8 citations · 22 across the 10 of their papers we have counts for
10 papers
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
Weijia Xu, Andrzej Banburski-Fahey, Nebojsa Jojic
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sa…
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
Weijia Xu, Sweta Agrawal, Eleftheria Briakou +2
Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remai…
Rule-based Morphological Inflection Improves Neural Terminology Translation
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…
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
Weijia Xu, Batool Haider, Jason Krone +1
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effectiv…
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?
Weijia Xu, Shuming Ma, Dongdong Zhang +1
While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive mode…
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
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 c…
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation
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 grad…
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
Weijia Xu, Batool Haider, Saab Mansour
Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an…
Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation
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…
Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation
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…