Weidi Xu
YOU?
Author Swipe
View article: Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning Open
Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. However, standard practices discard incorrect reasoning traces -- valuable, yet underutilized data. This pape…
View article: To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization
To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization Open
Recent advances in mathematical problem-solving with language models (LMs) integrate chain-of-thought (CoT) reasoning and code execution to harness their complementary strengths. However, existing hybrid frameworks exhibit a critical limit…
View article: Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought
Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought Open
Large language models (LLMs) have shown exceptional performance as general-purpose assistants, excelling across a variety of reasoning tasks. This achievement represents a significant step toward achieving artificial general intelligence (…
View article: LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints Open
Integrating first-order logic constraints (FOLCs) with neural networks is a crucial but challenging problem since it involves modeling intricate correlations to satisfy the constraints. This paper proposes a novel neural layer, LogicMP, wh…
View article: Learning to Discover Various Simpson's Paradoxes
Learning to Discover Various Simpson's Paradoxes Open
Simpson's paradox is a well-known statistical phenomenon that has captured the attention of statisticians, mathematicians, and philosophers for more than a century. The paradox often confuses people when it appears in data, and ignoring it…
View article: Extracting Trigger-sharing Events via an Event Matrix
Extracting Trigger-sharing Events via an Event Matrix Open
A growing interest emerges in event extraction which aims to extract multiple events with triggers and arguments. Previous methods mitigate the problem of multiple events extraction by predicting the arguments conditioned on the event trig…
View article: Question Directed Graph Attention Network for Numerical Reasoning over Text
Question Directed Graph Attention Network for Numerical Reasoning over Text Open
Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this cha…
View article: SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check Open
Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the simila…
View article: Question Directed Graph Attention Network for Numerical Reasoning over Text
Question Directed Graph Attention Network for Numerical Reasoning over Text Open
Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.
View article: SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check Open
Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the simila…
View article: Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
Symmetric Regularization based BERT for Pair-wise Semantic Reasoning Open
The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes …
View article: Variational Semi-Supervised Aspect-Term Sentiment Analysis via Transformer
Variational Semi-Supervised Aspect-Term Sentiment Analysis via Transformer Open
Aspect-term sentiment analysis (ATSA) is a longstanding challenge in natural language understanding. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborio…
View article: Semi-supervised Target-level Sentiment Analysis via Variational Autoencoder.
Semi-supervised Target-level Sentiment Analysis via Variational Autoencoder. Open
Aspect-term sentiment analysis (ATSA) is a longstanding challenge in natural language understanding. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborio…
View article: Variational Autoencoder for Semi-Supervised Text Classification
Variational Autoencoder for Semi-Supervised Text Classification Open
Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the…
View article: Semi-supervised Variational Autoencoders for Sequence Classification.
Semi-supervised Variational Autoencoders for Sequence Classification. Open
Although semi-supervised learning method based on variational autoencoder (\emph{SemiVAE}) works well in image classification tasks, it fails in text classification tasks if using vanilla LSTM as its conditional generative model. We find t…
View article: Variational Autoencoders for Semi-supervised Text Classification
Variational Autoencoders for Semi-supervised Text Classification Open
Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the…