Sciweavers

ACL
2004
14 years 29 days ago
Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Brian Roark, Murat Saraclar, Michael Collins, Mark...
ACL
2004
14 years 29 days ago
Learning to Resolve Bridging References
We use machine learning techniques to find the best combination of local focus and lexical distance features for identifying the anchor of mereological bridging references. We fin...
Massimo Poesio, Rahul Mehta, Axel Maroudas, Janet ...
ACL
2004
14 years 29 days ago
Balancing Clarity and Efficiency in Typed Feature Logic Through Delaying
The purpose of this paper is to re-examine the balance between clarity and efficiency in HPSG design, with particular reference to the design decisions made in the English Resourc...
Gerald Penn
ACL
2004
14 years 29 days ago
Mining Metalinguistic Activity in Corpora to Create Lexical Resources Using Information Extraction Techniques: the MOP System
This paper describes and evaluates MOP, an IE system for automatic extraction of metalinguistic information from technical and scientific documents. We claim that such a system ca...
Carlos Rodríguez Penagos
ACL
2004
14 years 29 days ago
A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
Sentiment analysis seeks to identify the viewpoint(s) underlying a text span; an example application is classifying a movie review as "thumbs up" or "thumbs down&qu...
Bo Pang, Lillian Lee
ACL
2004
14 years 29 days ago
An Alternative Method of Training Probabilistic LR Parsers
We discuss existing approaches to train LR parsers, which have been used for statistical resolution of structural ambiguity. These approaches are nonoptimal, in the sense that a c...
Mark-Jan Nederhof, Giorgio Satta
ACL
2004
14 years 29 days ago
Probabilistic Parsing Strategies
We present new results on the relation between context-free parsing strategies and their probabilistic counter-parts. We provide a necessary condition and a sufficient condition f...
Mark-Jan Nederhof, Giorgio Satta
ACL
2004
14 years 29 days ago
Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank
In this paper we present a methodology for extracting subcategorisation frames based on an automatic LFG f-structure annotation algorithm Penn-II Treebank. We extract abstract syn...
Ruth O'Donovan, Michael Burke, Aoife Cahill, Josef...
ACL
2004
14 years 29 days ago
Error Mining for Wide-Coverage Grammar Engineering
Parsing systems which rely on hand-coded linguistic descriptions can only perform adequately in as far as these descriptions are correct and complete. The paper describes an error...
Gertjan van Noord
ACL
2004
14 years 29 days ago
Multi-Engine Machine Translation with Voted Language Model
The paper describes a particular approach to multiengine machine translation (MEMT), where we make use of voted language models to selectively combine translation outputs from mul...
Tadashi Nomoto