Papers by Qiyu Wu
Word Alignment as Preference for Machine Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Hallucination and omission are a problem in machine translation because of an LLM's size and low-resource languages. |
| Approach: | They propose to use word alignment as preference to optimize an LLM-based MT model to mitigate hallucination and omission problems. |
| Outcome: | The proposed model is able to mitigate hallucination and omission by using word alignment as preference. |
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent trends in learning monolingual and multilingual sentence embeddings are based on contrastive learning (CL) among an anchor, one positive and multiple negative instances. |
| Approach: | They propose to leverage multiple positives to improve learning of multilingual sentence embeddings by using an anchor, one positive, and multiple negative instances. |
| Outcome: | The proposed approach improves retrieval, semantic similarity, and classification performance on unseen languages. |
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learning sentence embeddings in unsupervised manner depend on mono-augmenting . existing approaches depend on augmenting biases and thus corrupt the quality of sentence embeds. |
| Approach: | They propose a method to augment a sentence with a semantically-close positive instance to construct contrastive pairs in unsupervised manner. |
| Outcome: | The proposed method improves performance on STS benchmarks and compares with existing methods. |
Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent MT metrics like xCOMET, Met-ricX, and Remedy have strong correlations with human preferences, but they are black boxes, revealing little insight into why a translation is good or bad. |
| Approach: | They propose a reasoning-driven generative MT metric trained with reinforcement learning from pairwise translation preferences without requiring error-span annotations or distillation from closed LLMs. |
| Outcome: | The proposed reasoning-driven generative MT metric produces step-by-step analyses of accuracy, fluency, and completeness, enabling more interpretable assessments. |
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing word alignment methods rely on manual data and lack generalization ability. |
| Approach: | They propose to use a weakly-supervised large-scale weakly supervised dataset for word alignment pre-training via span prediction to reduce the need for manual data. |
| Outcome: | The proposed method improves upon the best supervised baseline by 3.3 6.1 points in F1 and 1.5 6.1 point in AER. |
THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to risk prediction from EHRs handle structured diagnostic codes and unstructured narrative notes separately. |
| Approach: | They propose a Temporal-Hierarchical Causal Model with Conformal Calibration . they construct a multimodal causal graph where nodes represent clinical entities from two modalities . |
| Outcome: | The proposed model infers three clinically grounded interactions from textual propositions and ICD codes mapped to textual descriptions. |
DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in music large language models have significantly improved music understanding tasks, but the potential of incorporating additional modalities such as images, videos and textual music features remains unexplored. |
| Approach: | They propose a multimodal music understanding LLM fine-tuned via multi-way instruction tuning with multi-ways aligned music, text, image, and video data. |
| Outcome: | The proposed model achieves state-of-the-art performance across six music understanding tasks and zero-shot scenarios. |
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment (2024.findings-naacl)
Copied to clipboard
| Challenge: | Current approaches to obtain cross-lingual sentence embeddings rely on pre-trained language models that implicitly align the contextual representations of similar units of sentences in different languages. |
| Approach: | They propose a framework that explicitly aligns words between English and eight low-resource languages by using off-the-shelf word alignment models. |
| Outcome: | The proposed framework improves on the bitext retrieval task and in high-resource languages. |
Improving Word Alignment Using Semi-Supervised Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing word alignment methods rely on labeled data, but augmenting training with pseudo-labeled data improves performance. |
| Approach: | They propose a semi-supervised framework to improve word alignment methods . they use pseudo-labeled data from multilingual encoder models as word aligners . |
| Outcome: | The proposed framework outperforms the current state-of-the-art binary alignment method on word alignment datasets. |