Stanza

Overview

This is a maintenance release of Stanza. It features new support for `jieba` as Chinese tokenizer, faster lemmatizer implementation, improved compatibility with CoreNLP v4.0.0, and many more!

Enhancements

- **Supporting `jieba` library as Chinese tokenizer**. The Stanza (simplified and traditional) Chinese pipelines now support using the `jieba` Chinese word segmentation library as tokenizer. Turn on this feature in a pipeline with: `nlp = stanza.Pipeline('zh', processors={'tokenize': 'jieba'}`, or by specifying argument `tokenize_with_jieba=True`.

- **Setting resource directory with environment variable**. You can now override the default model location `$HOME/stanza_resources` by setting an environmental variable `STANZA_RESOURCES_DIR` (https://github.com/stanfordnlp/stanza/issues/227). The new directory will then be used to store and look up model files. Thanks to dhpollack for implementing this feature.

- **Faster lemmatizer implementation.** The lemmatizer implementation has been improved to be about 3x faster on CPU and 5x faster on GPU (https://github.com/stanfordnlp/stanza/issues/249). Thanks to mahdiman for identifying the original issue.

- **Improved compatibility with CoreNLP 4.0.0**. The client is now fully compatible with the latest [v4.0.0 release of the CoreNLP package](https://stanfordnlp.github.io/CoreNLP/).

Bugfixes

- **Correct character offsets in NER outputs from pre-tokenized text**. We fixed an issue where the NER outputs from pre-tokenized text may be off-by-one (https://github.com/stanfordnlp/stanza/issues/229). Thanks to RyanElliott10 for reporting the issue.

- **Correct Vietnamese tokenization on sentences beginning with punctuation**. We fixed an issue where the Vietnamese tokenizer may throw an `AssertionError` on sentences that begin with a punctuation (https://github.com/stanfordnlp/stanza/issues/217). Thanks to aryamccarthy for reporting this issue.

- **Correct pytorch version requirement**. Stanza is now asking for `pytorch>=1.3.0` to avoid a runtime error raised by pytorch ((https://github.com/stanfordnlp/stanza/issues/231)). Thanks to Vodkazy for reporting this.

Known Model Issues & Solutions

- **Default Korean Kaist tokenizer failing on punctuation.** The default Korean Kaist model is reported to have issues with separating punctuations during tokenization (https://github.com/stanfordnlp/stanza/issues/276). Switching to the Korean `GSD` model may solve this issue.

- **Default Polish LFG POS tagger incorrectly labeling last word in sentence as `PUNCT`**. The default Polish model trained on the `LFG` treebank may incorrectly tag the last word in a sentence as `PUNCT` (https://github.com/stanfordnlp/stanza/issues/220). This issue may be solved by switching to the Polish `PDB` model.

Overview
This is the first major release of Stanza (previously known as [StanfordNLP](https://github.com/stanfordnlp/stanfordnlp/)), a software package to process many human languages. The main features of this release are
* **Multi-lingual named entity recognition support**. Stanza supports named entity recognition in 8 languages (and 12 datasets): Arabic, Chinese, Dutch, English, French, German, Russian, and Spanish. The most comprehensive NER models in each language is now part of the default model download of that model, along with other models trained on the largest dataset available.
* **Accurate neural network models**. Stanza features highly accurate data-driven neural network models for a wide collection of natural language processing tasks, including tokenization, sentence segmentation, part-of-speech tagging, morphological feature tagging, dependency parsing, and named entity recognition.
* **State-of-the-art pretrained models freely available**. Stanza features a few hundred pretrained models for 60+ languages, all freely availble and easily downloadable from native Python code. Most of these models achieve state-of-the-art (or competitive) performance on these tasks.
* **Expanded language support**. Stanza now supports more than 60 human languages, representing a wide-range of language families.
* **Easy-to-use native Python interface**. We've improved the usability of the interface to maximize transparency. Now intermediate processing results are more easily viewed and accessed as native Python objects.
* **Anaconda support**. Stanza now officially supports installation from Anaconda. You can install Stanza through Stanford NLP Group's Anaconda channel `conda install -c stanfordnlp stanza`.
* **Improved documentation**. We have improved [our documentation](https://stanfordnlp.github.io/stanza/) to include a comprehensive coverage of the basic and advanced functionalities supported by Stanza.
* **Improved CoreNLP support in Python**. We have improved the robustness and efficiency of the `CoreNLPClient` to access the Java CoreNLP software from Python code. It is also forward compatible with the next major release of CoreNLP.
Enhancements and Bugfixes
This release also contains many enhancements and bugfixes:
* [Enhancement] Improved lemmatization support with proper conditioning on POS tags (143). Thanks to nljubesi for the report!
* [Enhancement] Get the text corresponding to sentences in the document. Access it through `sentence.text`. (80)
* [Enhancement] Improved logging. Stanza now uses Python's `logging` for all procedual logging, which can be controlled globally either through `logging_level` or a `verbose` shortcut. See [this page](https://stanfordnlp.github.io/stanza/pipeline.html#pipeline) for more information. (81)
* [Enhancement] Allow the user to use the Stanza tokenizer with their own sentence split, which might be useful for applications like machine translation. Simply set `tokenize_no_ssplit` to `True` at pipeline instantiation. (108)
* [Enhancement] Support running the dependency parser only given tokenized, sentence segmented, and POS/morphological feature tagged data. Simply set `depparse_pretagged` to `True` at pipeline instantiation. (141) Thanks mrapacz for the contribution!
* [Enhancement] Added spaCy as an option for tokenizing (and sentence segmenting) English text for efficiency. See this [documentation page](https://stanfordnlp.github.io/stanza/tokenize.html#use-spacy-for-fast-tokenization-and-sentence-segmentation) for a quick example.
* [Enhancement] Add character offsets to tokens, sentences, and spans.
* [Bugfix] Correctly decide whether to load pretrained embedding files given training flags. (120)
* [Bugfix] Google proto buffers reporting errors for long input when using the `CoreNLPClient`. (154)
* [Bugfix] Remove deprecation warnings from newer versions of PyTorch. (162)
Breaking Changes
Note that if your code was developed on a previous version of the package, there are potentially many breaking changes in this release. The most notable changes are in the `Document` objects, which contain all the annotations for the raw text or document fed into the Stanza pipeline. The underlying implementation of `Document` and all related data objects have broken away from using the CoNLL-U format as its internal representation for more flexibility and efficiency accessing their attributes, although it is still compatible with CoNLL-U to maintain ease of conversion between the two. Moreover, many properties have been renamed for clarity and sometimes aliased for ease of access. Please see our documentation page about these [data objects](https://stanfordnlp.github.io/stanza/data_objects.html) for more information.

