Merge pull request #370 from NervanaSystems/v0.4_minor_patch

fix docs typos, formatting, and refs. add ABSA to main.rst

Author: Peter Izsak

doc/source/absa.rst

@@ -153,8 +153,8 @@ Arguments:
 References
 ==========
 
-.. [1] `Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations <https://transacl.org/ojs/index.php/tacl/article/view/885/198>`__, Kiperwasser, E., & Goldberg, Y, Transactions Of The Association For Computational Linguistics (2106), 4, 313-327.
-.. [2] `Opinion word expansion and target extraction through double propagation <https://dl.acm.org/citation.cfm?id=1970422>`__, Guang  Qiu,  Bing  Liu,  Jiajun  Bu,  and  Chun  Chen, In Computational Linguistics, volume 37(1).
-.. [3] `Mining and Summarizing Customer Reviews <http://dx.doi.org/10.1145/1014052.1014073>`__, Minqing Hu and Bing Liu, Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2004), pp. 168-177, 2004.
+.. [1] `Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations <https://transacl.org/ojs/index.php/tacl/article/view/885/198>`__, Eliyahu Kiperwasser and Yoav Goldberg. 2016. Transactions of the Association of Computational Linguistics, 4:313–327.
+.. [2] `Opinion Word Expansion and Target Extraction through Double Propagation <https://dl.acm.org/citation.cfm?id=1970422>`__, Guang Qiu, Bing Liu, Jiajun Bu, and Chun Chen. 2011. Computational Linguistics, 37(1): 9–27.
+.. [3] `Mining and Summarizing Customer Reviews <http://dx.doi.org/10.1145/1014052.1014073>`__, Minqing Hu and Bing Liu. 2004. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’04, pages 168–177.
 
 .. _Spacy: https://spacy.io

doc/source/absa_solution.rst

@@ -31,7 +31,7 @@ a statistical analysis of sentiment towards specific aspects in the inference da
 
 The solution uses the opinion and aspect lexicons that are generated using NLP Architect's ABSA
 training model (see blue blocks in 'flow' diagram below). For more details regarding the training step
-see :doc:`ABSA <absa>`
+see :doc:`ABSA <absa>`.
 
 The solution encapsulates the ABSA inference model (green blocks) and adds on top of it a
 statistical analysis module (grey block) for calculating the amount of positive and negative sentiment
@@ -61,23 +61,24 @@ blue and opinion terms are colored in green/red:
 Solution execution
 ==================
 
-The solution execution is divided to two parts - training A and inference:
+The solution execution is divided to two parts - training and inference:
 
 Training
 ========
 
-See training under :doc:`ABSA <absa>`
+See training under :doc:`ABSA <absa>`.
 
 
 Inference
 =========
 
+
 Full code example is available at ``examples/absa/solution/absa_solution.py``.
 There are two training modes:
 
-1. Providing solution data in a raw text format. In this case the solution flow will
-apply the dependency parser to the data:
 
+**1.** Providing solution data in a raw text format. In this case the solution flow will
+apply the dependency parser to the data:
 
 .. code:: python
 
@@ -86,7 +87,7 @@ apply the dependency parser to the data:
             data='/path/to/text/file/or/directory')
 
 
-Arguments:
+**Arguments:**
 
 ``aspect_lex'=/path/to/aspects.csv'``  - path to aspect lexicon (csv file) that was produced by the training phase.
 aspect.csv may be manually edited for grouping alias aspect names (e.g. 'drinks' and 'beverages')
@@ -98,7 +99,7 @@ together. Simply copy all alias names to the same line in the csv file.
 separated by newlines or a single csv file containing one doc per line or a directory containing one raw
 text file per document.
 
-Notes:
+**Notes:**
 
 a. For demonstration purposes we provide a sample of tripadvisor.co.uk
 restaurants reviews under the `Creative Commons Attribution-Share-Alike 3.0 License <https://creativecommons.org/licenses/by-sa/3.0/>`__ (Copyright 2018 Wikimedia Foundation).
@@ -107,8 +108,8 @@ The dataset can is located at ``datasets/absa/tripadvisor_co_uk-travel_restauran
 b. By default, when the execution terminates, a browser window is opened, displaying the
 visualization UI.
 
-
-2. Providing parsed training data. In this case the solution flow skips the parsing step:
+|
+| **2.** Providing parsed training data. In this case the solution flow skips the parsing step:
 
 .. code:: python
 
@@ -117,7 +118,7 @@ visualization UI.
                             parsed_data='/path/to/parsed/directory',
                             ui=False)
 
-Note:
+**Note:**
 
 Setting ``ui=False`` disables the UI and enables to get the sentiment statistics as dataframe. This
 enables the user to use those statistics as input to his own custom built visualization.

doc/source/main.rst

@@ -42,6 +42,7 @@ The library contains state-of-art and novel NLP and NLU models in a variety of t
 - Reading comprehension
 - Language modeling using Temporal Convolution Network
 - Unsupervised Crosslingual Word Embedding
+- Aspect Based Sentiment Analysis
 - Supervised sentiment analysis
 - Sparse and quantized neural machine translation
 - Relation Identification and cross document coreference