Related papers: GASE: Generatively Augmented Sentence Encoding

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1)…

Data augmentation can mitigate limited training data in machine-learning automated scoring engines for constructed response items. This study seeks to determine how well three approaches to large language model prompting produce essays that…

Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost. Annotating and gathering utterance relationships in…

Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pairs can boost…

This paper investigates techniques for knowledge injection into word embeddings learned from large corpora of unannotated data. These representations are trained with word cooccurrence statistics and do not commonly exploit syntactic and…

Generative adversarial networks (GANs) have made remarkable achievements in synthesizing images in recent years. Typically, training GANs requires massive data, and the performance of GANs deteriorates significantly when training data is…

We study sequence-to-sequence (seq2seq) pre-training with data augmentation for sentence rewriting. Instead of training a seq2seq model with gold training data and augmented data simultaneously, we separate them to train in different…

Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend and domain-related, so completely explaining the phenomenon by linguistic rules is challenging. Compared to most monolingual tasks,…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…

Recent progress in sentence embedding, which represents the meaning of a sentence as a point in a vector space, has achieved high performance on tasks such as a semantic textual similarity (STS) task. However, sentence representations as a…

Recent techniques in Question Answering (QA) have gained remarkable performance improvement with some QA models even surpassed human performance. However, the ability of these models in truly understanding the language still remains dubious…

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…

Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many applications, e.g., retrieval augmented generation (RAG),…

We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning. In line with recent advancements in unifying various NLP tasks into a single format, we train a unified text embedding model by employing…

Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…