Related papers: CoLLEGe: Concept Embedding Generation for Large La…

This paper presents CoLLIE: a simple, yet effective model for continual learning of how language is grounded in vision. Given a pre-trained multimodal embedding model, where language and images are projected in the same semantic space (in…

While the embedding of words has revolutionized the field of Natural Language Processing, the embedding of concepts has received much less attention so far. A dense and meaningful representation of concepts, however, could prove useful for…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…

Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source…

In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…

Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models. However, existing benchmarks for constrained generation usually…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Word embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data.…

Humans can quickly learn a new word from a few illustrative examples, and then systematically and flexibly use it in novel contexts. Yet the abilities of current language models for few-shot word learning, and methods for improving these…

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

In this work, we study the problem of data retrieval for few-shot imitation learning: selecting data from a large dataset to train a performant policy for a specific task, given only a few target demonstrations. Prior methods retrieve data…

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be…

Lexical semantics is concerned with both the multiple senses a word can adopt in different contexts, and the semantic relations that exist between meanings of different words. To investigate them, Contextualized Language Models are a…

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Pre-trained language models (PLMs) have been prevailing in state-of-the-art methods for natural language processing, and knowledge-enhanced PLMs are further proposed to promote model performance in knowledge-intensive tasks. However,…

Word embeddings induced from local context are prevalent in NLP. A simple and effective context-based multilingual embedding learner is Levy et al. (2017)'s S-ID (sentence ID) method. Another line of work induces high-performing…