Code implementation of paper Semantic Role Labeling with Associated Memory Network (NAACL 2019)
-
Updated
Aug 5, 2019 - Python
Code implementation of paper Semantic Role Labeling with Associated Memory Network (NAACL 2019)
A study on Knowledge-based question generation from images. Undergraduate Thesis for 2023-2024.
BERT-based FrameNet-SRL Extraction pipeline
VELOCITI Benchmark Evaluation and Visualisation Code
WikiBank is a new partially annotated resource for multilingual frame-semantic parsing task.
For SRL the task is to learn and predict the predicate – arguments structure of a sentence. My solution is a deep learning model which uses contextualized word embeddings and bi-affine attention mechanism.
Proposition Extraction based on Semantic Role Labeling, with an interface to navigate results (LREC 2016)
Collection of scripts used to create SRL datasets for Galician and Spanish using a verbal indexing method, as well as fine-tuned BERT and XLM-R models for SRL on each language
Code for ACL 2019 paper "How to best use Syntax in Semantic Role Labelling"
Probing for Predicate Argument Structures in Pretrained Language Models (ACL 2022).
Semantic Role Labeling project with 88.8% F1-score on English, 77.04% on French and 78.68% on Spanish. The dataset used in this task is the UniteD-SRL dataset. I developed it in Pytorch using Transformers, BiLSTMs and pos embeddings.
Grounded language Understanding via Transformers in Human Robot Interaction
Official Implementation of Paper "A Novel Metric for Evaluating Semantics Preservation"
A tool used to generate questions from lecture transcripts using template extraction from sample questions asked by real students. Performed using SRL.
An SRL-based approach to factuality estimation for text summarization
Code for "Mehta, S. V.*, Lee, J. Y.*, and Carbonell, J. (2018). Towards Semi-Supervised Learning for Deep Semantic Role Labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 4958-4963).
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).
Methods for extracting Within-Document(WD) and Semantic-Role-Labeling(SRL) information from already tokenized corpus
Code and models for the COLING2020 paper "Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach".
Code for the AAAI 2021 work End-to-end Semantic Role Labeling with Neural Transition-based Model
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."