Qi Zhang - Academia.edu (original) (raw)

Papers by Qi Zhang

Interspeech 2006, 2006

Spoken dialogue interfaces, mostly command-and-control, become more visible in applications where... more Spoken dialogue interfaces, mostly command-and-control, become more visible in applications where attention needs to be shared with other tasks, such as driving a car. The deployment of the simple dialog systems, instead of more sophisticated ones, is partly because the computing platforms used for such tasks have been less powerful and partly because certain issues from these cognitively challenging tasks have not been well addressed even in the most advanced dialog systems. This paper reports the progress of our research effort in developing a robust, wide-coverage, and cognitive load-sensitive spoken dialog interface called CHAT: Conversational Helper for Automotive Tasks. Our research in the past few years has led to promising results, including high task completion rate, dialog efficiency, and improved user experience.

Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06, 2006

Recent developments in statistical modeling of various linguistic phenomena have shown that addit... more Recent developments in statistical modeling of various linguistic phenomena have shown that additional features give consistent performance improvements. Quite often, improvements are limited by the number of features a system is able to explore. This paper describes a novel progressive training algorithm that selects features from virtually unlimited feature spaces for conditional maximum entropy (CME) modeling. Experimental results in edit region identification demonstrate the benefits of the progressive feature selection (PFS) algorithm: the PFS algorithm maintains the same accuracy performance as previous CME feature selection algorithms (e.g., Zhou et al., 2003) when the same feature spaces are used. When additional features and their combinations are used, the PFS gives 17.66% relative improvement over the previously reported best result in edit region identification on Switchboard corpus (Kahn et al., 2005), which leads to a 20% relative error reduction in parsing the Switchboard corpus when gold edits are used as the upper bound.

Proceedings of HLT/EMNLP on Interactive Demonstrations -, 2005

Proceedings of the Ninth International Workshop on Parsing Technology - Parsing '05, 2005

This paper describes our effort on the task of edited region identification for parsing disfluent... more This paper describes our effort on the task of edited region identification for parsing disfluent sentences in the Switchboard corpus. We focus our attention on exploring feature spaces and selecting good features and start with analyzing the distributions of the edited regions and their components in the targeted corpus. We explore new feature spaces of a partof-speech (POS) hierarchy and relaxed for rough copy in the experiments. These steps result in an improvement of 43.98% percent relative error reduction in F-score over an earlier best result in edited detection when punctuation is included in both training and testing data [Charniak and Johnson 2001], and 20.44% percent relative error reduction in F-score over the latest best result where punctuation is excluded from the training and testing data [Johnson and Charniak 2004].

This paper describes our participation in the opinion retrieval task at Blog Track 07. The system... more This paper describes our participation in the opinion retrieval task at Blog Track 07. The system consisted of the preprocess part, the topic retrieval part and sentiment analysis part. In the topic retrieval part, we adopted pseudo-relevance feedback and a novel approach to form a modified query. In the sentiment analysis part, each blog post was given an opinion score based on the sentences contained in this post. The subjectivity of each sentence was predicted by a CME classifier. Then the blog posts were reranked based on the similarity given by the topic retrieval and the opinion score given by the sentiment analysis.

Interspeech 2006, 2006

Spoken dialogue interfaces, mostly command-and-control, become more visible in applications where... more Spoken dialogue interfaces, mostly command-and-control, become more visible in applications where attention needs to be shared with other tasks, such as driving a car. The deployment of the simple dialog systems, instead of more sophisticated ones, is partly because the computing platforms used for such tasks have been less powerful and partly because certain issues from these cognitively challenging tasks have not been well addressed even in the most advanced dialog systems. This paper reports the progress of our research effort in developing a robust, wide-coverage, and cognitive load-sensitive spoken dialog interface called CHAT: Conversational Helper for Automotive Tasks. Our research in the past few years has led to promising results, including high task completion rate, dialog efficiency, and improved user experience.

Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06, 2006

Recent developments in statistical modeling of various linguistic phenomena have shown that addit... more Recent developments in statistical modeling of various linguistic phenomena have shown that additional features give consistent performance improvements. Quite often, improvements are limited by the number of features a system is able to explore. This paper describes a novel progressive training algorithm that selects features from virtually unlimited feature spaces for conditional maximum entropy (CME) modeling. Experimental results in edit region identification demonstrate the benefits of the progressive feature selection (PFS) algorithm: the PFS algorithm maintains the same accuracy performance as previous CME feature selection algorithms (e.g., Zhou et al., 2003) when the same feature spaces are used. When additional features and their combinations are used, the PFS gives 17.66% relative improvement over the previously reported best result in edit region identification on Switchboard corpus (Kahn et al., 2005), which leads to a 20% relative error reduction in parsing the Switchboard corpus when gold edits are used as the upper bound.

Proceedings of HLT/EMNLP on Interactive Demonstrations -, 2005

Proceedings of the Ninth International Workshop on Parsing Technology - Parsing '05, 2005

This paper describes our effort on the task of edited region identification for parsing disfluent... more This paper describes our effort on the task of edited region identification for parsing disfluent sentences in the Switchboard corpus. We focus our attention on exploring feature spaces and selecting good features and start with analyzing the distributions of the edited regions and their components in the targeted corpus. We explore new feature spaces of a partof-speech (POS) hierarchy and relaxed for rough copy in the experiments. These steps result in an improvement of 43.98% percent relative error reduction in F-score over an earlier best result in edited detection when punctuation is included in both training and testing data [Charniak and Johnson 2001], and 20.44% percent relative error reduction in F-score over the latest best result where punctuation is excluded from the training and testing data [Johnson and Charniak 2004].

This paper describes our participation in the opinion retrieval task at Blog Track 07. The system... more This paper describes our participation in the opinion retrieval task at Blog Track 07. The system consisted of the preprocess part, the topic retrieval part and sentiment analysis part. In the topic retrieval part, we adopted pseudo-relevance feedback and a novel approach to form a modified query. In the sentiment analysis part, each blog post was given an opinion score based on the sentences contained in this post. The subjectivity of each sentence was predicted by a CME classifier. Then the blog posts were reranked based on the similarity given by the topic retrieval and the opinion score given by the sentiment analysis.