Related papers: EAVE: Efficient Product Attribute Value Extraction…
Product attribute value extraction plays an important role for many real-world applications in e-Commerce such as product search and recommendation. Previous methods treat it as a sequence labeling task that needs more annotation for…
Product attribute value extraction is a pivotal component in Natural Language Processing (NLP) and the contemporary e-commerce industry. The provision of precise product attribute values is fundamental in ensuring high-quality…
Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…
Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irrelevant variables often leads to overfitting. In an attempt…
Recent advances in computer vision and neural networks have made it possible for more surveillance videos to be automatically searched and analyzed by algorithms rather than humans. This happened in parallel with advances in edge computing…
Aspect Sentiment Triplet Extraction (ASTE) aims to recognize targets, their sentiment polarities and opinions explaining the sentiment from a sentence. ASTE could be naturally divided into 3 atom subtasks, namely target detection, opinion…
Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot…
Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…
The biomedical literature provides a rich source of knowledge such as protein-protein interactions (PPIs), drug-drug interactions (DDIs) and chemical-protein interactions (CPIs). Biomedical relation extraction aims to automatically extract…
Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…
Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features…
We introduce a new task called Defeasible Visual Entailment (DVE), where the goal is to allow the modification of the entailment relationship between an image premise and a text hypothesis based on an additional update. While this concept…
Hybrid recommendations have recently attracted a lot of attention where user features are utilized as auxiliary information to address the sparsity problem caused by insufficient user-item interactions. However, extracted user features…
Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI…
Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…
To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE.…
Recommender systems have been studied extensively due to their practical use in many real-world scenarios. Despite this, generating effective recommendations with sparse user ratings remains a challenge. Side information associated with…