相关论文: Mix-and-Match: Scalable Dialog Response Retrieval …

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint…

Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augmentation strategy for training small language models (sLMs) to perform topic-controlled…

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch…

Modelling how concepts are related is a central topic in Lexical Semantics. A common strategy is to rely on knowledge graphs (KGs) such as ConceptNet, and to model the relation between two concepts as a set of paths. However, KGs are…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Many applications need access to background knowledge about how different concepts and entities are related. Although Knowledge Graphs (KG) and Large Language Models (LLM) can address this need to some extent, KGs are inevitably incomplete…

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively…

We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks. Our results suggest that while intrinsic tasks…

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…

Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this task. The sequence…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

Relation extraction task is a crucial and challenging aspect of Natural Language Processing. Several methods have surfaced as of late, exhibiting notable performance in addressing the task; however, most of these approaches rely on vast…

Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion…

We present a multi-modal dialog system to assist online shoppers in visually browsing through large catalogs. Visual browsing is different from visual search in that it allows the user to explore the wide range of products in a catalog,…

The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a ranking problem and learn a shared multi-modal embedding…

Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to…

Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally due to catastrophic forgetting. Existing approaches rely on experience replay, optimization…

Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial…