Fixed headlines, moved table of contents to top

README.md

@@ -1,5 +1,29 @@
 # Tracking Progress in Natural Language Processing
 
+### Table of contents
+
+- [CCG supertagging](ccg_supertagging.md)
+- [Chunking](chunking.md)
+- [Constituency parsing](constituency_parsing.md)
+- [Coreference resolution](coreference_resolution.md)
+- [Dependency parsing](dependency_parsing.md)
+- [Dialog](dialog.md)
+- [Domain adaptation](domain_adaptation.md)
+- [Language modelling](language_modeling.md)
+- [Machine translation](machine_translation.md)
+- [Multi-task learning](multi-task_learning.md)
+- [Multimodal](multimodal.md)
+- [Named entity recognition](named_entity_recognition.md)
+- [Natural language inference](natural_language_inference.md)
+- [Part-of-speech tagging](part-of-speech_tagging.md)
+- [Question answering](question_answering.md)
+- [Semantic textual similarity](semantic_textual_similarity.md)
+- [Sentiment analysis](sentiment_analysis.md)
+- [Semantic parsing](semantic_parsing.md)
+- [Semantic role labeling](semantic_role_labeling.md)
+- [Summarization](summarization.md)
+- [Text classification](text_classification.md)
+
 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.
 
@@ -47,27 +71,3 @@ the one that introduced the dataset.
 - We could potentially use [readthedocs](https://github.com/rtfd/readthedocs.org) to provide a clearer structure.
 - All current datasets in this list are for the English language (except for [UD](#ud)). In a separate section, we could add
 datasets for other languages.
-
-### Table of contents
-
-- [CCG supertagging](ccg_supertagging.md)
-- [Chunking](chunking.md)
-- [Constituency parsing](constituency_parsing.md)
-- [Coreference resolution](coreference_resolution.md)
-- [Dependency parsing](dependency_parsing.md)
-- [Dialog](dialog.md)
-- [Domain adaptation](domain_adaptation.md)
-- [Language modelling](language_modeling.md)
-- [Machine translation](machine_translation.md)
-- [Multi-task learning](multi-task_learning.md)
-- [Multimodal](multimodal.md)
-- [Named entity recognition](named_entity_recognition.md)
-- [Natural language inference](natural_language_inference.md)
-- [Part-of-speech tagging](part-of-speech_tagging.md)
-- [Question answering](question_answering.md)
-- [Semantic textual similarity](semantic_textual_similarity.md)
-- [Sentiment analysis](sentiment_analysis.md)
-- [Semantic parsing](semantic_parsing.md)
-- [Semantic role labeling](semantic_role_labeling.md)
-- [Summarization](summarization.md)
-- [Text classification](text_classification.md)

question_answering.md

@@ -12,7 +12,7 @@ based on accuracy.
 
 A public leaderboard is available on the [ARC website](http://data.allenai.org/arc/).
 
-## Reading comprehension
+## Reading comprehension
 
 Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph
 or document and the answer often is a span in the document. The Machine Reading group

semantic_parsing.md

@@ -4,7 +4,7 @@ Semantic parsing is the task of translating natural language into a formal meani
 representation on which a machine can act. Representations may be an executable language
 such as SQL or more abstract representations such as [Abstract Meaning Representation (AMR)](https://en.wikipedia.org/wiki/Abstract_Meaning_Representation).
 
-## SQL parsing
+## SQL parsing
 
 ### WikiSQL
 

sentiment_analysis.md

@@ -62,7 +62,7 @@ Binary classification:
 | CNN (Johnson and Zhang, 2016) | 2.90 | [Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings](https://arxiv.org/abs/1602.02373) |
 | Char-level CNN (Zhang et al., 2015) | 4.88 | [Character-level Convolutional Networks for Text Classification](https://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf) |
 
-## Aspect-based sentiment analysis
+## Aspect-based sentiment analysis
 
 ### Sentihood
 
@@ -76,3 +76,5 @@ for aspect detection and accuracy as evaluation metric for sentiment analysis.
 | Liu et al. (2018) | 78.5 | 91.0 | [Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis](http://aclweb.org/anthology/N18-2045) |
 | SenticLSTM (Ma et al., 2018) | 78.2 | 89.3 | [Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM](http://sentic.net/sentic-lstm.pdf) | 
 | LSTM-LOC (Saeidi et al., 2016) | 69.3 | 81.9 | [Sentihood: Targeted aspect based sentiment analysis dataset for urban neighbourhoods](http://www.aclweb.org/anthology/C16-1146) |
+
+[Go back to the README](README.md)