sentence_similarity_semantic_search

Dataset Collection:

• The news dataset is collected from Kaggledataset
• The dataset has news title ,news content and the label(the label shows the cosine similarity between news title and news content).
• Different strategies have been followed during the data gathering phase.

sentence transformer is fine-tuned for semantic search and sentence similarity

• The model is fine-tuned on the dataset.
• This model can be used for semantic search,sentence similarity,recommendation system.
• This model can be used for the inference purpose as well.

Data Fields:

label: cosine similarity between news title and news content news title: The title of the news news content:The content of the news

Application:

• This model is useful for the semantic search,sentence similarity,recommendation system.
• You can fine-tune this model for your particular use cases.

Model Implementation

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer, InputExample, losses
import pandas as pd
from sentence_transformers import SentenceTransformer, InputExample
from torch.utils.data import DataLoader
from sentence_transformers import SentenceTransformer, util

model_name="Sakil/sentence_similarity_semantic_search"
model = SentenceTransformer(model_name)
sentences = ['A man is eating food.',
          'A man is eating a piece of bread.',
          'The girl is carrying a baby.',
          'A man is riding a horse.',
          'A woman is playing violin.',
          'Two men pushed carts through the woods.',
          'A man is riding a white horse on an enclosed ground.',
          'A monkey is playing drums.',
          'Someone in a gorilla costume is playing a set of drums.'
          ]

#Encode all sentences
embeddings = model.encode(sentences)

#Compute cosine similarity between all pairs
cos_sim = util.cos_sim(embeddings, embeddings)

#Add all pairs to a list with their cosine similarity score
all_sentence_combinations = []

for i in range(len(cos_sim)-1):

    for j in range(i+1, len(cos_sim)):
    
        all_sentence_combinations.append([cos_sim[i][j], i, j])

#Sort list by the highest cosine similarity score

all_sentence_combinations = sorted(all_sentence_combinations, key=lambda x: x[0], reverse=True)

print("Top-5 most similar pairs:")

for score, i, j in all_sentence_combinations[0:5]:

    print("{} \t {} \t {:.4f}".format(sentences[i], sentences[j], cos_sim[i][j]))

Github: Sakil Ansari