Related papers: Minimally Supervised Hierarchical Domain Intent Le…

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification.…

Recent advance in Dense Retrieval (DR) techniques has significantly improved the effectiveness of first-stage retrieval. Trained with large-scale supervised data, DR models can encode queries and documents into a low-dimensional dense space…

Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA…

Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practical failures often stem from the lack of mechanisms to…

While the depth of modern Convolutional Neural Networks (CNNs) surpasses that of the pioneering networks with a significant margin, the traditional way of appending supervision only over the final classifier and progressively propagating…

Recommendation systems aim to assist users to discover most preferred contents from an ever-growing corpus of items. Although recommenders have been greatly improved by deep learning, they still faces several challenges: (1) Behaviors are…

The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the…

Bootstrapping natural language understanding (NLU) systems with minimal training data is a fundamental challenge of extending digital assistants like Alexa and Siri to a new language. A common approach that is adapted in digital assistants…

Constrained clustering is a semi-supervised task that employs a limited amount of labelled data, formulated as constraints, to incorporate domain-specific knowledge and to significantly improve clustering accuracy. Previous work has…

In Natural Language Processing (NLP), predicting linguistic structures, such as parsing and chunking, has mostly relied on manual annotations of syntactic structures. This paper introduces an unsupervised approach to chunking, a syntactic…

Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden,…

In this paper, we report on domain clustering in the ambit of an adaptive MT architecture. A standard bottom-up hierarchical clustering algorithm has been instantiated with five different distances, which have been compared, on an MT…

This paper presents a deployed, production-grade system designed to enhance and scale search query datasets for intent-based recommendation systems in digital banking. In real-world environments, the growing volume and complexity of user…

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open…

Climate change, population growth, and water scarcity present unprecedented challenges for agriculture. This project aims to forecast soil moisture using domain knowledge and machine learning for crop management decisions that enable…

We propose a nearest neighbor based clustering algorithm that results in a naturally defined hierarchy of clusters. In contrast to the agglomerative and divisive hierarchical clustering algorithms, our approach is not dependent on the…

We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings.…

Retrieval, the initial stage of a recommendation system, is tasked with down-selecting items from a pool of tens of millions of candidates to a few thousands. Embedding Based Retrieval (EBR) has been a typical choice for this problem,…

With recent advancements in language technologies, humans are now speaking to devices. Increasing the reach of spoken language technologies requires building systems in local languages. A major bottleneck here are the underlying…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…