This is the T5-3B model for System 3 DREAM-FLUTE (motivation), as described in our paper Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE, FigLang workshop @ EMNLP 2022 (Arxiv link: https://arxiv.org/abs/2210.16407)
Systems 3: DREAM-FLUTE - Providing DREAM’s different dimensions as input context
We adapt DREAM’s scene elaborations (Gu et al., 2022) for the figurative language understanding NLI task by using the DREAM model to generate elaborations for the premise and hypothesis separately. This allows us to investigate if similarities or differences in the scene elaborations for the premise and hypothesis will provide useful signals for entailment/contradiction label prediction and improving explanation quality. The input-output format is:
where the scene elaboration dimensions from DREAM are: consequence, emotion, motivation, and social norm. We also consider a system incorporating all these dimensions as additional context.
In this model, DREAM-FLUTE (motivation), we use elaborations along the "motivation" dimension. For more details on DREAM, please refer to DREAM: Improving Situational QA by First Elaborating the Situation, NAACL 2022 (Arxiv link: https://arxiv.org/abs/2112.08656, ACL Anthology link: https://aclanthology.org/2022.naacl-main.82/).
How to use this model?
We provide a quick example of how you can try out DREAM-FLUTE (motivation) in our paper with just a few lines of code:
>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> model = AutoModelForSeq2SeqLM.from_pretrained("allenai/System3_DREAM_FLUTE_motivation_FigLang2022")
>>> tokenizer = AutoTokenizer.from_pretrained("t5-3b")
>>> input_string = "Premise: After years of service and contribution to the company, he was finally promoted. [Premise - motivation] Company's motivation is to recognize his hard work. Hypothesis: The company released him after many years of service. [Hypothesis - motivation] Company's motivation is to get someone else to work. Is there a contradiction or entailment between the premise and hypothesis?"
>>> input_ids = tokenizer.encode(input_string, return_tensors="pt")
>>> output = model.generate(input_ids, max_length=200)
>>> tokenizer.batch_decode(output, skip_special_tokens=True)
['Answer : Contradiction. Explanation : To release someone means to let them go from a position, while to promote someone means to give them a higher position.']
More details about DREAM-FLUTE ...
For more details about DREAM-FLUTE, please refer to our:
This model is part of our DREAM-series of works. This is a line of research where we make use of scene elaboration for building a "mental model" of situation given in text. Check out our GitHub Repo for more!
