Related papers: Template-assisted Contrastive Learning of Task-ori…
Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences…
This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-the-art sentence…
Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…
Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a…
We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…
Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the…
We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also…
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…
In this paper, we introduce the task of learning unsupervised dialogue embeddings. Trivial approaches such as combining pre-trained word or sentence embeddings and encoding through pre-trained language models (PLMs) have been shown to be…
Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…
Contrastive learning is widely used for sentence representation learning. Despite this prevalence, most studies have focused exclusively on English and few concern domain adaptation for domain-specific downstream tasks, especially for…
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only…
Adaptive scaffolding enhances learning, yet the field lacks robust methods for measuring it within authentic tutoring dialogue. This gap has become more pressing with the rise of remote human tutoring and large language model-based systems.…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence…