Videos tagged with Natural Language Processing

In this talk I'll outline our work at the University of Edinburgh to model machine translation (MT) as a probabilistic machine learning problem. Although MT systems have made large gains in translation quality in recent years, most current approaches are based on a hand engineered pipeline of disparate models linked by heuristics. I'll motivate why MT provides an interesting, but hard, structur...

Many problems in Natural Language Processing (NLP) involves an efficient search for the best derivation over (exponentially) many candidates, especially in parsing and machine translation. In these cases, the concept of "packed forest" provides a compact representation of the huge search spaces, where efficient inference algorithms based on Dynamic Programming (DP) are possible. In th...

Reproducing an act with sensorimotor means and using fine natural language for communicating the intentionality behind the act is what Aristotle called "Poetics". POETICON explores the "poetics of everyday life", i.e. the synthesis of sensorimotor representations and natural language in everyday human interaction. This is related to an old problem in Artificial Intelligence ...

Modeling human sentence-processing can help us both better understand how the brain processes language, and also help improve user interfaces. For example, our systems could compare different (computer-generated) sentences and produce ones that are easiest to understand. I will talk about my work on evaluating theories about syntactic processing difficulty on a large eye-tracking corpus, and pr...

Ken Ingham, Ph.D. will describe the architecture and motivation behind the development of Amazability, Inc.'s Adept1 product. The Adept1 performs natural language analysis and interprets spoken words and phrases or typed input. It accepts and interprets verbal commands and responds with high quality speech. The Adept1 is equipped with voice recognition and text-to-speech output that dynamically...

We develop a morphological learner that evaluates evidence supporting specific claims that a string of letters is a distributional meaningful unit. The distributional evidence is evaluated by selectional properties of morphs, while evidence towards meaning is modelled by looking at the relationship between stems and words. To assess a proposed affix, it gets a probability measure of meaning by ...

Two approaches to Textual Entailment are presented. They both rely on lexico-syntactic information. The two approaches differ mainly in the way the syntactic relationships are derived. In one approach, the syntactic relationships are drawn from a phrase-based parse tree. In the other, we use information provided by a dependency parser. The first approach performs at 0.59 precision and 0.6047 av...

We introduce a new system for recognizing textual entailment (known as GROUNDHOG) which utilizes a classification-based approach to combine lexico-semantic information derived from text processing applications with a large collection of paraphrases acquired automatically from the WWW. Trained on 200,000 examples of textual entailment extracted from newswire corpora, our system managed to classi...

Most of text categorization techniques are based on word and/or phrase analysis of the text. Statistical analysis of a term frequency captures the importance of the term within a document only. However, two terms can have the same frequency in their documents, but one term contributes more to the meaning of its sentences than the other term. Thus, the underlying model should indicate terms that...