Semantic Textual Similarity
560 papers with code • 13 benchmarks • 17 datasets
Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.
Image source: Learning Semantic Textual Similarity from Conversations
Benchmarks
These leaderboards are used to track progress in Semantic Textual Similarity
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Semantic Textual Similarity models and implementations
GLUE
MRPC
SICK
SentEval
CARER
MTEB
STS Benchmark
EVALution
Most implemented papers
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
The scalability of Nystr\"{o}mformer enables application to longer sequences with thousands of tokens.
MedSTS: A Resource for Clinical Semantic Textual Similarity
A subset of MedSTS (MedSTS_ann) containing 1, 068 sentence pairs was annotated by two medical experts with semantic similarity scores of 0-5 (low to high similarity).
Q8BERT: Quantized 8Bit BERT
NervanaSystems/nlp-architect
•
•
Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks.
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
tensorflow/models
•
•
ACL 2020
Then, we conduct knowledge transfer from this teacher to MobileBERT.
RealFormer: Transformer Likes Residual Attention
google-research/google-research
•
•
Findings (ACL) 2021
Transformer is the backbone of modern NLP models.
Calculating the similarity between words and sentences using a lexical database and corpus statistics
To calculate the semantic similarity between words and sentences, the proposed method follows an edge-based approach using a lexical database.
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
facebookresearch/SentEval
•
•
ICLR 2018
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
huggingface/transformers
•
•
EMNLP (sustainlp) 2020
Humans read and write hundreds of billions of messages every day.
How to Train BERT with an Academic Budget
peteriz/academic-budget-bert
•
•
EMNLP 2021
While large language models a la BERT are used ubiquitously in NLP, pretraining them is considered a luxury that only a few well-funded industry labs can afford.
Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding
Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions.
