Related papers: UmBERTo-MTSA @ AcCompl-It: Improving Complexity an…

Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitting. Auxiliary tasks…

Although the annotation paradigm based on Large Language Models (LLMs) has made significant breakthroughs in recent years, its actual deployment still has two core bottlenecks: first, the cost of calling commercial APIs in large-scale…

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…

Recent work on few-shot learning \cite{tian2020rethinking} showed that quality of learned representations plays an important role in few-shot classification performance. On the other hand, the goal of self-supervised learning is to recover…

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

Deep learning has proven effective for various application tasks, but its applicability is limited by the reliance on annotated examples. Self-supervised learning has emerged as a promising direction to alleviate the supervision bottleneck,…

One of the most popular paradigms of applying large pre-trained NLP models such as BERT is to fine-tune it on a smaller dataset. However, one challenge remains as the fine-tuned model often overfits on smaller datasets. A symptom of this…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for…

Recently, sign language researchers have turned to sign language interpreted TV broadcasts, comprising (i) a video of continuous signing and (ii) subtitles corresponding to the audio content, as a readily available and large-scale source of…

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with…

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a…

Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of translating a sentence;…

State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…

Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach that leverages Large Language Model…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…