• Contribute
• What's New
• Submit News

What is Natural Language?

What is Natural Language Processing?
NLP (Natural Language Processing) is a field in AI involving anything that processes natural language. Extensive research in NLP over the past decade has brought us one of the most useful applications of AI: machine translation. If we could one day created a program that could translate (for example) English text to Japanese and vice versa without need of polishing by a professional translator then bridges of communication could be significantly widened. Our current translation programs have not yet reached this level, but they may do so very soon.

In particular, NLP research also deals with speech recognition. Currently, programs that convert spoken speech into text have been widely used and are fairly dependable. Another field of study in NLP are story understanders, as well as chatterboxes. During the 1960s Joseph Weizenbaum created ELIZA. ELIZA created a storm of public interest in AI, as it helped thousands overcome their personal problems. ELIZA was a psychiatrist, particularly one that posed analytical questions for every answer the user gave it. Though sometimes they may have seemed ambiguous, people actually felt ELIZA could take care of their needs just as well as any other therapist. They became emotionally involved with ELIZA, even Weizenbaum's secretary demanded to be left alone with the program. The following is a transcript of ELIZA chatting with another program PARRY:

Parry:I don't understand your motives.
Eliza:Why don't you understand my motives?
Parry:Shouldn't I be?
Eliza:What did you say just now?
Parry:That's just the way it is.
Eliza:Suppose that's just the way it were not.
Parry:So?
Eliza:I am not sure I understand you fully.
Parry:You harp on the same questions too much.
Eliza:What does this similarity suggest to you?
Parry:I don't get you.
Eliza:Do you wish that I you did get I?
Parry:It's about time you showed some interest in my feelings.
Eliza:Oh? I showed some interest in your feelings?

When people had started calling ELIZA intelligent, Joseph Weizenbaum went into an uproar. Technically, ELIZA was actually unable to understand people's personal problems to the depth of any other human being. ELIZA could only manipulate syntax (grammar), and check for some key words. Certainly, if someone had no knowledge of ELIZA being a program, one could easily conclude that it behaved like a human conversing, although it never really neccessary understood everything to the detail that humans do.

Coincidentally, ELIZA creates questions to help people's personal problems, while IQATS (Intelligent Question and Answer Test Summarizer), a program written by Sam Hsiung (Generation 5 staff member), creates questions for test-making purposes. Unlike ELIZA, IQATS is able to learn how to ask new questions, if it is given a sample question and answer. Yet, like ELIZA, it knows and will learn only how to manipulate syntax. It will be able to ask a question about what the capital or Saudi Arabia is, however if it were given something a bit more complex, such as Martin Luther King's I have a dream speech, it would not be able to come up with questions that force people to draw inferences (Ex.: Under what context was this speech given in?); neither does it really understand what it is asking.

Many researchers realized this limitation, and as a result conceptual dependency (CD) (pioneered by Roger Schank) theory was created. CR systems such as SAM (Script Applier Mechanism) are story understanders. When SAM is given a story, and later asked questions about it, it will answer many of those questions accurately. (Thus showing that it "understands") It can even infer. It accomplishes this through use of scripts. The scripts designate a sequence of actions that are to be performed in chronological fashion for a certain situation. A restaurant script would say that you would need to sit down by a table before you are served dinner.

The following is a small example of SAM (Script Applier Mechanism) paraphrasing a story (notice the inferences):

Input: John went to a restaurant. He sat down. He got mad. He left.

Paraphrase: JOHN WAS HUNGRY. HE DECIDED TO GO TO A RESTAURANT. HE WENT TO ONE. HE SAT DOWN IN A CHAIR. A WAITER DID NOT GO TO THE TABLE. JOHN BECAME UPSET. HE DECIDED HE WAS GOING TO LEAVE THE RESTAURANT. HE LEFT IT.

Scripts allow CD systems to draw links and inferences between things. They are also able to classify and distinguish primitive actions. Kicking someone, for example could be a physical action that institutes 'hurt', while loving could be an emotional expressiong that implies 'affection'.

