Skip to main content

Natural language interactions for learning


From so many years, humans are constantly trying to make machines as they are to make their life easier and advance. Natural Language Processing was one big step towards making the computers understand human language. Natural Language Processing made computers able to convert a set of natural language rules into computer code. Now computers do more than that, Yes!! Now computers not only understand what we say but also understand what we mean with the help of Natural Language Interactions. Natural Language Interaction is the advancement of NLP that allows computers and humans to communicate using natural language.
Today, NLIs on machines are often trained once and deployed and user is bound to their limitations. Research suggests that when learning a language, rather than consciously analyzing increasingly complex linguistic structures (e.g. sentence forms, word conjugations), humans advance their linguistic ability through meaningful interactions[1]. The standard machine learning data set setting has no interaction and that only continue for any action. Interactivity requires adaptive and customizable systems and that brings complexity. Natural Language Interactions come with many challenges such as :
    1.        Modifier attachment
2.      Conjunction and dis-junction
3.    Anaphora resolution
There have been many attempts towards interactive language learning applications; some of them are listed below.
  • SHRDLU Language game: In a language game, the computer and the human user need to collaboratively accomplish a goal even though they do not initially speak a common language. In SHRDLU,[2] the objective  is to transform a start state into a goal state, but the only action the human can take is entering an utterance. The computer parses the utterance and produces a ranked list of possible interpretations according to its current model. The human scrolls through the list and chooses the intended one, simultaneously advancing the state of the blocks and providing feedback to the computer. Both the human and the computer wish to reach the goal state with minimum steps possible. For the success of computer, it has to learn quickly so that human can work efficiently and human speeds up by accommodating to the computer. Computer generates many candidate logical forms and human’s feedback helps it learn and adjust the parameters. The most interesting thing here is the real time learning, in which human also learns and adapts to computers. In the pilot version, English, Arabic, Polish and a custom programming language were considered.

  • A calendar scheduler: If we scale NLI to more complex and broader domain spaces, richer feedback signals from human is required and for generalizability of the application, community based data collection is needed. Event scheduling is a common task but allows limited natural language input. These applications fail as soon as complex input such as ‘Move all the tuesday afternoon appointments back an hour’ is given. In practice, if the correct interpretation is not among the top choices, the system falls back to a GUI and the user uses the GUI to show the system what they meant.
  • IBM Language access
  • iAskWeb from Anserity Inc[3]
  • Siri: Siri is an intelligent personal assistant application integrated with iOS. Siri’s marketing claims to include that it adapts to user’s individual preference over time and personalizes the results.
Looking forward, NLIs must learn through interaction with users, and improve over time. NLIs have the potential to replace GUIs and scripting for many tasks, and doing so can bridge the great digital divide of skills and enable all of us to better make use of computers.

References:
[1] “Principles and practice in Second language acquisition” Stephen D Kreshen, 1983
[2] “Learning language games through interaction”, Sida I. Wang Percy Liang Christopher D. Manning, Stanford University.
[3] Galitsky, Boris (2003). Natural Language Question Answering: technique of semantic headers, Adelaid, Australia: Advance Knowledge International.
[4]“Natural Language-based User Interface for Knowledge Management System. A Computational Linguistics Approach” Mario Monteleone, Maria Pia di Buono and Federica Marano University of Salerno, Fisciano (SA) – Italy 

Labels:

Comments

Post a Comment

Popular posts from this blog

NLP in Video Games

From the last few decades, NLP (Natural Language Processing) has obtained a high level of success in the field  of Computer Science, Artificial Intelligence and Computational Logistics. NLP can also be used in video games, in fact, it is very interesting to use NLP in video games, as we can see games like Serious Games includes Communication aspects. In video games, the communication includes linguistic information that is passed either through spoken content or written content. Now the question is why and where can we use NLP in video games?  There are some games that are related to pedagogy or teaching (Serious Games). So, NLP can be used in these games to achieve these objectives in the real sense. In other games, one can use the speech control using NLP so that the player can play the game by concentrating only on visuals rather on I/O. These things at last increases the realism of the game. Hence, this is the reason for using NLP in games.  We can use NLP to impr
4 comments
Read more

Discourse Analysis

NLP makes machine to understand human language but we are facing issues like word ambiguity, sarcastic sentiments analysis and many more. One of the issue is to predict correctly relation between words like " Patrick went to the club on last Friday. He met Richard ." Here, ' He' refers to 'Patrick'. This kind of issue makes Discourse analysis one of the important applications of Natural Language Processing. What is Discourse Analysis ? The word discourse in linguistic terms means language in use. Discourse analysis may be defined as the process of performing text or language analysis, which involves text interpretation and knowing the social interactions. Discourse analysis may involve dealing with morphemes, n-grams, tenses, verbal aspects, page layouts, and so on. It is often used to refer to the analysis of conversations or verbal discourse. It is useful for performing tasks, like A naphora Resolution (AR) , Named Entity Recognition (NE
5 comments
Read more

Coreference Resolution and Applications in NLP

In computational linguistics and natural language processing coreference resolution (CR) is an avidly studies problem in discourse which has managed to be only partially solved by the state of the art and consequently remain one of the most exciting open problems in this field. Introduction and Definition The process of linking together mentions of a particular entity in a speech or text excerpt that related to real world entities is termed as coreference resolution. This process identifies the dependence between a phrase with the rest of the sentence or other sentences in the text.  This is an integral part of natural languages to avoid repetition, demonstrate possession/relation etc. A basic example to illustrate the above definition is given below : Another example which uses elements from popular fiction literature : Harry  wouldn’t bother to read “ Hogwarts: A History ” as long as  Hermione  is around.  He  knows  she  knows  the book  by heart. The different type
Post a Comment
Read more