Discourse segmentation of multi-party conversation

Xie

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

2010

There has been increasing interest recently in meeting understanding, such as summarization, browsing, action item detection, and topic segmentation. However, there is very limited effort on using rich recognition output (e.g., recognition confidence measure or more recognition candidates) for these downstream tasks. This paper presents an initial study using n-best recognition hypotheses for two tasks, extractive summarization and keyword extraction. We extend the approach used on 1-best output to n-best hypotheses: MMR (maximum marginal relevance) for summarization and TFIDF (term frequency, inverse document frequency) weighting for keyword extraction. Our experiments on the ICSI meeting corpus demonstrate promising improvement using n-best hypotheses over 1-best output. These results suggest worthy future studies using n-best or lattices as the interface between speech recognition and downstream tasks.

Section: Datamentioning

confidence: 99%

Using n-best recognition output for extractive summarization and keyword extraction in meeting speech

Xie

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

2010

2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU)

“…Following Galley et al [34], we have explored two basic approaches to this task [30]. An unsupervised approach, LCSeg, does not require a training set of hand-marked topic boundaries, but can automatically infer topic boundaries as points where the statistics of text change significantly.…”

Section: Topic Segmentationmentioning

confidence: 99%

Recognition and understanding of meetings the AMI and AMIDA projects

Renals

Hain

Bourlard

2007

111

The AMI and AMIDA projects are concerned with the recognition and interpretation of multiparty meetings. Within these projects we have: developed an infrastructure for recording meetings using multiple microphones and cameras; released a 100 hour annotated corpus of meetings; developed techniques for the recognition and interpretation of meetings based primarily on speech recognition and computer vision; and developed an evaluation framework at both component and system levels. In this paper we present an overview of these projects, with an emphasis on speech recognition and content extraction.

Advances in Artificial Intelligence

“…Similarity Features Three features were used which capture the lexical similarity between two comments: TF-IDF, LSA ( [5]) and Lexical Cohesion( [3]). For each comment, each of these three scores was calculated for both the preceding and following comment (0 if there was no comment before or after), giving a total of six similarity features.…”

Section: Featuresmentioning

confidence: 99%

Exploiting Conversational Features to Detect High-Quality Blog Comments

FitzGerald

Carenini

Murray

et al. 2011

Abstract. In this work, we present a method for classifying the quality of blog comments using Linear-Chain Conditional Random Fields (CRFs). This approach is found to yield high accuracy on binary classification of high-quality comments, with conversational features contributing strongly to the accuracy. We also present a new corpus of blog data in conversational form, complete with user-generated quality moderation labels from the science and technology news blog Slashdot.