ACL
2008
13 years 6 months ago
2008
This paper presents an approach to text categorization that i) uses no machine learning and ii) reacts on-the-fly to unknown words. These features are important for categorizing B...
ACL
2008
13 years 6 months ago
2008
We show that question-based sentence fusion is a better defined task than generic sentence fusion (Q-based fusions are shorter, display less variety in length, yield more identica...
ACL
2008
13 years 6 months ago
2008
Current statistical speech translation approaches predominantly rely on just text transcripts and do not adequately utilize the rich contextual information such as conveyed throug...
ACL
2008
13 years 6 months ago
2008
The omnipresence of unknown words is a problem that any NLP component needs to address in some form. While there exist many established techniques for dealing with unknown words i...
ACL
2008
13 years 6 months ago
2008
Earlier work in parsing Arabic has speculated that attachment to construct state constructions decreases parsing performance. We make this speculation precise and define the probl...
ACL
2008
13 years 6 months ago
2008
Frequency counts from very large corpora, such as the Web 1T dataset, have recently become available for language modeling. Omission of low frequency n-gram counts is a practical ...
ACL
2008
13 years 6 months ago
2008
This paper studies the impact of written language variations and the way it affects the capitalization task over time. A discriminative approach, based on maximum entropy models, ...
ACL
2008
13 years 6 months ago
2008
Finding temporal and causal relations is crucial to understanding the semantic structure of a text. Since existing corpora provide no parallel temporal and causal annotations, we ...
ACL
2008
13 years 6 months ago
2008
This paper describes an extractive summarizer for educational science content called COGENT. COGENT extends MEAD based on strategies elicited from an empirical study with domain a...
ACL
2008
13 years 6 months ago
2008
We use an EM algorithm to learn user models in a spoken dialog system. Our method requires automatically transcribed (with ASR) dialog corpora, plus a model of transcription error...