advertisement

Good, Great, Excellent: Global Inference of Semantic Intensities

100 %
0 %
advertisement
Information about Good, Great, Excellent: Global Inference of Semantic Intensities
Technology

Published on March 12, 2014

Author: gdm3003

Source: slideshare.net

Description

Adjectives like good, great, and excellent are similar in meaning, but differ in intensity. Intensity order information is very useful for language learners as well as in several NLP tasks, but is missing in most lexical resources (dictionaries, WordNet, and thesauri). In this paper, we present a primarily unsupervised approach that uses semantics from Web-scale data (e.g., phrases like good but not excellent) to rank words by assigning them positions on a continuous scale. We rely on Mixed Integer Linear Programming to jointly determine the ranks, such that individual decisions benefit from global information. When ranking English adjectives, our global algorithm achieves substantial improvements over previous work on both pairwise and rank correlation metrics (specifically, 70% pairwise accuracy as compared to only 56% by previous work). Moreover, our approach can incorporate external synonymy information (increasing its pairwise accuracy to 78%) and extends easily to new languages.
advertisement

Add a comment

Related presentations

Presentación que realice en el Evento Nacional de Gobierno Abierto, realizado los ...

In this presentation we will describe our experience developing with a highly dyna...

Presentation to the LITA Forum 7th November 2014 Albuquerque, NM

Un recorrido por los cambios que nos generará el wearabletech en el futuro

Um paralelo entre as novidades & mercado em Wearable Computing e Tecnologias Assis...

Microsoft finally joins the smartwatch and fitness tracker game by introducing the...

Related pages

Good, Great, Excellent: Global Inference of Semantic ...

Good, Great, Excellent: Global Inference of Semantic Intensities Gerard de Melo ICSI, Berkeley demelo@icsi.berkeley.edu Mohit Bansal CS Division, UC Berkeley
Read more

Good, Great, Excellent: Global Inference of Semantic ...

(good, great) (great, good) (small, minute) good , but not great ! 24492.0 not great , just good ! 248.0 small , almost minute ! 97.0 good , if not great ...
Read more

Good, Great, Excellent: Global Inference of Semantic ...

Good, Great, Excellent: Global Inference of Semantic Intensities. This page provides additional information about the paper Good, Great, Excellent: Global ...
Read more

論文感想: "Good, Great, Excellent: Global Inference of ...

Good, Great, Excellent: Global Inference of Semantic Intensities 図表、式は論文中から引用 概要 似た意味の形容詞の強弱の順序 ...
Read more

www1.icsi.berkeley.edu

@article{deMeloBansal2013, author = {Gerard de Melo and Mohit Bansal}, title = {Good, Great, Excellent: Global Inference of Semantic Intensities} ...
Read more

Coreference resolution using semantic relatedness ...

... Coreference resolution using semantic relatedness ... Good, Great, Excellent: Global Inference of ... Intensity order information is very ...
Read more

Mohit Bansal - University of Chicago

Mohit Bansal, David Burkett ... Good, Great, Excellent: Global Inference of Semantic Intensities Gerard de Melo and Mohit Bansal.
Read more

Gerard de Melo

Gerard de Melo (Homepage), ... for our paper Semantic Information Extraction ... Good, Great, Excellent: Global Inference of Semantic Intensities PDF ...
Read more

iiis.tsinghua.edu.cn

@article{deMeloBansal2013Intensities, author = {Gerard de Melo and Mohit Bansal}, title = {Good, Great, Excellent: Global Inference of Semantic Intensities ...
Read more