Related papers: Sequence-to-sequence Pre-training with Data Augmen…

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned on both a short…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity…

This paper presents our system developed for the SemEval-2025 Task 9: The Food Hazard Detection Challenge. The shared task's objective is to evaluate explainable classification systems for classifying hazards and products in two levels of…

Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring…

Recently, significant improvements have been achieved in various natural language processing tasks using neural sequence-to-sequence models. While aiming for the best generation quality is important, ultimately it is also necessary to…

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate data augmentation techniques for supervised deep…

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results…

Data Augmentation through generating pseudo data has been proven effective in mitigating the challenge of data scarcity in the field of Grammatical Error Correction (GEC). Various augmentation strategies have been widely explored, most of…

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models. This paper presents a novel data augmentation technique to…

Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Text-to-video (T2V) generation has gained significant attention recently. However, the costs of training a T2V model from scratch remain persistently high, and there is considerable room for improving the generation performance, especially…

We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies…

Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by…

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

To build a French national electronic injury surveillance system based on emergency room visits, we aim to develop a coding system to classify their causes from clinical notes in free-text. Supervised learning techniques have shown good…