NAACL
2007
14 years 1 months ago
2007
We present our work on using Wikipedia as a knowledge source for Natural Language Processing. We first describe our previous work on computing semantic relatedness from Wikipedia...
NAACL
2007
14 years 1 months ago
2007
This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Ar...
NAACL
2007
14 years 1 months ago
2007
The work1 we present here is concerned with the acquisition of deep grammatical information for nouns in Spanish. The aim is to build a learner that can handle noise, but, more in...
NAACL
2007
14 years 1 months ago
2007
Texts exhibit subtle yet identifiable modality about writers’ estimation of how true each statement is (e.g., definitely true or somewhat true). This study is an analysis of suc...
NAACL
2007
14 years 1 months ago
2007
NAACL
2007
14 years 1 months ago
2007
We describe the use of meeting metadata, acquired using a computerized meeting organization and note-taking system, to improve automatic transcription of meetings. By applying a t...
NAACL
2007
14 years 1 months ago
2007
We propose a variation of the SO-PMI algorithm for Japanese, for use in Weblog Opinion Mining. SO-PMI is an unsupervised approach proposed by Turney that has been shown to work we...
NAACL
2007
14 years 1 months ago
2007
We present the first known empirical study on speech summarization without lexical features for Mandarin broadcast news. We evaluate acoustic, lexical and structural features as ...
NAACL
2007
14 years 1 months ago
2007
This paper presents empirical results that contradict the prevailing opinion that entity extraction is a boring solved problem. In particular, we consider data sets that resemble ...
NAACL
2007
14 years 1 months ago
2007
This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simula...