Related papers: Snippext: Semi-supervised Opinion Mining with Augm…

Opinion mining and Sentiment analysis have emerged as a field of study since the widespread of World Wide Web and internet. Opinion refers to extraction of those lines or phrase in the raw and huge data which express an opinion. Sentiment…

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…

Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not…

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

We propose InsightNet, a novel approach for the automated extraction of structured insights from customer reviews. Our end-to-end machine learning framework is designed to overcome the limitations of current solutions, including the absence…

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pre-trained on two…

Data augmentation is a widely used strategy for training robust machine learning models. It partially alleviates the problem of limited data for tasks like speech emotion recognition (SER), where collecting data is expensive and…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Semi-supervised few-shot learning (SSFSL) formulates real-world applications like ''auto-annotation'', as it aims to learn a model over a few labeled and abundant unlabeled examples to annotate the unlabeled ones. Despite the availability…

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task which aims to extract the aspects from sentences and identify their corresponding sentiments. Aspect term extraction (ATE) is the crucial step for ABSA. Due to…

Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data. In this paper, we explore whether we…

State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling. During pseudo-labeling,…

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of…

In this paper, we investigate the usage of autoencoders in modeling textual data. Traditional autoencoders suffer from at least two aspects: scalability with the high dimensionality of vocabulary size and dealing with task-irrelevant words.…

Applications that learn from opinionated documents, like tweets or product reviews, face two challenges. First, the opinionated documents constitute an evolving stream, where both the author's attitude and the vocabulary itself may change.…

Software analytics often builds from labeled data. Labeling can be slow, error prone, and expensive. When human expertise is scarce, SE researchers sometimes ask large language models (LLMs) for the missing labels. While this has been…

Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment…