metadata

language: en
widget:
  - text: 'define \"dread\": The overwhelming amount of filled him with dread'

T5-define

(This model is still a work in progress. If you use it for fine tuning, make sure to save a local copy)

This model is trained to generate word definitions based on the word and a context, using a subset of wordnet for all words that have an example and definition. The model uses task prompts on the format 'define "[word]": [example sentence]'

To my knowledge, this is the first public model trained on a word definition task. Similar work: Zero-shot Word Sense Disambiguation using Sense Definition Embeddings

For this project, there are two objectives:

Explore generalizability on generating word definitions for unseen words
Explore the utility of word embeddings by definition models

How to run:

from transformers import T5ForConditionalGeneration, T5Tokenizer

tokenizer = T5Tokenizer.from_pretrained("marksverdhei/t5-base-define")
model = T5ForConditionalGeneration.from_pretrained("marksverdhei/t5-base-define")

prompt = "define \"noseplow\": The children hid as the noseplow drove across the street"

ids = tokenizer(prompt, return_tensors="pt").input_ids
generated_tokens = model.generate(ids)[0][1:-1]
tokenizer.decode(generated_tokens)