EMNLP
2009
13 years 10 months ago
2009
Distance-based (windowless) word assocation measures have only very recently appeared in the NLP literature and their performance compared to existing windowed or frequency-based ...
EMNLP
2009
13 years 10 months ago
2009
We present the first unsupervised approach to the problem of learning a semantic parser, using Markov logic. Our USP system transforms dependency trees into quasi-logical forms, r...
EMNLP
2009
13 years 10 months ago
2009
Many approaches to unsupervised morphology acquisition incorporate the frequency of character sequences with respect to each other to identify word stems and affixes. This typical...
EMNLP
2009
13 years 10 months ago
2009
Keyphrases are widely used as a brief summary of documents. Since manual assignment is time-consuming, various unsupervised ranking methods based on importance scores are proposed...
EMNLP
2009
13 years 10 months ago
2009
This paper investigates a new task, subjectivity word sense disambiguation (SWSD), which is to automatically determine which word instances in a corpus are being used with subject...
EMNLP
2009
13 years 10 months ago
2009
Information Extraction (IE) systems that extract role fillers for events typically look at the local context surrounding a phrase when deciding whether to extract it. Often, howev...
EMNLP
2009
13 years 10 months ago
2009
In this paper, we investigate how an accurate question classifier contributes to a question answering system. We first present a Maximum Entropy (ME) based question classifier whi...
EMNLP
2009
13 years 10 months ago
2009
In this research we aim to detect subjective sentences in multimodal conversations. We introduce a novel technique wherein subjective patterns are learned from both labeled and un...
EMNLP
2009
13 years 10 months ago
2009
We present an inexact search algorithm for the problem of predicting a two-layered dependency graph. The algorithm is based on a k-best version of the standard cubictime search al...
EMNLP
2009
13 years 10 months ago
2009
This paper explores the use of innovative kernels based on syntactic and semantic structures for a target relation extraction task. Syntax is derived from constituent and dependen...