Related papers: Modeling Sequential Sentence Relation to Improve C…

We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant potential in recommendation systems. However, the effective application of MLLMs to multimodal sequential recommendation remains unexplored: A)…

Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality, a loss of…

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known…

We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared BPE…

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or passage as a single mean-pooled…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on…

While (large) language models have significantly improved over the last years, they still struggle to sensibly process long sequences found, e.g., in books, due to the quadratic scaling of the underlying attention mechanism. To address…

Sequential recommender systems predict items that may interest users by modeling their preferences based on historical interactions. Traditional sequential recommendation methods rely on capturing implicit collaborative filtering signals…

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence separately, our proposed framework utilizes both sequences…

We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment…

Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning…

Sequential sentence classification (SSC) in scientific publications is crucial for supporting downstream tasks such as fine-grained information retrieval and extractive summarization. However, current SSC methods are constrained by model…

Existing technologies expand BERT from different perspectives, e.g. designing different pre-training tasks, different semantic granularities, and different model architectures. Few models consider expanding BERT from different text formats.…

Adapting language models (LMs) to novel domains is often achieved through fine-tuning a pre-trained LM (PLM) on domain-specific data. Fine-tuning introduces new knowledge into an LM, enabling it to comprehend and efficiently perform a…

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines…

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…