Related papers: Syntactic and Semantic-driven Learning for Open In…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL methods typically rely on task-agnostic semantic similarity for…

Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their…

The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred…

We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

In-context learning (ICL) greatly improves the performance of large language models (LLMs) on various down-stream tasks, where the improvement highly depends on the quality of demonstrations. In this work, we introduce syntactic knowledge…

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual…

The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

In this paper, we propose SEA, a novel approach for active robot exploration through semantic map prediction and a reinforcement learning-based hierarchical exploration policy. Unlike existing learning-based methods that rely on one-step…

In stream-based active learning, the learning procedure typically has access to a stream of unlabeled data instances and must decide for each instance whether to label it and use it for training or to discard it. There are numerous active…

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE). Note that high-quality instruction data is the vital key for enhancing…

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…

Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to help later acquire another, such as the meanings of new words. Empirical results supporting both…

Instruction data is crucial for improving the capability of Large Language Models (LLMs) to align with human-level performance. Recent research LIMA demonstrates that alignment is essentially a process where the model adapts instructions'…

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…

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet. In consequence, we need curious and continuously learning algorithms that actively acquire knowledge…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…