Machine Translation
Over the past few decades, machine translated texts have gotten better and better. We have not yet reached the stage of producing perfect translations that do not require revisions from professional translators. Coincidentally, there are programs available that can produce draft quality translations. Much progress has been made since the 1950s. Back then, researchers had assumed a simple dictionary translation of words with syntax (grammar) adjustments would do. The result of this folly can be seen in this classic machine-translation tidbit.

Translators must first take into consideration the context of the things being spoken, before actual translation. Machines translation programs likewise, must also do the same, or else they are very likely to fail. While this problem has been partially dealt with by Conceptual Dependency/Representation Theory (Schank's scripts), many programs have difficulty translating slang, or idioms, all of which are usually unique to each individual language & culture. Grammar and punctuation mistakes that users may make also presents another consideration.

SYSTRAN is a machine translation program available on the world wide web. This program was used to translated Generation 5's openning page from english to french, spanish and german. This program provides an excellent look at where machine translation is today. You can test out the program's accuracy by converting text from one language to another, and then converting it back. Here are some interesting translations done by SYSTRAN.

Language Converted	Input	Output
English French English	Robots will one day take over the world by stealing everyone's macaroni and cheese.	The robots one day will succeed the world while stealing each one the macaronis and the cheese.
English Spanish English	More than three-quarters of a million residents and visitors were ordered Tuesday to leave most of the Carolinas' coastline as Hurricane Bonnie accelerated on a path that could carry its fury onto the low-lying Outer Banks island chain.	More than three quarters of million residents and visitors Tuesday was requested to leave most of the line of the coast of the Carolina like Bonnie hurricane accelerated in a way that could take its fury on the external linking under-low-lying of the island of the batteries.
English German English	The spirit is willing but the flesh is weak.	The spirit is ready, but the flesh is weak.
English Italian English	Artificial intelligence. To you, the reader, these very words may bring images of robots hailing from Terminator 2 seeking nothing less of world domination. Otherwise, you're probably wondering about friendlier robots such as R2-D2 or Robbie the Robot. These robots save human lives, cook dinner, wash the dishes, and drive the children to school. Is this science-fiction future possible? or are these fantasies 'just' science fiction? Perhaps someday, these musings could become a reality, but certainly such a future is a long way off.	Artificial intelligence. You, the reader, these same words can carry the images of the robots that more hail from not trying terminal 2 nothing than less of the domination of the world. Otherwise, probabilmentesiete domandandosi iete domandandosi approximately the friendlier robots which R2-D2 or Robbie the robot. These human robots save the screw, lunch of the cook, wash the plates and guide the children to the school. It is this future of possible science-novel? or is these fantasies ' the just ' fantascienza? Perhaps some day, these musings could transformarsi in in a truth, but sure a such future is a long way outside.
English Portuguese English	Besides fantasizing, many people also wonder about machine intelligence. Can machines be intelligent? Will they one day become conscious? Will robots have emotions? (Feel free to cast your votes) Artificial Intelligence is a field of study that cannot do without the important philosophical questions that have perplexed us in the past, and will continue to perplex us. If we wish to learn more about how machines could become sentient, we must first learn about why animals such as us are in the first place. This is perhaps the most important objective for scientists studying AI.	Besides fantasizing, many people also to wonder about machine intelligence. Can machines be intelligent? Will they one day become conscious? Will robots have emotions? (Feel free you cast your you vote) Artificial Intelligence is field of study that cannot of without the important philosophical questions that have perplexed US in the past, and will continues you perplex US. If we wish you learn lives about how machines could become sentient, we must first learn about why animals such US ploughs in the first place. This is perhaps the most important objective will be scientists studying AI.

Note that with each conversion, the quality of the translated text degrades. With just one conversion there are twice as less errors than the examples above. As you can see, the quality of texts differ from language to language and paragraph to paragraph. Probably the most impressive translation was the English to Portuguese to English translation. The German translation fared much better than its Russian counterpart. Although these translations are far from perfect, they are clearly very useful (and far better than nothing).