no code implementations • COLING 2022 • Elsbeth Turcan, David Wan, Faisal Ladhak, Petra Galuscakova, Sukanta Sen, Svetlana Tchistiakova, Weijia Xu, Marine Carpuat, Kenneth Heafield, Douglas Oard, Kathleen McKeown
Query-focused summaries of foreign-language, retrieved documents can help a user understand whether a document is actually relevant to the query term.
1 code implementation • Findings (EMNLP) 2021 • Weijia Xu, Yuwei Yin, Shuming Ma, Dongdong Zhang, Haoyang Huang
Multilingual neural machine translation models typically handle one source language at a time.
no code implementations • 25 Apr 2024 • Xiangyu Peng, Jessica Quaye, Weijia Xu, Chris Brockett, Bill Dolan, Nebojsa Jojic, Gabriel DesGarennes, Ken Lobb, Michael Xu, Jorge Leandro, Claire Jin, Sudha Rao
We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives.
no code implementations • 15 Nov 2023 • Jorge Leandro, Sudha Rao, Michael Xu, Weijia Xu, Nebosja Jojic, Chris Brockett, Bill Dolan
\textbf{GRIM}, a prototype \textbf{GR}aph-based \textbf{I}nteractive narrative visualization system for ga\textbf{M}es, generates a rich narrative graph with branching storylines that match a high-level narrative description and constraints provided by the designer.
no code implementations • 17 May 2023 • Weijia Xu, Andrzej Banburski-Fahey, Nebojsa Jojic
We introduce Reprompting, an iterative sampling algorithm that searches for the Chain-of-Thought (CoT) recipes for a given task without human intervention.
1 code implementation • 18 Jan 2023 • Weijia Xu, Sweta Agrawal, Eleftheria Briakou, Marianna J. Martindale, Marine Carpuat
Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text.
no code implementations • 27 Nov 2021 • Weijia Xu, Heidi Ross, Joel Meyer, Kelly Pierce, Natalia Ruiz Juri, Jennifer Duthie
The goal for this research is to understand the correlation between bus stop locations and mid-block crossings, so as to assist traffic engineers in implementing Vision Zero strategies to improve pedestrian safety.
1 code implementation • EMNLP 2021 • Weijia Xu, Marine Carpuat
Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms.
no code implementations • ACL (MetaNLP) 2021 • Weijia Xu, Batool Haider, Jason Krone, Saab Mansour
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks.
no code implementations • Findings (ACL) 2021 • Weijia Xu, Shuming Ma, Dongdong Zhang, Marine Carpuat
While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive models.
1 code implementation • 13 Nov 2020 • Weijia Xu, Marine Carpuat
We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Weijia Xu, Xing Niu, Marine Carpuat
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared.
3 code implementations • 1 Jul 2020 • J. Gregory Pauloski, Zhao Zhang, Lei Huang, Weijia Xu, Ian T. Foster
Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales.
no code implementations • WS 2020 • Weijia Xu, Marine Carpuat
We introduce an iterative text refinement model to reduce the decoding space of non-autoregressive models by disentangling the token prediction and relative position prediction.
3 code implementations • EMNLP 2020 • Weijia Xu, Batool Haider, Saab Mansour
We introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus.
no code implementations • 27 Jul 2019 • Zihan Jiang, Wanling Gao, Lei Wang, Xingwang Xiong, Yuchen Zhang, Xu Wen, Chunjie Luo, Hainan Ye, Yunquan Zhang, Shengzhong Feng, Kenli Li, Weijia Xu, Jianfeng Zhan
In this paper, we propose HPC AI500 --- a benchmark suite for evaluating HPC systems that running scientific DL workloads.
1 code implementation • NAACL 2019 • Weijia Xu, Xing Niu, Marine Carpuat
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are aligned at each time step.
1 code implementation • NAACL 2019 • Xing Niu, Weijia Xu, Marine Carpuat
We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT).
no code implementations • WS 2018 • Weijia Xu, Marine Carpuat
This paper describes the University of Maryland{'}s submission to the WMT 2018 Chinese↔English news translation tasks.