Skip to search formSkip to main contentSkip to account menu

A Transformer-based Approach for Source Code Summarization

This work explores the Transformer model that uses a self-attention mechanism and has shown to be effective in capturing long-range dependencies in source code summarization, and shows that despite the approach is simple, it outperforms the state-of-the-art techniques by a significant margin.
View on ACL (opens in a new tab)

Unified Pre-training for Program Understanding and Generation

Analysis reveals that PLBART learns program syntax, style, logical flow, and style that are crucial to program semantics and thus excels even with limited annotations, and outperforms or rivals state-of-the-art models.
View on ACL (opens in a new tab)

Context Attentive Document Ranking and Query Suggestion

A two-level hierarchical recurrent neural network is introduced to learn search context representation of individual queries, search tasks, and corresponding dependency structure by jointly optimizing two companion retrieval tasks: document ranking and query suggestion.
View on ACM (opens in a new tab)

On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing

Investigating crosslingual transfer and posit that an orderagnostic model will perform better when transferring to distant foreign languages shows that RNN-based architectures transfer well to languages that are close to English, while self-attentive models have better overall cross-lingualtransferability and perform especially well on distant languages.
View on ACL (opens in a new tab)

Multi-Task Learning for Document Ranking and Query Suggestion

View Paper (opens in a new tab)

GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction

This work introduces GATE, a Graph Attention Transformer Encoder, and test its cross-lingual transferability on relation and event extraction tasks, and shows that GATE outperforms three recently proposed methods by a large margin.
View PDF on arXiv (opens in a new tab)

PolicyQA: A Reading Comprehension Dataset for Privacy Policies

This paper argues that providing users with a short text span from policy documents reduces the burden of searching the target information from a lengthy text segment, and evaluates two existing neural QA models and performs rigorous analysis to reveal the advantages and challenges offered by PolicyQA.
View on ACL (opens in a new tab)

Cross-Lingual Dependency Parsing with Unlabeled Auxiliary Languages

This work explores adversarial training for learning contextual encoders that produce invariant representations across languages to facilitate cross-lingual transfer and proposes to leverage unannotated sentences from auxiliary languages to help learning language-agnostic representations.
View on ACL (opens in a new tab)

Intent-aware Query Obfuscation for Privacy Protection in Personalized Web Search

This work proposes a client-centered intent-aware query obfuscation solution for protecting user privacy in a personalized web search scenario, and develops two new metrics from an information theoretic perspective to evaluate the effectiveness of provided privacy protection.
View on ACM (opens in a new tab)

Multi-lingual Evaluation of Code Generation Models

This work presents MBXP, an execution-based code completion benchmark in 10+ programming languages that is able to evaluate code generation models in a multi-lingual fashion, and discovers generalization ability of language models on out-of-domain languages, advantages of large multi-lingsual models over mono-lingUAL, benefits of few-shot prompting, and zero-shot translation abilities.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)