Sciweavers

NAACL
2007
13 years 9 months ago
Creating a Knowledge Base from a Collaboratively Generated Encyclopedia
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...
Simone Paolo Ponzetto
NAACL
2007
13 years 9 months ago
On using Articulatory Features for Discriminative Speaker Adaptation
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...
Florian Metze
NAACL
2007
13 years 9 months ago
Automatic Acquisition of Grammatical Types for Nouns
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...
Núria Bel, Sergio Espeja, Montserrat Marimo...
NAACL
2007
13 years 9 months ago
Stating with Certainty or Stating with Doubt: Intercoder Reliability Results for Manual Annotation of Epistemically Modalized St
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...
Victoria L. Rubin
NAACL
2007
13 years 9 months ago
Subtree Mining for Relation Extraction from Wikipedia
Dat P. T. Nguyen, Yutaka Matsuo, Mitsuru Ishizuka
NAACL
2007
13 years 9 months ago
Implicitly Supervised Language Model Adaptation for Meeting Transcription
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...
David Huggins-Daines, Alexander I. Rudnicky
NAACL
2007
13 years 9 months ago
Modifying SO-PMI for Japanese Weblog Opinion Mining by Using a Balancing Factor and Detecting Neutral Expressions
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...
Guangwei Wang, Kenji Araki
NAACL
2007
13 years 9 months ago
Speech Summarization Without Lexical Features for Mandarin Broadcast News
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 ...
Jian Zhang, Pascale Fung
NAACL
2007
13 years 9 months ago
Entity Extraction is a Boring Solved Problem - Or is it?
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 ...
Marc Vilain, Jennifer Su, Suzi Lubar
NAACL
2007
13 years 9 months ago
Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System
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...
Jost Schatzmann, Blaise Thomson, Karl Weilhammer, ...