Related papers: Automated Concatenation of Embeddings for Structur…

Recent recommender systems increasingly leverage embeddings from large pre-trained language models (PLMs). However, such embeddings exhibit two key limitations: (1) PLMs are not explicitly optimized to produce structured and discriminative…

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…

Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our…

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…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps…

Nowadays, search engine users commonly rely on query suggestions to improve their initial inputs. Current systems are very good at recommending lexical adaptations or spelling corrections to users' queries. However, they often struggle to…

Multi-agent systems must decide which agent is the most appropriate for a given task. We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by extending the…

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their…

Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration, assistive robotics, and autonomous navigation. However,…

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association…

Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as search, matching, and…

Word2vec is one of the most used algorithms to generate word embeddings because of a good mix of efficiency, quality of the generated representations and cognitive grounding. However, word meaning is not static and depends on the context in…

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

Large pre-trained models (LMs) and Large Language Models (LLMs) are typically effective at capturing language semantics and contextual relationships. However, these models encounter challenges in maintaining optimal performance on tasks…

We suggest a model for metaphor interpretation using word embeddings trained over a relatively large corpus. Our system handles nominal metaphors, like "time is money". It generates a ranked list of potential interpretations of given…

Today's densely instrumented world offers tremendous opportunities for continuous acquisition and analysis of multimodal sensor data providing temporal characterization of an individual's behaviors. Is it possible to efficiently couple such…