TAILIEUCHUNG - Báo cáo khoa học: "Automatic Segmentation of Multiparty Dialogue"

In this paper, we investigate the problem of automatically predicting segment boundaries in spoken multiparty dialogue. We extend prior work in two ways. We first apply approaches that have been proposed for predicting top-level topic shifts to the problem of identifying subtopic boundaries. We then explore the impact on performance of using ASR output as opposed to human transcription. | Automatic Segmentation of Multiparty Dialogue Pei-Yun Hsueh School of Informatics University of Edinburgh Edinburgh EH8 9LW Gb Johanna D. Moore School of Informatics University of Edinburgh Edinburgh EH8 9LW GB Steve Renals School of Informatics University of Edinburgh Edinburgh EH8 9LW GB Abstract In this paper we investigate the problem of automatically predicting segment boundaries in spoken multiparty dialogue. We extend prior work in two ways. We first apply approaches that have been proposed for predicting top-level topic shifts to the problem of identifying subtopic boundaries. We then explore the impact on performance of using ASR output as opposed to human transcription. Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks 1 for predicting subtopic boundaries the lexical cohesion-based approach alone can achieve competitive results 2 for predicting top-level boundaries the machine learning approach that combines lexical-cohesion and conversational features performs best and 3 conversational cues such as cue phrases and overlapping speech are better indicators for the toplevel prediction task. We also find that the transcription errors inevitable in ASR output have a negative impact on models that combine lexical-cohesion and conversational features but do not change the general preference of approach for the two tasks. 1 Introduction Text segmentation . determining the points at which the topic changes in a stream of text plays an important role in applications such as topic detection and tracking summarization automatic genre detection and information retrieval and extraction Pevzner and Hearst 2002 . In recent work researchers have applied these techniques to corpora such as newswire feeds transcripts of radio broadcasts and spoken dialogues in order to facilitate browsing information retrieval and topic detection Allan et al.

• Báo cáo khoa học
• Automatic Segmentation
• Multiparty Dialogue
• Pei Yun Hsueh
• scientific reports
• model language
• process natural language
• Automatic Adaptation of Annotation Standards
• Chinese Word Segmentation and POS Tagging
• A Case Study
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Automatic Story Segmentation
• Bayesian Decision Framework
• Statistical Models
• Lexical Chain Features
• The utility of parse derived features
• automatic discourse segmentation
• Seeger Fisher and Brian Roark
• mô hình ngôn ngữ
• Luận án Tiến sĩ
• Atomic and nuclear physics
• Luận án Tiến sĩ Vật lý
• Spect CT images segmentation software
• Automatic detection
• Brain tumors
• Supervised Texture Classification
• Medical Image Segmentation
• Color Fundus Photographs
• Pancreatic Tumors
• Computed Tomography
• Intravascular
• BMC Bioinformatics
• Invasive monitoring
• Intracerebral electrodes
• Stereo Electroencephalography
• Muscle image segmentation
• Cloud computing
• Multi core programming
• Muscle cell segmentation
• 3D laserscanning
• High throughput
• Plant phenotyping
• Deep learning
• Instance segmentation
• Head circumference
• Mask RCNN
• Segmentation system
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• Color enhancement
• Human vision model
• Image processing
• Image segmentation
• Artificial intelligence
• Histochemical image analysis
• Epileptic zone detections
• Medical imaging
• Environmental sciences
• Earth sciences
• Optical Remote Sensing
• Landsat 8 OLI
• Automatic cloud detection
• Open Data Cube
• the electrocardiography images as a tool to identify heart diseases
• Tool to identify heart diseases
• The electrocardiography images
• Automatic detection of heart disease
• The recorded ECG is time consuming