Articles

Language modeling (LM) involves determining the joint probability of words in a sentence. The conditional approach is dominant, representing the joint probability in terms of conditionals. Examples include n-gram LMs and neural network LMs. An alternative approach, called the random field (RF) approach, is used in whole-sentence maximum entropy (WSME) …...

Latent variable topic models such as La- tent Dirichlet Allocation (LDA) can dis- cover topics from text in an unsupervised fashion. However, scaling the models up to the many distinct topics exhibited in modern corpora is challenging. “Flat” topic models like LDA have difficulty modeling sparsely expressed topics, and richer …...

Extra-linguistic factors influence language use, and are accounted for by speakers and listeners. Most natural language pro- cessing (NLP) tasks to date, however, treat language as uniform. This assump- tion can harm performance. We investi- gate the effect of including demographic information on performance in a variety of text-classification tasks. …...

In order to build psycholinguistic mod- els of processing difficulty and evaluate these models against human data, we need highly accurate language models. Here we specifically consider surprisal, a word’s predictability in context. Existing ap- proaches have mostly used n-gram models or more sophisticated syntax-based pars- ing models; this largely …...

Meaning of a word varies from one do- main to another. Despite this impor- tant domain dependence in word seman- tics, existing word representation learning methods are bound to a single domain. Given a pair of source-target domains, we propose an unsupervised method for learning domain-specific word representa- tions that …...

Semantic representation lies at the core of several applications in Natural Language Processing. However, most existing se- mantic representation techniques cannot be used effectively for the representation of individual word senses. We put for- ward a novel multilingual concept repre- sentation, called MUFFIN, which not only enables accurate representation of …...

Traditional approaches to word sense dis- ambiguation (WSD) rest on the assump- tion that there exists a single, unambigu- ous communicative intention underlying every word in a document. However, writ- ers sometimes intend for a word to be in- terpreted as simultaneously carrying mul- tiple distinct meanings. This deliberate use …...

Stubs on Wikipedia often lack comprehen- sive information. The huge cost of edit- ing Wikipedia and the presence of only a limited number of active contributors curb the consistent growth of Wikipedia. In this work, we present WikiKreator, a system that is capable of generating content au- tomatically to improve …...

Our research focuses on the multilin- gual enhancement of ontologies that, of- ten represented only in English, need to be translated in different languages to en- able knowledge access across languages. Ontology translation is a rather different task then the classic document translation, because ontologies contain highly specific vocabulary and …...

In this paper, we first explore the role of inter-annotator agreement statistics in grammatical error correction and conclude that they are less informative in fields where there may be more than one correct answer. We next created a dataset of 50 student essays, each corrected by 10 dif- ferent annotators …...

Knowledge graphs are useful resources for numerous AI applications, but they are far from completeness. Previous work such as TransE, TransH and TransR/CTransR re- gard a relation as translation from head en- tity to tail entity and the CTransR achieves state-of-the-art performance. In this pa- per, we propose a more …...

In this paper we present a formal compu- tational framework for modeling manip- ulation actions. The introduced formal- ism leads to semantics of manipulation ac- tion and has applications to both observ- ing and understanding human manipula- tion actions as well as executing them with a robotic mechanism (e.g. a …...

The path ranking algorithm (PRA) has been recently proposed to address relational classification and retrieval tasks at large scale. We describe Cor-PRA, an enhanced system that can model a larger space of relational rules, including longer relational rules and a class of first order rules with constants, while maintaining scalability. …...

Identifying negative or speculative narra- tive fragments from fact is crucial for natural language processing (NLP) appli- cations. Previous studies on negation and speculation identification in Chinese lan- guage suffers much from two problems: corpus scarcity and the bottleneck in fun- damental Chinese information processing. To resolve these problems, this …...

In the current fast-paced world, people tend to possess limited knowledge about things from the past. For example, some young users may not know that Walkman played similar func- tion as iPod does nowadays. In this paper, we approach the temporal correspondence prob- lem in which, given an input term …...

We study the application of word embed- dings to generate semantic representations for the domain adaptation problem of re- lation extraction (RE) in the tree kernel- based method. We systematically evaluate various techniques to generate the seman- tic representations and demonstrate that they are effective to improve the general- ization …...

Relation classification is an important se- mantic processing task for which state-of- the-art systems still rely on costly hand- crafted features. In this work we tackle the relation classification task using a convo- lutional neural network that performs clas- sification by ranking (CR-CNN). We pro- pose a new pairwise ranking …...

Aspect extraction and sentiment analysis of reviews are both important tasks in opinion mining. We propose a novel senti- ment and aspect extraction model based on Restricted Boltzmann Machines to jointly address these two tasks in an unsupervised setting. This model reflects the gener- ation process of reviews by introducing …...

Extracted keyphrases can enhance numer- ous applications ranging from search to tracking the evolution of scientific dis- course. We present SCHBASE, a hier- archical database of keyphrases extracted from large collections of scientific liter- ature. SCHBASE relies on a tendency of scientists to generate new abbrevia- tions that “extend” existing …...

In this paper, we present a novel approach to joint word sense disambiguation (WSD) and entity linking (EL) that combines a set of complementary objectives in an exten- sible multi-objective formalism. During disambiguation the system performs con- tinuous optimization to find optimal prob- ability distributions over candidate senses. The performance …...