Machine Translation Digest for Sep 14 2025
Here is today's selection of cs.CL papers exploring advancements in transformer models and their applications. The common themes include improving language models for specific tasks such as coreference resolution and relation classification, as well as enhancing performance in specialized domains like biomedical information extraction and Arabic clinical question answering through innovative strategies like adversarial training and prompt engineering.
Improving LLMs' Learning for Coreference Resolution
Coreference Resolution (CR) is crucial for many NLP tasks, but existing LLMs struggle with hallucination and under-performance. In this paper, we investigate the limitations of existing LLM-based approaches to CR-specifically the Question-Answering (QA) Template and Document Template methods and propose two novel techniques: Reversed Training with Joint Inference and Iterative Document Generation. Our experiments show that Reversed Training improves the QA Template method, while Iterative Document Generation eliminates hallucinations in the generated source text and boosts coreference resolution. Integrating these methods and techniques offers an effective and robust solution to LLM-based coreference resolution.
Transformer Enhanced Relation Classification: A Comparative Analysis of Contextuality, Data Efficiency and Sequence Complexity
In the era of large language model, relation extraction (RE) plays an important role in information extraction through the transformation of unstructured raw text into structured data (Wadhwa et al., 2023). In this paper, we systematically compare the performance of deep supervised learning approaches without transformers and those with transformers. We used a series of non-transformer architectures such as PA-LSTM(Zhang et al., 2017), C-GCN(Zhang et al., 2018), and AGGCN(attention guide GCN)(Guo et al., 2019), and a series of transformer architectures such as BERT, RoBERTa, and R-BERT(Wu and He, 2019). Our comparison included traditional metrics like micro F1, as well as evaluations in different scenarios, varying sentence lengths, and different percentages of the dataset for training. Our experiments were conducted on TACRED, TACREV, and RE-TACRED. The results show that transformer-based models outperform non-transformer models, achieving micro F1 scores of 80-90% compared to 64-67% for non-transformer models. Additionally, we briefly review the research journey in supervised relation classification and discuss the role and current status of large language models (LLMs) in relation extraction.
!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning
We present our systems for Track 2 (General Arabic Health QA, MedArabiQ) of the AraHealthQA-2025 shared task, where our methodology secured 2nd place in both Sub-Task 1 (multiple-choice question answering) and Sub-Task 2 (open-ended question answering) in Arabic clinical contexts. For Sub-Task 1, we leverage the Gemini 2.5 Flash model with few-shot prompting, dataset preprocessing, and an ensemble of three prompt configurations to improve classification accuracy on standard, biased, and fill-in-the-blank questions. For Sub-Task 2, we employ a unified prompt with the same model, incorporating role-playing as an Arabic medical expert, few-shot examples, and post-processing to generate concise responses across fill-in-the-blank, patient-doctor Q&A, GEC, and paraphrased variants.
RanAT4BIE: Random Adversarial Training for Biomedical Information Extraction
We introduce random adversarial training (RAT), a novel framework successfully applied to biomedical information extraction (BioIE) tasks. Building on PubMedBERT as the foundational architecture, our study first validates the effectiveness of conventional adversarial training in enhancing pre-trained language models' performance on BioIE tasks. While adversarial training yields significant improvements across various performance metrics, it also introduces considerable computational overhead. To address this limitation, we propose RAT as an efficiency solution for biomedical information extraction. This framework strategically integrates random sampling mechanisms with adversarial training principles, achieving dual objectives: enhanced model generalization and robustness while significantly reducing computational costs. Through comprehensive evaluations, RAT demonstrates superior performance compared to baseline models in BioIE tasks. The results highlight RAT's potential as a transformative framework for biomedical natural language processing, offering a balanced solution to the model performance and computational efficiency.
FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs
Speech tokenization enables discrete representation and facilitates speech language modeling. However, existing neural codecs capture low-level acoustic features, overlooking the semantic and contextual cues inherent to human speech. While recent efforts introduced semantic representations from self-supervised speech models or incorporated contextual representations from pre-trained language models, challenges remain in aligning and unifying the semantic and contextual representations. We introduce FuseCodec, which unifies acoustic, semantic, and contextual representations through strong cross-modal alignment and globally informed supervision. We propose three complementary techniques: (i) Latent Representation Fusion, integrating semantic and contextual features directly into the encoder latent space for robust and unified representation learning; (ii) Global Semantic-Contextual Supervision, supervising discrete tokens with globally pooled and broadcasted representations to enhance temporal consistency and cross-modal alignment; and (iii) Temporally Aligned Contextual Supervision, strengthening alignment by dynamically matching contextual and speech tokens within a local window for fine-grained token-level supervision. We further introduce FuseCodec-TTS, demonstrating our methodology's applicability to zero-shot speech synthesis. Empirically, FuseCodec achieves state-of-the-art performance in LibriSpeech, surpassing EnCodec, SpeechTokenizer, and DAC in transcription accuracy, perceptual quality, intelligibility, and speaker similarity. Results highlight the effectiveness of contextually and semantically guided tokenization for speech tokenization and downstream tasks. Code and pretrained models are available at https://github.com/mubtasimahasan/FuseCodec.
| Curated by yukajii.com |