Semantic Role Labeling

132 papers with code • 7 benchmarks • 14 datasets

Semantic role labeling aims to model the predicate-argument structure of a sentence and is often described as answering "Who did what to whom". BIO notation is typically used for semantic role labeling.

Example:

Housing starts are expected to quicken a bit from August’s pace
B-ARG1 I-ARG1 O O O V B-ARG2 I-ARG2 B-ARG3 I-ARG3 I-ARG3

Latest papers with no code

AMR Parsing with Instruction Fine-tuned Pre-trained Language Models

no code yet • 24 Apr 2023

Instruction fine-tuned language models on a collection of instruction annotated datasets (FLAN) have shown highly effective to improve model performance and generalization to unseen tasks.

Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning

no code yet • 27 Mar 2023

In this study, we present a novel dataset of two million culinary recipes labeled in respective categories leveraging the knowledge of food experts and an active learning technique.

Automatic Generation of Multiple-Choice Questions

no code yet • 25 Mar 2023

Moreover, we present a novel approach to automatically generate adequate distractors for a given QAP.

Friend-training: Learning from Models of Different but Related Tasks

no code yet • 31 Jan 2023

Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes.

Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?

no code yet • 26 Jan 2023

A common problem associated with meme comprehension lies in detecting the entities referenced and characterizing the role of each of these entities.

Experiencer-Specific Emotion and Appraisal Prediction

no code yet • 21 Oct 2022

Emotion classification in NLP assigns emotions to texts, such as sentences or paragraphs.

Tag-Set-Sequence Learning for Generating Question-Answer Pairs

no code yet • 20 Oct 2022

Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts.

Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

no code yet • 6 Oct 2022

In this work, we investigate the integration of a latent graph for CSRL.

Heterogeneous Line Graph Transformer for Math Word Problems

no code yet • 11 Aug 2022

We originally planned to employ existing models but realized that they processed a math word problem as a sequence or a homogeneous graph of tokens.

Fast and Accurate Span-based Semantic Role Labeling as Graph Parsing

no code yet • ACL ARR January 2022

Currently, BIO-based and Tuple-based approaches perform quite well on the span-based semantic role labeling (SRL) task.