What are the current hot topics in natural

language processing?
Almost everything in Natural Language Processing (NLP) should be considered to be done in
multiple languages, starting from English. Where the complexity of an NLP task can differ
across languages, we consider English as the first choice, and then only tend to move to other
languages. For instance, consider word segmentation, which is rather straightforward for
English. The following does not cover any speech related tasks, since those topics should be
better listed under the speech paradigm. Also, optical character recognition like methods are
more to be listed under the computer vision paradigm.

Natural Language Generation

(1) Generation of realistic, rhymed and theme based poetry (creative writing)

(2) Generation of theme based short stories (creative writing)

(3) Generation of theme based novels (creative writing)

(4) Generation of news / short articles based on numerical / audio / video data

(5) Generation of research papers based on a topic. Here (4) helps but one also needs proper
understanding and summarization of various research papers (which will involve a lot of other
aspects of NLP and also some inference over figures and mathematical equations)

Natural Language Understanding

(1) Sentiment Analysis - Deriving sentiments in sentences (positive, negative, neutral), and also
in articles (though that will be more appropriate like bag of sentence sentiments). The future is to
include emotions (attributes) in that, like the attributes now on Facebook posts - Love, Like,
Angry, Surprised, Sad, Hilarious. These attributes make a lot more sense for sentiments going
forward.

(2) Text Summarization - Summarizing a single or many articles according to a particular theme.

(3) Textual Entailment - Inferring directional causal relationships between textual fragments.
This can be challenging in a long article.

(4) Information Extraction - Find structured information from unstructured data, like entities,
relationships, co-reference resolution. This at a basic level is very useful for algorithmic trading.
An extension of this is a global form of extracting logic structures (first order and higher order).

(5) Topic Segmentation - Topic Extraction (with regions). Normally, there will be overlapping
regions.
(6) Question Answering - Answer the questions to both closed (specific) and open questions
(subjective). Answers to subjective questions is the main challenge for the likes of realistic
Virtual Assistants.

(7) Parsing - Parsing natural language generally in the form a tree. This involves hierarchical
segmentation of the language involving the grammar rules.

(8) Prediction - Given a short text, predict what happens next. The prediction problem is
beginning to be targeted in vision, but it has never ever gained paths for realistic products. For
closed and deterministic prediction (not innovative else that would fall under the paradigm of
creative writing), this can be a useful task for prediction of future events based on past evidences
and analysis. This can be then very useful for finance sectors.

(9) Part of Speech Tagging (POS) - Tagging words whether they are nouns, verbs or adjectives.

(10) Translation - Translate one language to another. This can be very challenging given the
nature of the language, and the grammar. Normally, under probabilistic models, this assumes that
the underlying grammar is mostly the same, and thus, models normally fail for Sanskrit.

(11) Query Expansion - Expand query in possible ways for making the search results more
meaningful. This is normally an issue with search engines, where people do not know what all
keywords (or query sentences) to include to cover the entire gamut of relevancy.

(12) Argumentation Mining - Evolving field of NLP, where one wants to analyse discussions and
arguments.

(13) Interestingness - Most interesting portion of text in an article. This can be done very much
on the same lines as in images, where one ranks the likeness of images.

Natural Language Processing and Computer Vision

The areas of Visual Question Answering and Automated Image Captioning can be seen as
utilizing the skills from both the fields of Computer Vision and NLP. These areas are still in their
infancy, and a lot of scope lies ahead for product-realistic amelioration !!

Some of the trending topics in Natural Language Processing are:

1. Natural Language Understanding
2. Natural Language Generation
3. Text extraction
4. Language translation
5. Parsing
6. Parts-of-speech tagging

Natural language processing is currently (late 2013) hot in general. According to Gartner Hype
Cycles report, it is nearing the apogee of hype (just before the "trough of disillusionment").
The hottest topics are:

by far margin from the rest, natural language understanding and specifically natural
language user interfaces.
extraction of actionable intelligence from social media or customer feedback. This
includes sentiment analysis, but the binary sentiment analysis is no longer enough.
named entity extraction.
classic "binary" sentiment analysis is already old news.