arXiv research

Locally-contextual CRFs improve sequence labeling performance.

Predict stock movement with news headlines using BERT embeddings.

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in contex…

CAEL-MIPS learns embeddings to improve MIPS for better OPE in contextual bandits.

Faster, context-aware topic modeling approach unveiled.

SLiCE learns contextual node embeddings for link prediction in heterogeneous networks.

SCNode improves node embeddings for GNNs in both homophilic and heterophilic graphs.

Study examines biases in clinical word embeddings, revealing performance gaps across groups.

Method learns audio embeddings with contextualized tags.

New algorithm tackles dynamic query routing to multiple embedding models.

BERT embeddings improve sequence quality metrics.

New approach combines semi-supervised learning and bandits for better predictions.

This paper explores the complexity of learning representations in contextual linear bandits.

IITK wins FinSim 2020 task on financial hypernym detection.

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine recommendations, e.g. when a user specifies a price range or product category filter. …

BERTopic improves financial text analysis with FinTextSim's contextual embeddings.

This paper introduces a new task to better understand Transformers in quantitative contexts.

Novel approach to contextual bandits using self-supervised learning.

Models use embeddings and attention for better claim severity prediction.

MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Lis…

New OPE estimator improves offline policy evaluation for large action spaces.

LaT-PFN model predicts time series with zero-shot capability.

Contemporary debates on filter bubbles and polarization in public and social media raise the question to what extent news media of the past exhibited biases. This paper specifically examines bias related to gender in six Dutch national newspapers between 1950 and 1990. We measure bias related to gender by comparing loc…

A new linear contextual bandit algorithm with improved regret bound.

The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to s…

SARD improves deep learning clinical prediction performance.

Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attent…

Contextualizing financial news improves stock price predictions.

Trip recommendation is an important location-based service that helps relieve users from the time and efforts for trip planning. It aims to recommend a sequence of places of interest (POIs) for a user to visit that maximizes the user's satisfaction. When adding a POI to a recommended trip, it is essential to understand…

Improves topic modeling using LLM embeddings and Poisson process.

Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as clustering similar words and inferring learning relationships, many challenges …

Proposes MDR estimator for unbiased OPE with large action spaces.

We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allowing for language specific parameterization, and that can also be used for domain adaptation. Our approach requires no changes to the model a…

Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different co…

AEALT uses autoencoders to reduce text embedding dimensions for improved efficiency.

Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an entirely unsupervised manner using a contextual window and doing so much faster th…

We consider the problem of developing suitable learning representations (embeddings) for library packages that capture semantic similarity among libraries. Such representations are known to improve the performance of downstream learning tasks (e.g. classification) or applications such as contextual search and analogica…

MBExplainer provides explanations for models combining graph embeddings and tabular features.

GICDM corrects hubness in embedding spaces for better generative model evaluation.

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are cru…

Paper introduces G-LowTESTR for efficient tensor bandits.

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically …

Model predicts political ideology using context vectors to mitigate bias and scarcity.

Contextualized ML learns context-dependent effects using deep learning.

IDS improves reinforcement learning with contextual information.

A framework converts spatial data into embeddings for insurance risk modelling.

SADCBO optimizes contextual variables by balancing relevance and cost.