Match!
Peter D. Turney
National Research Council
78Publications
38H-index
13.6kCitations
Publications 78
Newest
#1Peter D. TurneyH-Index: 38
#2Saif M. Mohammad (National Research Council)H-Index: 35
We introduce a dataset for studying the evolution of words, constructed from WordNet and the Google Books Ngram Corpus. The dataset tracks the evolution of 4,000 synonym sets (synsets), containing 9,000 English words, from 1800 AD to 2000 AD. We present a supervised learning algorithm that is able to predict the future leader of a synset: the word in the synset that will have the highest frequency. The algorithm uses features based on a word’s length, the characters in the word, and the historic...
#1Carissa Schoenick (Allen Institute for Artificial Intelligence)H-Index: 3
#2Peter Clark (Allen Institute for Artificial Intelligence)H-Index: 33
Last.Oren Etzioni (Allen Institute for Artificial Intelligence)H-Index: 71
view all 5 authors...
Answering questions correctly from standardized eighth-grade science tests is itself a test of machine intelligence.
Feb 12, 2016 in AAAI (National Conference on Artificial Intelligence)
#1Peter Clark (Allen Institute for Artificial Intelligence)H-Index: 33
#2Oren Etzioni (Allen Institute for Artificial Intelligence)H-Index: 71
Last.Daniel Khashabi (UIUC: University of Illinois at Urbana–Champaign)H-Index: 8
view all 7 authors...
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatical...
Jan 1, 2016 in ACL (Meeting of the Association for Computational Linguistics)
#1Sujay Kumar Jauhar (CMU: Carnegie Mellon University)H-Index: 8
#2Peter D. Turney (Allen Institute for Artificial Intelligence)H-Index: 38
Last.Eduard Hovy (CMU: Carnegie Mellon University)H-Index: 66
view all 3 authors...
#1Sujay Kumar JauharH-Index: 8
#2Peter D. TurneyH-Index: 38
Last.Eduard HovyH-Index: 66
view all 3 authors...
We describe two new related resources that facilitate modelling of general knowledge reasoning in 4th grade science exams. The first is a collection of curated facts in the form of tables, and the second is a large set of crowd-sourced multiple-choice questions covering the facts in the tables. Through the setup of the crowd-sourced annotation task we obtain implicit alignment information between questions and tables. We envisage that the resources will be useful not only to researchers working ...
Jan 1, 2016 in ACL (Meeting of the Association for Computational Linguistics)
#1Saif M. Mohammad (National Research Council)H-Index: 35
#2Ekaterina Shutova (UCSD: University of California, San Diego)H-Index: 12
Last.Peter D. Turney (Allen Institute for Artificial Intelligence)H-Index: 38
view all 3 authors...
It is generally believed that a metaphor tends to have a stronger emotional impact than a literal statement; however, there is no quantitative study establishing the extent to which this is true. Further, the mechanisms through which metaphors convey emotions are not well understood. We present the first data-driven study comparing the emotionality of metaphorical expressions with that of their literal counterparts. Our results indicate that metaphorical usages are, on average, significantly mor...
#1Peter D. Turney (National Research Council)H-Index: 38
#2Saif M. Mohammad (National Research Council)H-Index: 35
Inference in natural language often involves recognizing lexical entailment (RLE); that is, identifying whether one word entails another. For example, buy entails own. Two general strategies for RLE have been proposed: One strategy is to manually construct an asymmetric similarity measure for context vectors (directional similarity) and another is to treat RLE as a problem of learning to recognize semantic relations using supervised machine learning techniques (relation classification). In this ...
#1Xiaodan Zhu (National Research Council)H-Index: 25
#2Peter D. Turney (National Research Council)H-Index: 38
Last.André Vellino (U of O: University of Ottawa)H-Index: 8
view all 4 authors...
The importance of a research article is routinely measured by counting how many times it has been cited. However, treating all citations with equal weight ignores the wide variety of functions that citations perform. We want to automatically identify the subset of references in a bibliography that have a central academic influence on the citing paper. For this purpose, we examine the effectiveness of a variety of features for determining the academic influence of a citation. By asking authors to...
Semantic composition is the task of understanding the meaning of text by composing the meanings of the individual words in the text. Semantic decomposition is the task of understanding the meaning of an individual word by decomposing it into various aspects (factors, constituents, components) that are latent in the meaning of the word. We take a distributional approach to semantics, in which a word is represented by a context vector. Much recent work has considered the problem of recognizing com...
#1Saif M. MohammadH-Index: 35
#2Bonnie J. Dorr (UMD: University of Maryland, College Park)H-Index: 35
Last.Peter D. TurneyH-Index: 38
view all 4 authors...
Knowing the degree of semantic contrast between words has widespread application in natural language processing, including machine translation, information retrieval, and dialogue systems. Manually created lexicons focus on opposites, such as hot and cold. Opposites are of many kinds such as antipodals, complementaries, and gradable. Existing lexicons often do not classify opposites into the different kinds, however. They also do not explicitly list word pairs that are not opposites but yet have...
12345678