---
license: apache-2.0
library_name: onnx
tags: 
  - punctuation 
  - sentence boundary detection
  - truecasing
language:
- af
- am
- ar
- bg
- bn
- de
- el
- en
- es
- et
- fa
- fi
- fr
- gu
- hi
- hr
- hu
- id
- is
- it
- ja
- kk
- kn
- ko
- ky
- lt
- lv
- mk
- ml
- mr
- nl
- or
- pa
- pl
- ps
- pt
- ro
- ru
- rw
- so
- sr
- sw
- ta
- te
- tr
- uk
- zh
---
# Model Overview
This model accepts as input lower-cased, unpunctuated, unsegmented text in 47 languages and performs punctuation restoration, true-casing (capitalization), and sentence boundary detection (segmentation).

# Model Details

This model generally follows the graph shown below, with brief descriptions for each step following.

![graph.png](https://s3.amazonaws.com/moonup/production/uploads/1677025540482-62d34c813eebd640a4f97587.png)


1. **Encoding**:
The model begins by tokenizing the text with a subword tokenizer.
The tokenizer used here is a `SentencePiece` model with a vocabulary size of 64k.
Next, the input sequence is encoded with a base-sized Transformer, consisting of 6 layers with a model dimension of 512.

2. **Post-punctuation**:
The encoded sequence is then fed into a classification network to predict "post" punctuation tokens. 
Post punctuation are punctuation tokens that may appear after a word, basically most normal punctuation.
Post punctation is predicted once per subword - further discussion is below. 

3. **Re-encoding**
All subsequent tasks (true-casing, sentence boundary detection, and "pre" punctuation) are dependent on "post" punctuation.
Therefore, we must conditional all further predictions on the post punctuation tokens.
For this task, predicted punctation tokens are fed into an embedding layer, where embeddings represent each possible punctuation token.
Each time step is mapped to a 4-dimensional embeddings, which is concatenated to the 512-dimensional encoding.
The concatenated joint representation is re-encoded to confer global context to each time step to incorporate puncuation predictions into subsequent tasks.

4. **Pre-punctuation**
After the re-encoding, another classification network predicts "pre" punctuation, or punctation tokens that may appear before a word.
In practice, this means the inverted question mark for Spanish and Asturian, `¿`.
Note that a `¿` can only appear if a `?` is predicted, hence the conditioning.

5. **Sentence boundary detection**
Parallel to the "pre" punctuation, another classification predicts from the re-encoded text sentence boundaries.
In all languages, sentence boundaries can occur only if a potential full stop is predicted, hence the conditioning.

6. **Shift and concat sentence boundaries**
In many languages, the first character of each sentence should be upper-cased.
Thus, we want to feed the sentence boundary information to the true-case classification network.
Since the true-case classification network is feed-forward and has no context, each time step must embed whether it is the first word of a sentence.
Therefore, we shift right by one the binary sentence boundary decisions.
Concatenating this with the re-encoded text, each time step contains whether it is the first word of a sentence as predicted by the SBD head.

7. **True-case prediction**
Armed with the knowledge of punctation and sentence boundaries, a classification network predicts true-casing.
Since true-casing should be done on a per-character basis, the classification network makes `N` predictions per token, where `N` is the length of the subtoken.
(In practice, `N` is the longest possible subword, and the extra predictions are ignored).
This scheme captures acronyms, e.g., "NATO", as well as bi-capitalized words, e.g., "MacDonald".


## Post-Punctuation Tokens
This model predicts the following set of "post" punctuation tokens:

| Token  | Description | Relavant Languages |
| ---: | :---------- | :----------- |
| .    | Latin full stop | Many |
| ,    | Latin comma | Many |
| ?    | Latin question mark | Many |
| ？    | Full-width question mark | Chinese, Japanese |
| ，    | Full-width comma | Chinese, Japanese |
| 。    | Full-width full stop | Chinese, Japanese |
| 、    | Ideographic comma | Chinese, Japanese |
| ・    | Middle dot | Japanese |
| ।    | Danda | Hindi, Bengali, Oriya |
| ؟    | Arabic question mark | Arabic |
| ;    | Greek question mark | Greek |
| ።    | Ethiopic full stop | Amharic |
| ፣    | Ethiopic comma | Amharic |
| ፧    | Ethiopic question mark | Amharic |


# Usage


# Training Details
This model was trained in the NeMo framework.

## Training Data
This model was trained with News Crawl data from WMT.

1M lines of text for each language was used, except for a few low-resource languages which may have used less.

Languages were chosen based on whether the News Crawl corpus contained enough reliable-quality data as judged by the author.

# Bias, Risks, and Limitation
This model was trained on news data, and may not perform well on conversational or informal data.

This is also a base-sized model with many languages and many tasks, so capacity may be limited.

# Evaluation