Search By Subject

Relational clustering has received much attention from researchers in the last decade. In this paper we present a parametric method that employs a combination of both hard and soft clustering. Based on the corresponding Markov chain of an affinity ...

We study two approaches to the marking of extra-propositional aspects of statements in text: the task-independent cue-and-scope representation considered in the CoNLL-2010 Shared Task, and the tagged-event representation applied in several recent event ...

We describe a machine learning system based on large margin structure perceptron for unrestricted coreference resolution that introduces two key modeling techniques: latent coreference trees and entropy guided feature induction. The proposed latent tree ...

Online debate forums provide a powerful communication platform for individual users to share information, exchange ideas and express opinions on a variety of topics. Understanding people's opinions in such forums is an important task as its results can ...

Twitter is a micro blogging website, where users can post messages in very short text called Tweets. Tweets contain user opinion and sentiment towards an object or person. This sentiment information is very useful in various aspects for business and ...

Different Bengali TTS systems are already available on a resourceful platform such as a personal computer. However, porting these systems to a resource limited device such as a mobile phone is not an easy task. Practical aspects including application ...

This paper brings a contribution to the field of discourse annotation of corpora. Using ANNODIS, a french corpus annotated with discourse relations by naive and expert annotators, we focus on two of them, Elaboration and Entity-Elaboration. These two ...

It is our pleasure to welcome you to the EMNLP-CoNLL 2012 conference, a joint meeting of the Conference on Empirical Methods in Natural Language Learning (EMNLP) and the Conference on Computational Natural Language Learning (CoNLL). After the successful ...

In sentiment classification, unlabeled user reviews are often free to collect for new products, while sentiment labels are rare. In this case, active learning is often applied to build a high-quality classifier with as small amount of labeled instances ...

As General Chair, I am indeed honored to pen the first words of ACL 2012 proceedings. In the past year, research in computational linguistics has continued to thrive across Asia and all over the world. On this occasion, I share with you the excitement ...

The goal of this paper is to present a first step toward integrating Incremental Speech Recognition (ISR) and Partially-Observable Markov Decision Process (POMDP) based dialogue systems. The former provides support for advanced turn-taking behavior ...

Probabilistic models such as Bayesian Networks are now in widespread use in spoken dialogue systems, but their scalability to complex interaction domains remains a challenge. One central limitation is that the state space of such models grows ...

Datasets that answer difficult clinical questions are expensive in part due to the need for medical expertise and patient informed consent. We investigate the effect of small sample size on the performance of a text categorization algorithm. We show how ...

Evidence Based Medicine (EBM) is the practice of using the knowledge gained from the best medical evidence to make decisions in the effective care of patients. This medical evidence is extracted from medical documents such as research papers. The ...

Language models are a critical component in many speech and natural language processing technologies, such as speech recognition and understanding, voice search, conversational interaction and machine translation. Over the last few decades, several ...

The introduction of large-margin based discriminative methods for optimizing statistical machine translation systems in recent years has allowed exploration into many new types of features for the translation process. By removing the limitation on the ...

This paper addresses the problem of automatic text simplification. Automatic text simplifications aims at reducing the reading difficulty for people with cognitive disability, among other target groups. We describe an automatic text simplification ...

Currently, health care costs associated with aging at home can be prohibitive if individuals require continual or periodic supervision or assistance because of Alzheimer's disease. These costs, normally associated with human caregivers, can be mitigated ...

Most icon-based augmentative and alternative communication (AAC) devices require users to formulate messages in syntactic order in order to produce syntactic utterances. Reliance on syntactic ordering, however, may not be appropriate for individuals ...

Domain adaptation is a time consuming and costly procedure calling for the development of algorithms and tools to facilitate its automation. This paper presents an unsupervised algorithm able to learn the main concepts in event summaries. The method ...