Related papers: Imposing Label-Relational Inductive Bias for Extre…

Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…

Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. However, the latent…

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However,…

Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching. Various graph convolutional…

The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including tabular data, facilitated by serialization methods. However,…

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…

Labeling datasets is a noteworthy challenge in machine learning, both in terms of cost and time. This research, however, leverages an efficient answer. By exploring label propagation in semi-supervised learning, we can significantly reduce…

Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks. This vulnerability is aggravated in distillation, where a student model may have lesser representational capacity than the…

Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to…

Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph, including the target…

Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retraining. Predicting links in a KG faces the challenge of…

Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes…

We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining. The…

Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods. However, only qualitative analysis and ablation study are provided as evidence. In…

A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very…

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

Inductive knowledge graph completion has been considered as the task of predicting missing triplets between new entities that are not observed during training. While most inductive knowledge graph completion methods assume that all entities…