Papers by Frank F. Xu
Mining Cross-Cultural Differences and Similarities in Social Media (P18-1)
Copied to clipboard
| Challenge: | a new paper examines the problem of computing cross-cultural differences and similarities in natural language understanding . cross-culture differences are important for cross-lingual research, especially in social media . |
| Approach: | They propose a framework for computing cross-cultural differences and similarities from social media . they propose to use a social media platform to find similar terms for slang across languages . |
| Outcome: | The proposed framework outperforms baseline methods on two novel tasks. |
Beyond Browsing: API-Based Web Agents (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing web agents use browsers to facilitate human activities such as online shopping, online planning, and other work-related tasks. |
| Approach: | They propose to use web browsers as an interface to interact with online content through application programming interfaces (APIs) they propose to call APIs and use Hybrid Agents to perform online tasks. |
| Outcome: | The proposed agents outperform web Browsing Agents on a widely-used and realistic benchmark for web navigation tasks. |
ExtRA: Extracting Prominent Review Aspects from Customer Feedback (D18-1)
Copied to clipboard
| Challenge: | Existing methods for analyzing and summarizing customer reviews are based on a number of prominent review aspects. |
| Approach: | They propose a framework for extracting the most prominent aspects of a given product type from textual reviews. |
| Outcome: | The proposed framework extracts K most prominent aspect terms which do not overlap semantically without supervision. |
CodeRAG-Bench: Can Retrieval Augment Code Generation? (2025.findings-naacl)
Copied to clipboard
Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu, Yiqing Xie, Graham Neubig, Daniel Fried
| Challenge: | Language models excel at generating code, but many programs are difficult to generate using only parametric knowledge. |
| Approach: | They propose a retrieval-augmented code generation benchmark that provides reproducible evaluations on retrieval and end-to-end code generation performance. |
| Outcome: | The proposed benchmark covers programming, open-domain, and repository-level tasks and provides reproducible evaluations on retrieval and end-to-end code generation performance. |
How Can We Know What Language Models Know? (2020.tacl-1)
Copied to clipboard
| Challenge: | Recent work examines knowledge contained in language models by having the LM fill in the blanks of prompts such as “Obama is a __ by profession”. |
| Approach: | They propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. |
| Outcome: | The proposed methods improve accuracy from 31.1% to 39.6% on the LAMA benchmark for extracting relational knowledge from LMs. |
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles. |
| Approach: | They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach . |
| Outcome: | The proposed approach achieves stronger performance than a range of comparison methods. |
AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging (P19-3)
Copied to clipboard
| Challenge: | Existing sequence annotation tools focus on improving user interfaces and user interface. |
| Approach: | They propose an open-source web-based data annotation framework for sequence tagging tasks . the framework is based on active learning and automatic crowd consolidation . |
| Outcome: | The proposed framework is a comprehensive solution for sequence labeling tasks . it can be deployed in downstream systems while new annotations are being made . |
Automatic Extraction of Commonsense LocatedNear Knowledge (P18-2)
Copied to clipboard
| Challenge: | LocatedNear relation is a kind of commonsense knowledge describing two physical objects that are typically found near each other in real life. |
| Approach: | They propose to automatically extract LocatedNear relation from corpus by a sentence-level relation classifier and aggregating scores of entity pairs from a large corpus. |
| Outcome: | The proposed method can be used to extract the commonsense LOCATEDNEAR relation from a large corpus. |
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on open-domain code generation focuses on limited domains or domain-specific languages with limited set of operators. |
| Approach: | They incorporate external knowledge into NL-to-code generation by combining StackOverflow and programming language API documentation with data augmentation and retrieval-based data re-sampling. |
| Outcome: | The proposed approach improves the current state-of-the-art by up to 2.2% absolute BLEU score on the code generation testbed CoNaLa. |
MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages (2023.findings-eacl)
Copied to clipboard
| Challenge: | MCoNaLa benchmarks natural language code generation in languages that are not native to English. |
| Approach: | They propose to benchmark natural language code generation from natural language commands extending beyond English by using a multilingual dataset. |
| Outcome: | The proposed dataset compares natural language commands with code generation systems in three languages. |