PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers EACL

Michael Saxon | Xinyi Wang | Wenda Xu | William Yang Wang |

A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models F i n d i n g s - E A C L

Jimin Sun | Patrick Fernandes | Xinyi Wang | Graham Neubig |

TheoremQA: A Theorem-driven Question Answering Dataset EMNLP

Wenhu Chen | Ming Yin | Max Ku | Pan Lu | Yixin Wan | Xueguang Ma | Jianyu Xu | Xinyi Wang | Tony Xia |

Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction F i n d i n g s - A C L

Xinyi Wang | Zitao Wang | Wei Hu |

Continual Event Extraction with Semantic Confusion Rectification EMNLP

Zitao Wang | Xinyi Wang | Wei Hu |

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages F i n d i n g s - E M N L P

Sebastian Ruder | Jonathan Clark | Alexander Gutkin | Mihir Kale | Min Ma | Massimo Nicosia | Shruti Rijhwani | Parker Riley | Jean-Michel Sarr | Xinyi Wang | John Wieting | Nitish Gupta | Anna Katanova | Christo Kirov | Dana Dickinson | Brian Roark | Bidisha Samanta | Connie Tao | David Adelani | Vera Axelrod | Isaac Caswell | Colin Cherry | Dan Garrette | Reeve Ingle | Melvin Johnson | Dmitry Panteleev | Partha Talukdar |

Evaluating and Modeling Attribution for Cross-Lingual Question Answering EMNLP

Benjamin Muller | John Wieting | Jonathan Clark | Tom Kwiatkowski | Sebastian Ruder | Livio Soares | Roee Aharoni | Jonathan Herzig | Xinyi Wang |

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning F i n d i n g s - E M N L P

Liangming Pan | Alon Albalak | Xinyi Wang | William Wang |

Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation EMNLP

Wanrong Zhu | Xinyi Wang | Yujie Lu | Tsu-Jui Fu | Xin Wang | Miguel Eckstein | William Wang |

mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations F i n d i n g s - E M N L P

Jonas Pfeiffer | Francesco Piccinno | Massimo Nicosia | Xinyi Wang | Machel Reid | Sebastian Ruder |

CMU’s IWSLT 2022 Dialect Speech Translation System ACL IWSLT

Brian Yan | Patrick Fernandes | Siddharth Dalmia | Jiatong Shi | Yifan Peng | Dan Berrebbi | Xinyi Wang | Graham Neubig | Shinji Watanabe |

Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation ACL

Xinyi Wang | Sebastian Ruder | Graham Neubig |

Multi-view Subword Regularization NAACL

Xinyi Wang | Sebastian Ruder | Graham Neubig |

Modeling Disclosive Transparency in NLP Application Descriptions EMNLP

Michael Saxon | Sharon Levy | Xinyi Wang | Alon Albalak | William Yang Wang |

Efficient Test Time Adapter Ensembling for Low-resource Language Varieties EMNLP Findings

Xinyi Wang | Yulia Tsvetkov | Sebastian Ruder | Graham Neubig |

Balancing Training for Multilingual Neural Machine Translation ACL

Xinyi Wang | Yulia Tsvetkov | Graham Neubig |

Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation EMNLP Findings

Luyu Gao | Xinyi Wang | Graham Neubig |

Domain Differential Adaptation for Neural Machine Translation EMNLP WS

Zi-Yi Dou | Xinyi Wang | Junjie Hu | Graham Neubig |

compare-mt: A Tool for Holistic Comparison of Language Generation Systems NAACL

Graham Neubig | Zi-Yi Dou | Junjie Hu | Paul Michel | Danish Pruthi | Xinyi Wang |

Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation ACL

Xinyi Wang | Graham Neubig |

SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation EMNLP

Xinyi Wang | Hieu Pham | Zihang Dai | Graham Neubig |

A Tree-based Decoder for Neural Machine Translation EMNLP

Xinyi Wang | Hieu Pham | Pengcheng Yin | Graham Neubig |

XNMT: The eXtensible Neural Machine Translation Toolkit AMTA WS

Graham Neubig | Matthias Sperber | Xinyi Wang | Matthieu Felix | Austin Matthews | Sarguna Padmanabhan | Ye Qi | Devendra Sachan | Philip Arthur | Pierre Godard | John Hewitt | Rachid Riad | Liming Wang |