This release features major improvements on memory efficiency and speed of the neural network pipeline in stanfordnlp and various bugfixes. These features include:

- The downloadable pretrained neural network models are now substantially smaller in size (due to the use of smaller pretrained vocabularies) with comparable performance. Notably, the default English model is now ~9x smaller in size, German ~11x, French ~6x and Chinese ~4x. As a result, memory efficiency of the neural pipelines for most languages are substantially improved.

- Substantial speedup of the neural lemmatizer via reduced neural sequence-to-sequence operations.

- The neural network pipeline can now take in a Python list of strings representing pre-tokenized text. (https://github.com/stanfordnlp/stanfordnlp/issues/58)

- A requirements checking framework is now added in the neural pipeline, ensuring the proper processors are specified for a given pipeline configuration. The pipeline will now raise an exception when a requirement is not satisfied. (https://github.com/stanfordnlp/stanfordnlp/issues/42)

- Bugfix related to alignment between tokens and words post the multi-word expansion processor. (https://github.com/stanfordnlp/stanfordnlp/issues/71)

- More options are added for customizing the Stanford CoreNLP server at start time, including specifying properties for the default pipeline, and setting all server options such as username/password. For more details on different options, please checkout the [client documentation page](https://stanfordnlp.github.io/stanfordnlp/corenlp_client.html#customizing-properties-for-server-start-and-requests).

- `CoreNLPClient` instance can now be created with CoreNLP default language properties as:
python
client = CoreNLPClient(properties='chinese')


- Alternatively, a properties file can now be used during the creation of a `CoreNLPClient`:
python
client = CoreNLPClient(properties='/path/to/corenlp.props')


- All specified CoreNLP annotators are now preloaded by default when a `CoreNLPClient` instance is created. (https://github.com/stanfordnlp/stanfordnlp/issues/56)

This is a maintenance release of stanfordnlp. This release features:

* Allowing the tokenizer to treat the incoming document as pretokenized with space separated words in newline separated sentences. Set `tokenize_pretokenized` to `True` when building the pipeline to skip the neural tokenizer, and run all downstream components with your own tokenized text. (24, 34)
* Speedup in the POS/Feats tagger in evaluation (up to 2 orders of magnitude). (18)
* Various minor fixes and documentation improvements

We would also like to thank the following community members for their contribution:
Code improvements: lwolfsonkin
Documentation improvements: 0xflotus
And thanks to everyone that raised issues and helped improve stanfordnlp!

The initial release of StanfordNLP. StanfordNLP is the combination of the software package used by the Stanford team in the CoNLL 2018 Shared Task on Universal Dependency Parsing, and the group’s official Python interface to the [Stanford CoreNLP software](https://stanfordnlp.github.io/CoreNLP). This package is built with highly accurate neural network components that enables efficient training and evaluation with your own annotated data. The modules are built on top of [PyTorch](https://pytorch.org/) (v1.0.0).

StanfordNLP features:

- Native Python implementation requiring minimal efforts to set up;
- Full neural network pipeline for robust text analytics, including tokenization, multi-word token (MWT) expansion, lemmatization, part-of-speech (POS) and morphological features tagging and dependency parsing;
- Pretrained neural models supporting 53 (human) languages featured in 73 treebanks;
- A stable, officially maintained Python interface to CoreNLP.