Related papers: A Multi-Resolution Word Embedding for Document Ret…
Word embeddings capture syntactic and semantic information about words. Definition modeling aims to make the semantic content in each embedding explicit, by outputting a natural language definition based on the embedding. However, existing…
Visual-semantic embedding aims to learn a joint embedding space where related video and sentence instances are located close to each other. Most existing methods put instances in a single embedding space. However, they struggle to embed…
Retrieval-augmented generation (RAG) is a common way to ground language models in external documents and up-to-date information. Classical retrieval systems relied on lexical methods such as BM25, which rank documents by term overlap with…
Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…
We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…
Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations…
In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of…
Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This…
In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…
This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…
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…
Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the…
Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to…
Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…
Reference resolution, which aims to identify entities being referred to by a speaker, is more complex in real world settings: new referents may be created by processes the agents engage in and/or be salient only because they belong to the…
Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired…
Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching. In this paper, we study the advantages of probabilistic embeddings in a cross-modal setting (i.e., text and images),…
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…
Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for large collections due to its labor-intensive and…
Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…