Timezone: »
Poster
NS3: Neuro-symbolic Semantic Code Search
Shushan Arakelyan · Anna Hakhverdyan · Miltiadis Allamanis · Luis Garcia · Christophe Hauser · Xiang Ren
Semantic code search is the task of retrieving a code snippet given a textual description of its functionality. Recent work has been focused on using similarity metrics between neural embeddings of text and code. However, current language models are known to struggle with longer, compositional sentences, and multi-step reasoning. To overcome this limitation, we propose supplementing the query sentence with a layout of its semantic structure. The semantic layout is used to break down the final reasoning decision into a series of lower-level decisions. We use a Neural Module Network architecture to implement this idea. We compare our model - $NS^3$ (Neuro-Symbolic Semantic Search) - to a number of baselines, including state-of-the-art semantic code retrieval methods, such as CodeBERT, CuBERT and GraphCodeBERT, and evaluate on two datasets - Code Search Net (CSN) and Code Search and Question Answering (CoSQA). On these datasets, we demonstrate that our approach results in higher performance. We also perform additional studies to show the effectiveness of our modular design when handling compositional queries.
Author Information
Shushan Arakelyan (University of Southern California)
Anna Hakhverdyan (Magical Labs)
Miltiadis Allamanis (Microsoft Research)
Luis Garcia (University of Southern California Information Sciences Institute)

Hi! I’m Dr. Luis Antonio Garcia. I just recently joined USC Information Sciences Institute as a Computer Research Scientist focusing on how we can provide any notions of safety and security for the learning-enabled Internet-of-Things (IoT)/Cyber-physical Systems (CPS). I previously held a postdoctoral appointment at the Networked & Embedded Systems Laboratory at the UCLA ECE Department, collaborating with Dr. Mani Srivastava. I have my PhD in Computer Engineering with a Cybersecurity focus from Rutgers University, where my research advisor was Dr. Saman Zonouz. My dissertation was titled “Physics for the Sake of Security, Security for the Sake of Physics.”
Christophe Hauser (USC/ISI)
Xiang Ren (University of Southern California)
More from the Same Authors
-
2020 : Poster #2 »
Xiang Ren -
2021 Spotlight: Refining Language Models with Compositional Explanations »
Huihan Yao · Ying Chen · Qinyuan Ye · Xisen Jin · Xiang Ren -
2022 : PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales »
Peifeng Wang · Aaron Chan · Filip Ilievski · Muhao Chen · Xiang Ren -
2022 : Adaptive Pre-training of Language Models for Better Logical Reasoning »
Soumya Sanyal · Yichong Xu · Shuohang Wang · Ziyi Yang · Reid Pryzant · Wenhao Yu · Chenguang Zhu · Xiang Ren -
2022 : SPRINT: Scalable Semantic Policy Pre-training via Language Instruction Relabeling »
Jesse Zhang · Karl Pertsch · Jiahui Zhang · Taewook Nam · Sung Ju Hwang · Xiang Ren · Joseph Lim -
2022 : Information-Theoretic Evaluation of Free-Text Rationales with Conditional $\mathcal{V}$-Information »
Hanjie Chen · Faeze Brahman · Xiang Ren · Yangfeng Ji · Yejin Choi · Swabha Swayamdipta -
2022 : PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales »
Peifeng Wang · Aaron Chan · Filip Ilievski · Muhao Chen · Xiang Ren -
2022 : Deep End-to-end Causal Inference »
Tomas Geffner · Javier Antorán · Adam Foster · Wenbo Gong · Chao Ma · Emre Kiciman · Amit Sharma · Angus Lamb · Martin Kukla · Nick Pawlowski · Miltiadis Allamanis · Cheng Zhang -
2022 : SPRINT: Scalable Semantic Policy Pre-training via Language Instruction Relabeling »
Jesse Zhang · Karl Pertsch · Jiahui Zhang · Taewook Nam · Sung Ju Hwang · Xiang Ren · Joseph Lim -
2022 Poster: Simultaneous Missing Value Imputation and Structure Learning with Groups »
Pablo Morales-Alvarez · Wenbo Gong · Angus Lamb · Simon Woodhead · Simon Peyton Jones · Nick Pawlowski · Miltiadis Allamanis · Cheng Zhang -
2022 Poster: Unsupervised Cross-Task Generalization via Retrieval Augmentation »
Bill Yuchen Lin · Kangmin Tan · Chris Miller · Beiwen Tian · Xiang Ren -
2021 Poster: SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning »
Aaron Chan · Jiashu Xu · Boyuan Long · Soumya Sanyal · Tanishq Gupta · Xiang Ren -
2021 Poster: Gradient-based Editing of Memory Examples for Online Task-free Continual Learning »
Xisen Jin · Arka Sadhu · Junyi Du · Xiang Ren -
2021 Poster: Refining Language Models with Compositional Explanations »
Huihan Yao · Ying Chen · Qinyuan Ye · Xisen Jin · Xiang Ren -
2018 Poster: Hierarchical Graph Representation Learning with Differentiable Pooling »
Zhitao Ying · Jiaxuan You · Christopher Morris · Xiang Ren · Will Hamilton · Jure Leskovec -
2018 Spotlight: Hierarchical Graph Representation Learning with Differentiable Pooling »
Zhitao Ying · Jiaxuan You · Christopher Morris · Xiang Ren · Will Hamilton · Jure Leskovec