Related papers: WSPAlign: Word Alignment Pre-training via Large-Sc…

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…

Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We take a step forward in this direction by borrowing from…

Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational…

Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is…

Supervised approaches for Neural Abstractive Summarization require large annotated corpora that are costly to build. We present a French meeting summarization task where reports are predicted based on the automatic transcription of the…

Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…

We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method that improves the efficiency of VLMs. Unlike MetaCLIP, our method does not need metadata for pruning, but selects text-image pairs to prune based on…

Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages. Current unsupervised…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…

The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we first introduce a…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an…

We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching. Our approach directly supervises the dense matching scores predicted by the network, encoded as a conditional probability distribution.…

We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is possible to infer such lexicon, without…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

There is an increasing interest in obtaining accurate word-level timestamps from strong automatic speech recognizers, in particular Whisper. Existing approaches either require additional training or are simply not competitive. The…