Model

This sentence-transformers model model was obtained by fine-tuning bert-base-cased on the ClaimRev dataset.

Paper: Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale Authors: Gabriella Skitalinskaya, Jonas Klaff, Henning Wachsmuth

Claim Quality Classification

We cast this task as a pairwise classification task, where the objective is to compare two versions of the same claim and determine which one is better. We train this model by fine-tuning SBERT based on bert-base-cased using a siamese network structure with softmax loss. Outputs can also be used to rank multiple versions of the same claim, for example, using SVMRank or BTL (Bradley-Terry-Luce model).

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('gabski/sbert-relative-claim-quality')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('gabski/sbert-relative-claim-quality')
model = AutoModel.from_pretrained('gabski/sbert-relative-claim-quality')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

@inproceedings{skitalinskaya-etal-2021-learning,
    title = "Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale",
    author = "Skitalinskaya, Gabriella  and
      Klaff, Jonas  and
      Wachsmuth, Henning",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-main.147",
    doi = "10.18653/v1/2021.eacl-main.147",
    pages = "1718--1729",
}