Tracking Progress in Natural Language Processing

Table of contents

• CCG supertagging
• Chunking
• Constituency parsing
• Coreference resolution
• Dependency parsing
• Dialog
• Domain adaptation
• Entity Linking
• Language modelling
• Machine translation
• Multi-task learning
• Multimodal
• Named entity recognition
• Natural language inference
• Part-of-speech tagging
• Question answering
• Semantic textual similarity
• Sentiment analysis
• Semantic parsing
• Semantic role labeling
• Summarization
• Text classification

This document aims to track the progress in Natural Language Processing (NLP) and give an overview of the state-of-the-art across the most common NLP tasks and their corresponding datasets.

It aims to cover both traditional and core NLP tasks such as dependency parsing and part-of-speech tagging as well as more recent ones such as reading comprehension and natural language inference. The main objective is to provide the reader with a quick overview of benchmark datasets and the state-of-the-art for their task of interest, which serves as a stepping stone for further research. To this end, if there is a place where results for a task are already published and regularly maintained, such as a public leaderboard, the reader will be pointed there.

Wish list

These are tasks and datasets that are still missing.

• Bilingual dictionary induction
• Discourse parsing
• Information extraction
• Keyphrase extraction
• Knowledge base population (KBP)
• More dialogue tasks
• Relation extraction
• Semi-supervised learning

Contributing

If you would like to add a new result, you can do so with a pull request. In order to minimize noise and to make maintenance somewhat manageable, results reported in published papers will be preferred (indicate the venue of publication in your PR); an exception may be made for influential preprints. The result should include the name of the method, the citation, the score, and a link to the paper and should be added so that the table is sorted.

In order to make reproduction easier, we recommend to add a link to an implementation to each method if available. You can add a Code column (see below) to the table if it does not exist. In the Code column, indicate an official implementation with Official. If an unofficial implementation is available, use Link (see below). If no implementation is available, you can leave the cell empty.

Model	Score	Paper / Source	Code
			Official
			Link

To add a new dataset or task, follow the below steps. Any new datasets should have been used for evaluation in at least one published paper besides the one that introduced the dataset.

1. Fork the repository.
2. If your task is completely new, create a new file and link to it in the table of contents above. If not, add your task or dataset to the respective section of the corresponding file.
3. Briefly describe the dataset/task and include relevant references.
4. Describe the evaluation setting and evaluation metric.
5. Show how an annotated example of the dataset/task looks like.
6. Add a download link if available.
7. Copy the below table and fill in at least two results (including the state-of-the-art) for your dataset/task (change Score to the metric of your dataset).
8. Submit your change as a pull request.

Model	Score	Paper / Source	Code

Things to do

• Add a column for code (see above) to each table and a link to the source code to each method.
• Add pointers on how to retrieve data.
• Provide more details regarding the evaluation setup of each task.
• Add an example to every task/dataset.
• Add statistics to every dataset.
• Provide a description and details for every task / dataset.
• We could potentially use readthedocs to provide a clearer structure.
• All current datasets in this list are for the English language (except for UD). In a separate section, we could add datasets for other languages.