Top Challenges in Computational Linguistics

The field of computational linguistics has a long list of unsolved problems that have been challenging linguists all around the world for decades now. Disciplines like Natural Language Processing (NLP) and Machine Translation (MT), as well as speech technologies like Automatic Speech Recognition (ASR) and Text-To-Speech (TTS), despite having proved successful in the past few years, still lack the naturalness that is inherent to human communication.

Before delving into the challenges faced within the field of Computational Linguistics, we must first understand its definition.

What is Computational Linguistics?

Computational linguistics explores the ways machines can automatically process and interpret natural human language. Research in this area focuses on dealing with logical and mathematical characteristics of natural language to develop algorithms and models for language processing, machine translation of languages and the simulation of artificial intelligence.

Computers process human language in nearly every industry. Computational linguistics develops and analyzes the methods that facilitate these processes. It also looks at the nature of a language, such as fundamental linguistic issues morphology and syntax to more complex applications such as translation or assessing the accuracy of certain statements.

Models are drawn from these analyses that help machines handle language more efficiently. Computational linguistics is a key contributor to the development of artificial intelligence and applications that enable machines to simulate human conversations as realistically as possible.

Top Challenges of Computational Linguistics

Among the many actual challenges still to be solved by computational linguists, it is worth highlighting some significant ones that need solving and that will subsequently play a major role in future advancements within the field:

Input Level

Difficulties in speech recognition systems are mainly caused by variations in terms of accents; use of spontaneous speech; differences in articulation, volume, speed, etc.; acoustic conditions, and quite many others.

Understanding Level

Morphological and syntactic phenomena such as ellipsis and anaphora resolution present challenges at NLU level and are active areas of research.

Word-Sense Disambiguation (WSD), aiming at the selection of one single meaning for an ambiguous word, is one of the most popular open issues in linguistics, for it has a huge impact on the accuracy of search engines.

Dialog Level

Context disambiguation, social intelligence, interpretation of spontaneous gestures, etc. are some of the current gaps (to different extents) at discourse level.

Output Level

Far beyond achievements in speech synthesis there still remain challenges like conferring human-like capabilities to embodied agents (in terms of appearance, non-verbal communication, etc.).

Computational Linguistics Problems in Virtual Assistants

Virtual Assistants (VAs) are a composite gathering of quite many different sub-fields across computational linguistics, that’s why they still lack completeness. Weak points in the above disciplines are most visible in a VA, which can be thought of as one of the most complex front-ends of applied computational linguistics.

Pure linguistic issues holding back overt success for all kinds of NLP-based applications may range from pronunciation and accent variation in speech recognition to context disambiguation and anaphora resolution at discourse level.

When brought together, the different components in a VA (and/or dialog system) are so interdependent that a minor error on one of its sides might lead to poor results and behavior from the natural language and dialog management ends.

Imagine your different reactions to the phrase, “that’s speech recognition,” if it was interpreted as “that’s peach wreck in kitchen”. Now, imagine what an NLU model would get out of these diverse phrases. Can you also manage how a wrong interpretation would affect a dialog manager?

Fortunately, the best Conversational AI platforms can find solutions to these problems.

Solving Computational Linguistics Problems on your VA

Teneo benefits from extensive experience both in the field of Research & Development and the world of professional services. It’s a powerful symbiosis between analysis and pragmatism.

With tools like Teneo Studio at our service, Conversational AI Developers (as well as customers themselves) are now able to build robust, cross-platform applications, having the chance to easily address some of these difficulties.

A profound familiarity with these widely claimed linguistic problems, from both developers’ and linguists’ perspectives, make Teneo’s array of linguistic tools and resources highly promising and functional.

I want to believe that we are ready to take up the challenge. What’s more, customers are now ready to take up the challenge with us too.

Do YOU want to take up the challenge?

UPCOMING WEBINAR

How to Develop Scalable Multilingual Conversational AI Applications Quick & Easy

December 17 at 11am CET

Register Here

Carmen Del Solar is currently working as a Computational Linguist in the Information Technologies Sector. After +10 years of industry experience in Spain, she relocated to the USA in 2017. She is currently based in Chicago (Illinois), working as a Conversational AI Engineer at Artificial Solutions Inc. Carmen holds a B.S. in Linguistics and a M.A. in Applied Linguistics. She spent the first year of her Graduate studies as a visiting student at the Department of Linguistics at the University of Pennsylvania, USA. Her interests include NLP, Dialogue Systems, Human-Computer Interaction, ML and Data Science.

Leave a Reply

Your email address will not be published. Required fields are marked *