Related papers: Structured Tuning for Semantic Role Labeling

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance. Existing attentive models attend to all words without…

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the…

The goal of semantic role labeling (SRL) is to discover the predicate-argument structure of a sentence, which plays a critical role in deep processing of natural language. This paper introduces simple yet effective auxiliary tags for…

We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuning leverages the…

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:…

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

Many efforts of research are devoted to semantic role labeling (SRL) which is crucial for natural language understanding. Supervised approaches have achieved impressing performances when large-scale corpora are available for resource-rich…

Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when performing fine-grained visual editing. We introduce a…

Semantic role labeling (SRL) is a crucial task of natural language processing (NLP). Although generative decoder-based large language models (LLMs) have achieved remarkable success across various NLP tasks, they still lag behind…

The latest developments in neural semantic role labeling (SRL) have shown great performance improvements with both the dependency and span formalisms/styles. Although the two styles share many similarities in linguistic meaning and…

With the rapid development of online advertising and recommendation systems, click-through rate prediction is expected to play an increasingly important role.Recently many DNN-based models which follow a similar Embedding&MLP paradigm have…

Semantic role labeling (SRL) aims to discover the predicateargument structure of a sentence. End-to-end SRL without syntactic input has received great attention. However, most of them focus on either span-based or dependency-based semantic…

This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance…

Language model pre-training and derived methods are incredibly impactful in machine learning. However, there remains considerable uncertainty on exactly why pre-training helps improve performance for fine-tuning tasks. This is especially…

We propose structured prompt tuning, a simple and effective method to improve prompt tuning. Instead of prepending a sequence of tunable embeddings to the input, we generate the soft prompt embeddings through a hypernetwork. Our approach…

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…

End-to-end semantic role labeling (SRL) has been received increasing interest. It performs the two subtasks of SRL: predicate identification and argument role labeling, jointly. Recent work is mostly focused on graph-based neural models,…

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…

We explore a novel approach for Semantic Role Labeling (SRL) by casting it as a sequence-to-sequence process. We employ an attention-based model enriched with a copying mechanism to ensure faithful regeneration of the input sequence, while…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…