A very simple framework for state-of-the-art Natural Language Processing (NLP)
-
Updated
Aug 25, 2024 - Python
A very simple framework for state-of-the-art Natural Language Processing (NLP)
基于Pytorch和torchtext的知识图谱深度学习框架。
A neural network architecture for NLP tasks, using cython for fast performance. Currently, it can perform POS tagging, SRL and dependency parsing.
Deep Semantic Role Labeling with Self-Attention
Astock
Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.
Collection of papers on Emotion Cause Analysis
[COLING'22] Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".
Natural Language Parsing and Feature Generation
VerbNet semantic parser and related utilities
The Mingled Structured Predictor
Scripts for preprocessing the CoNLL-2005 SRL dataset.
SRL deep learning model is based on DB-LSTM which is described in this paper : [End-to-end learning of semantic role labeling using recurrent neural networks](https://www.aclweb.org/anthology/P15-1109)
*SEM 2018: Learning Distributed Event Representations with a Multi-Task Approach
A Structured Span Selector (NAACL 2022). A structured span selector with a WCFG for span selection tasks (coreference resolution, semantic role labelling, etc.)
Sequence Labeling in Tensorflow
GSRL is a seq2seq model for end-to-end dependency- and span-based SRL (IJCAI2021).
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).
A semantic role labeling system for the Sumerian language. A Google Summer of Code '18 initiative.
BERT-based nominal Semantic Role Labeling (SRL), both using the Nombank dataset and the Ontonotes dataset.
Add a description, image, and links to the semantic-role-labeling topic page so that developers can more easily learn about it.
To associate your repository with the semantic-role-labeling topic, visit your repo's landing page and select "manage topics."