Jun 2021 • Xinyi Wang, Lang Tong
An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation.
no code implementations • 11 Jun 2021 • Xinyi Wang, Haiqin Yang, Liang Zhao, Yang Mo, Jianping Shen
Differently, in this paper, we propose RefBERT to leverage the knowledge learned from the teacher, i. e., facilitating the pre-computed BERT representation on the reference sample and compressing BERT into a smaller student model.
1 code implementation • NeurIPS 2021 • Xinyi Wang, Wenhu Chen, Michael Saxon, William Yang Wang
Although deep learning models have driven state-of-the-art performance on a wide array of tasks, they are prone to spurious correlations that should not be learned as predictive clues.
no code implementations • 29 Apr 2021 • Renjie Li, Xinyi Wang, Katherine Lawler, Saurabh Garg, Quan Bai, Jane Alty
With populations ageing, the number of people with dementia worldwide is expected to triple to 152 million by 2050.
1 code implementation • NAACL 2021 • Xinyi Wang, Sebastian Ruder, Graham Neubig
Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary.
no code implementations • 26 Feb 2021 • Xinyi Wang, Ankur Bapna, Melvin Johnson, Orhan Firat
To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts.
1 code implementation • ICLR 2021 • Hieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig
Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data.
no code implementations • 28 Jan 2021 • Hao Zhang, Xinyi Wang, Hai-Bin Yu, Jack F. Douglas
We investigate the fast $\beta$- and Johari-Goldstein (JG) $\beta$-relaxation processes, along with the elastic scattering response of glass-forming (GF) liquids and the Boson peak, in a simulated Al-Sm GF material exhibiting a fragile-strong (FS) transition.
no code implementations • 27 Jan 2021 • Hao Zhang, Xinyi Wang, Hai-Bin Yu, Jack F. Douglas
We investigate the Johari-Goldstein (JG) $\beta$-relaxation process in a model metallic glass-forming (GF) material (Al90Sm10), previously studied extensively by both frequency-dependent mechanical measurements and simulation studies devoted to equilibrium properties, by molecular dynamics simulations based on validated and optimized interatomic potentials with the primary aim of better understanding the nature of this universal relaxation process from a dynamic heterogeneity (DH) perspective.
1 code implementation • EMNLP 2021 • Michael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, William Yang Wang
Broader disclosive transparency$-$truth and clarity in communication regarding the function of AI systems$-$is widely considered desirable.
no code implementations • 9 Dec 2020 • Kursat Rasim Mestav, Xinyi Wang, Lang Tong
A deep learning approach is proposed to detect data and system anomalies using high-resolution continuous point-on-wave (CPOW) or phasor measurements.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Luyu Gao, Xinyi Wang, Graham Neubig
To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL).
no code implementations • 23 Aug 2020 • Xinyi Wang, Yilu Liu, Lang Tong
A data compression system capable of providing real-time streaming of high-resolution continuous point-on-wave (CPOW) and phasor measurement unit (PMU) measurements is proposed.
2 code implementations • ACL 2020 • Xinyi Wang, Yulia Tsvetkov, Graham Neubig
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others.
5 code implementations • ICLR 2020 • Junxian He, Xinyi Wang, Graham Neubig, Taylor Berg-Kirkpatrick
Across all style transfer tasks, our approach yields substantial gains over state-of-the-art non-generative baselines, including the state-of-the-art unsupervised machine translation techniques that our approach generalizes.
1 code implementation • ICML 2020 • Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Jaime Carbonell, Graham Neubig
To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems.
no code implementations • 21 Nov 2019 • Xinyi Wang, Jason Weston, Michael Auli, Yacine Jernite
Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence.
Ranked #5 on Open-Domain Question Answering on ELI5
1 code implementation • WS 2019 • Zi-Yi Dou, Xinyi Wang, Junjie Hu, Graham Neubig
We then use these learned domain differentials to adapt models for the target task accordingly.
no code implementations • ACL 2019 • Xinyi Wang, Graham Neubig
To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018).
2 code implementations • NAACL 2019 • Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang, John Wieting
In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation.
no code implementations • 24 Feb 2019 • Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard Hovy, Alan W. black, Jaime Carbonell, Graham V. Horwood, Shabnam Tafreshi, Mona Diab, Efsun S. Kayi, Noura Farra, Kathleen McKeown
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
1 code implementation • ICLR 2019 • Xinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig
Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages.
1 code implementation • EMNLP 2018 • Xinyi Wang, Hieu Pham, Pengcheng Yin, Graham Neubig
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations.
no code implementations • EMNLP 2018 • Xinyi Wang, Hieu Pham, Zihang Dai, Graham Neubig
In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT).
1 code implementation • WS 2018 • Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Singh Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, Liming Wang
In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing.