#
Wolfram Neural Net Repository

Immediate Computable Access to Neural Net Models

Represent text as a sequence of vectors

Released in 2019, these four pre-trained feature extractors leverage a large multidomain scientific corpus with a total of 3.17 billion tokens. Two vocabularies are available, each coming in both cased and uncased versions: the original BERT vocabulary and a new "Scivocab", with overlapping by 42% with the original. The resulting model has improved performance on a suite of downstream scientific NLP tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains.

Number of models: 4

- SemanticScholar, a dataset consisting of 1.14 million scientific publications with 18% of the papers from computer science domain and 82% from the broad biomedical domain.

F1 scores for fine-tuned BERT and Uncased-Scivocab SciBERT models for various natural language inference tasks:

Get the pre-trained net:

In[1]:= |

Out[1]= |

This model consists of a family of individual nets, each identified by a specific parameter combination. Inspect the available parameters:

In[2]:= |

Out[2]= |

Pick a non-default net by specifying the parameters:

In[3]:= |

Out[3]= |

Pick a non-default uninitialized net:

In[4]:= |

Out[4]= |

Given a piece of text, SciBERT net produces a sequence of feature vectors of size 768, which corresponds to the sequence of input words or subwords:

In[5]:= |

Obtain the dimensions of the embeddings:

In[6]:= |

Out[6]= |

Visualize the embeddings:

In[7]:= |

Out[7]= |

Each input text segment is first tokenized into words or subwords using a word-piece tokenizer and additional text normalization. Integer codes called token indices are generated from these tokens, together with additional segment indices:

In[8]:= |

Out[9]= |

For each input subword token, the encoder yields a pair of indices that corresponds to the token index in the vocabulary and the index of the sentence within the list of input sentences:

In[10]:= |

Out[10]= |

The list of tokens always starts with special token index 102, which corresponds to the classification index. Also the special token index 103 is used as a separator between the different text segments. Each subword token is also assigned a positional index:

In[11]:= |

Out[11]= |

A lookup is done to map these indices to numeric vectors of size 768:

In[12]:= |

Out[13]= |

For each subword token, these three embeddings are combined by summing elements with ThreadingLayer:

In[14]:= |

Out[14]= |

The transformer architecture then processes the vectors using 12 structurally identical self-attention blocks stacked in a chain:

In[15]:= |

Out[15]= |

The key part of these blocks is the attention module comprising of 12 parallel self-attention transformations, also called “attention heads.” Each head uses an AttentionLayer at its core:

In[16]:= |

Out[16]= |

SciBERT uses self-attention, where the embedding of a given subword depends on the full input text. The following figure compares self-attention (lower left) to other types of connectivity patterns that are popular in deep learning:

Define a sentence embedding that takes the last feature vector from SciBERT subword embeddings (as an arbitrary choice):

In[17]:= |

Out[17]= |

Define a list of sentences in three broad categories (diseases, medicines and NLP models):

In[18]:= |

Precompute the embeddings for a list of sentences:

In[19]:= |

Visualize the similarity between the sentences using the net as a feature extractor:

In[20]:= |

Out[20]= |

Inspect the number of parameters of all arrays in the net:

In[21]:= |

Out[21]= |

Obtain the total number of parameters:

In[22]:= |

Out[22]= |

Obtain the layer type counts:

In[23]:= |

Out[23]= |

Display the summary graphic:

In[24]:= |

Out[24]= |

Wolfram Language 12.1 (March 2020) or above

- I. Beltagy, K. Lo, A. Cohan, "SciBERT: A Pretrained Language Model for Scientific Text," arXiv:1903.10676 (2019)
- (available from https://github.com/allenai/scibert)
- Rights: Apache 2.0 License