Semantic Line Breaker (SemBr)

> When writing text
> with a compatible markup language,
> add a line break
> after each substantial unit of thought.

What is SemBr?

SemBr is a command-line tool powered by Transformer models that breaks lines in a text file at semantic boundaries.

Installation

SemBr is available as a Python package on PyPI. To install it, simply run the following command in your terminal, assuming that you have Python 3.10 or later installed:

pip install sembr

Supported Platforms

SemBr is supported on Linux, Mac and Windows. On machines with CUDA devices, or on Apple Silicon Macs, SemBr will use the GPU / Apple Neural Engine to accelerate inference.

Usage

To use SemBr, run the following command in your terminal:

sembr -i <input_file> -o <output_file>

where <input_file> and <output_file> are the paths to the input and output files respectively.

On the first run, it will download the SemBr model and cache it in ~/.cache/huggingface. Subsequent runs will check for updates and use the cached model if it is up-to-date.

Alternatively, you can pipe the input into sembr, and the output can also be printed to the terminal:

cat <input_file> | sembr

This is especially useful if you want to use SemBr with clipboard managers, for instance, on a Mac:

pbpaste | sembr | pbcopy

Or on Linux:

xclip -o | sembr | xclip -i

Additionally, you can specify the following options to customize the behavior of SemBr:

• -m <model_name>: The name of the Hugging Face model to use.
  • The default is admko/sembr2023-bert-small.
  • To use it offline, you can download the model from Hugging Face, and then specify the path to the model directory, or prepend TRANSFORMERS_OFFLINE=1 to the command to use the cached model.
• -l: Serves the SemBr API on a local server.
  • Each instance of sembr run will detect if the API is accessible, and if not it will run the model on its own.
  • This option is useful to avoid the time taken to initialize the model by keeping it in memory in a separate process.
• -p <port>: The port to serve the SemBr API on.
  • The default is 8384.
• -s <ip>: The IP address to serve the SemBr API on.
  • The default is 127.0.0.1.

What are Semantic Line Breaks?

Semantic Line Breaks or Semantic Linefeeds describe a set of conventions for using insensitive vertical whitespace to structure prose along semantic boundaries.

Why use Semantic Line Breaks?

Semantic Line Breaks has the following advantages:

• Breaking lines by splitting clauses reflects the logical, grammatical and semantic structure of the text.

• It enhances the ease of editing and version control for a text file. Merge conflicts are less likely to occur when small changes are made, and the changes are easier to identify.

• Documents written with semantic line breaks are easier to navigate and edit with Vim and other text editors that use Vim keybindings.

• Semantic line breaks are invisible to readers. The final rendered output shows no changes to the source text.

Why SemBr?

Converting existing text not written with semantic line breaks takes a long time to do it manually, and it is surprisingly difficult to do it automatically with rule-based methods.

Challenges of rule-based methods

Rule-based heuristics do not work well with the actual semantic structure of the text, often leading to incorrect semantic boundaries. Moreover, these boundaries are hierarchical and nested, and a rule-based approach cannot capture this structure. A semantic line break may occur after a dependent clause, but where to break clauses into lines is challenging to determine without syntactic and semantic reasoning capabilities. For examples:

• A rule that breaks lines at punctuation marks will not work well with sentences that contain periods in abbreviations or mathematical expressions.

• Syntactic or semantic structures are not always easy to determine. "I like to eat apples and oranges because they are healthy." should be broken into lines as follows:

  > I like to eat apples and oranges
  > because they are healthy.
  

  rather than:

  > I like to eat apples
  > and oranges because they are healthy.
  

For this reason, I have created SemBr, which uses finetuned Transformer models to predict line breaks at semantic boundaries.

How does SemBr work?

SemBr uses a Transformer model to predict line breaks at semantic boundaries.

A small dataset of text with semantic line breaks was created from my existing LaTeX documents. The dataset was split into training (46,295 lines, 170,681 words and 1,492,952 characters) and test (2,187 lines, 7,564 words and 72,231 characters) datasets.

The data was prepared by extracting line breaks and indent levels from the files, and then converting the result into strings of paragraphs with line breaks removed. The data can then be tokenized using the tokenizer and converted into a dataset with tokens, where each token has a label denoting if there is line break before it, and the indent level of the token.

For LaTeX documents, there are two types of line breaks: one with a normal line break that adds implicit spacing (e.g. line a⏎line b) and one with no spacing (e.g. line a%⏎line b). The data processor also tries to preserve the LaTeX syntax of the text by adding and removing comment symbols (%), if necessary.

The pretrained masked language model is then finetuned as a token classifier on the training dataset to predict the labels of the tokens. We save the model with the best F1 score on correctly predicting the existence of a line break on the test set. The finetuning logs for the following models can be found on this WandB report:

• distilbert-base-uncased [Pretrained] [Finetuned]
• distilbert-base-cased [Pretrained] [Finetuned]
• distilbert-base-uncased-finetuned-sst-2-english [Pretrained] [Finetuned]
• prajjwal1/bert-tiny [Pretrained] [Finetuned]
• prajjwal1/bert-mini [Pretrained] [Finetuned]
• prajjwal1/bert-small [Pretrained] [Finetuned]

Performance

Current inference speed on an M2 Macbook Pro is about 850 words per second on bert-small with the default options, the memory usage is about 1.70 GB.

The link breaking accuracy is difficult to measure, and the locations of line breaks could also be subjective. On the test set, the per-token line break accuracy of the models are >95%, with ~80% F1 scores. Because of the sparse nature of line breaks, the accuracy is not a good metric to measure the performance of the model, and I used the F1 score instead to save best models.

Improvements and TODOs

• Features:
  • Natural language support:
    • Support natural languages other than English.
  • Typesetting languages support:
    • Markdown.
    • Typst.
  • Usability:
    • Inference queue.
    • Daemon with model unloading.
  • Editor integration:
    • NeoVim plugin.
    • VSCode extension.
  • Use the Hugging Face API for inference. It is free to use but has a rate limit, and also does not return logit values, so no additional algorithms can be used to improve the predictions.
• Accuracy:
  • Some lines are too short or too long:
    • Long lines can be penalized greedily by breaking lines with token counts more than --tokens-per-line.
    • Support --words-per-line.
    • Improve the algorithm to penalize short and long lines with a more sophisticated method.
  • Improve indent level prediction.
  • Performance and accuracy benchmarking, and comparisons with related works.
• Performance:
  • Improve inference speed.
  • Reduce memory usage.

Related Projects and References

Sentence splitting:

• https://code.google.com/archive/p/splitta/
• https://en.wikipedia.org/wiki/Sentence_boundary_disambiguation
• https://github.com/nipunsadvilkar/pySBD
• https://www.nltk.org/api/nltk.tokenize.sent_tokenize.html

Semantic line breaking:

• https://github.com/sembr/specification
• https://github.com/waldyrious/semantic-linebreaker
• https://github.com/bobheadxi/readable (blog post)
• https://github.com/chrisgrieser/obsidian-sembr
• https://github.com/cllns/semantic_linefeeds