In this paper, we study the problem of summarizing email conversations. We first build a sentence quotation graph that captures the conversation structure among emails. We adopt t...
Entropy Guided Transformation Learning (ETL) is a new machine learning strategy that combines the advantages of decision trees (DT) and Transformation Based Learning (TBL). In thi...
This paper presents a new unsupervised algorithm (WordEnds) for inferring word boundaries from transcribed adult conversations. Phone ngrams before and after observed pauses are u...
This paper describes how external resources can be used to improve parser performance for heavily lexicalised grammars, looking at both robustness and efficiency. In terms of robu...
Online forum discussions often contain vast amounts of questions that are the focuses of discussions. Extracting contexts and answers together with the questions will yield not on...
We take a multi-pass approach to machine translation decoding when using synchronous context-free grammars as the translation model and n-gram language models: the first pass uses...
Paraphrases have proved to be useful in many applications, including Machine Translation, Question Answering, Summarization, and Information Retrieval. Paraphrase acquisition meth...
We outline the problem of ad hoc rules in treebanks, rules used for specific constructions in one data set and unlikely to be used again. These include ungeneralizable rules, erro...