A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Dialogue Session Segmentation by Embedding-Enhanced TextTiling
[article]
2016
arXiv
pre-print
Preserved Fulltext
We propose an embedding-enhanced TextTiling approach, inspired by the observation that conversation utterances are highly noisy, and that word embeddings provide a robust way of capturing semantics. ...
However, it is unwise to track all previous utterances in the current session as not all of them are equally important. In this paper, we address the problem of session segmentation. ...
In our study, we prefer the simple yet effective TextTiling approach for open-domain dialogue session segmentation, but enhance it with modern advances of word embeddings, which are robust in capturing ...
arXiv:1610.03955v1
fatcat:khvjezh2fzezlmhhlzbeecs3wa
Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. ...
In this work, we address this limitation by leveraging supervisory signals from the utterance-pair coherence scoring task. ...
This research was supported by the Language & Speech Innovation Lab of Cloud BU, Huawei Technologies Co., Ltd. ...
arXiv:2106.06719v1
fatcat:fwutddbpw5ej3pvuhzliegkumm
A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We propose a reinforcement learning (RL) method for topic segmentation and labeling in goal-oriented dialogues, which aims to detect topic boundaries among dialogue utterances and assign topic labels to ...
Topic structure analysis plays a pivotal role in dialogue understanding. ...
Embedding enhanced TextTiling works much better since word embedding can well capture the semantic similarity. ...
doi:10.24963/ijcai.2018/612
dblp:conf/ijcai/TakanobuHZLCZN18
fatcat:xh7266632jfrjbsfoa67pdfimu
Experiments with interactive question-answering
2005
Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
questions into the context of a Q/A dialogue. ...
We present experimental results from large user studies (featuring a fully-implemented interactive Q/A system named FERRET) that demonstrates that surprising performance is achieved by integrating predictive ...
As with Approach 2, segments were produced using the TextTiling algorithm. ...
doi:10.3115/1219840.1219866
dblp:conf/acl/HarabagiuHLM05
fatcat:7fcbldwgszfahpcnitjley2dfe
Message from the general chair
2015
2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Our end system outperforms the state-of-the-art baseline by 2 B 3 F1 points on non-transcript portion of the ACE 2004 dataset. ...
and polysemy by learning multiple embeddings per word. ...
This algorithm is based on the well-known TextTiling algorithm, and segments documents using the Latent Dirichlet Allocation (LDA) topic model. ...
doi:10.1109/ispass.2015.7095776
dblp:conf/ispass/Lee15
fatcat:ehbed6nl6barfgs6pzwcvwxria
ACHI 2017 COMMITTEE ACHI Steering Committee
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
ACKNOWLEDGMENTS
ACKNOWLEDGMENT The authors would like to thank Günes ¸Karababa, C ¸agatay Koc ¸and Ege Sarıoglu for the fruitful discussion sessions and their invaluable ideas. ...
This work was supported by JSPS KAKENHI Grant Number JP15K12093. ...
In this system, we emphasized familiarity by embedding context, but it is not perfect. ...
fatcat:tpfwv4cis5hgjbwof45jgpljci
Modeling Users' Information Needs in a Document Recommender for Meetings
2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We also provided an example of the results obtained by our method and the baselines. ...
We used sentence-aligned parallel corpora for training the model used by the Moses and document-aligned parallel corpora for learning multilingual topic models. ...
The ASR transcripts or the subtitles of each lecture of the dataset are segmented using the TextTiling algorithm implemented in the NLTK toolkit (Bird, 2006) . ...
doi:10.5075/epfl-thesis-6760
fatcat:pq5bkum2hffrrp52frgdcxhwzu