Papers by Derry Wijaya
On Measuring Social Biases in Prompt-Based Multi-Task Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | a large body of work within prompt engineering attempts to understand the effects of input forms and prompts in achieving superior performance. |
| Approach: | They propose a large-scale text-to-text language model trained using prompts . they consider two different forms of semantically equivalent inputs - question-answer format and premise-hypothesis format . |
| Outcome: | The proposed model can generalize into novel forms of language and handle novel tasks. |
DUnE: Dataset for Unified Editing (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models are susceptible to errors necessitating a comprehensive retraining process. |
| Approach: | They propose to define an edit as any natural language expression that solicits a change in the model’s outputs. |
| Outcome: | The proposed editing benchmarks show that retrieval-augmented language modeling outperforms specialized editing techniques and neither set of approaches has fully solved the generalized editing problem covered by the proposed benchmark. |
Monitoring Hate Speech in Indonesia: An NLP-based Classification of Social Media Texts (2024.emnlp-demo)
Copied to clipboard
| Challenge: | a lack of mechanisms to track the spread and severity of hate speech complicates the formulation of effective solutions. |
| Approach: | They have developed a universally robust hate speech classifier tailored for a narrower subset of texts that target vulnerable groups that have historically been the targets of hate speech in Indonesia. |
| Outcome: | The proposed tool has persuaded the General Election Supervisory Body in Indonesia (BAWASLU) to collaborate with the Alliance of Independent Journalists (AJI) to monitor hate speech in vulnerable areas in the country known for hate speech dissemination or hate-related violence in the upcoming Indonesian regional elections. |
Better Quality Estimation for Low Resource Corpus Mining (2022.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art Quality Estimation models lack robustness to out-of domain examples. |
| Approach: | They propose a method that uses multitask training, data augmentation and contrastive learning to achieve better and more robust QE performance. |
| Outcome: | The proposed method improves QE performance significantly in the MLQE challenge and the robustness of QE models when tested in the Parallel Corpus Mining setup. |
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing language models (LMs) generate factually correct text and estimate truth values of individual claims, but they do not reflect a coherent, manipulable model of the world. |
| Approach: | They propose a method that uses language models to identify implications of (and contradictions within) the text they generate. |
| Outcome: | The proposed method improves LM factuality by 3-26% across the CREAK, MQuAKE, and Reversal Curse datasets. |
Explain-then-translate: an analysis on improving program translation with self-generated explanations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Using self-generated natural language explanations improves zero-shot performance by 12% on average. |
| Approach: | They propose to use self-generated natural language explanations as an intermediate step for code-to-code translation with language models. |
| Outcome: | The proposed approach improves zero-shot performance by 12% on average . the proposed approach is not evaluated on a broader set of languages including low-resource languages. |
COVID-19 Vaccine Misinformation in Middle Income Countries (2023.emnlp-main)
Copied to clipboard
| Challenge: | a multilingual dataset of COVID-19 vaccine misinformation is available from Brazil, Indonesia, and Nigeria. |
| Approach: | They propose to use a multilingual dataset of COVID-19 vaccine misinformation from Brazil, Indonesia, and Nigeria to assess their relevance to vaccines and the presence of misinformation. |
| Outcome: | The proposed models improve from 2.7 to 15.9 percentage points in macro F1-score compared to baseline models. |