scholarly journals “How Did We Get Here?”: Topic Drift in Online Health Discussions

2016 ◽  
Vol 18 (11) ◽  
pp. e284 ◽  
Author(s):  
Albert Park ◽  
Andrea L Hartzler ◽  
Jina Huh ◽  
Gary Hsieh ◽  
David W McDonald ◽  
...  
Keyword(s):  
Topic Drift

scholarly journals Modeling Topical Relevance for Multi-Turn Dialogue Generation

2020 ◽  
Author(s):  
Hainan Zhang ◽  
Yanyan Lan ◽  
Liang Pang ◽  
Hongshen Chen ◽  
Zhuoye Ding ◽  
...  
Keyword(s):  
Topic Model ◽  
State Of The Art ◽  
Training Dataset ◽  
Common Phenomenon ◽  
New Model ◽  
Sentence Level ◽  
Topic Distribution ◽  
Topic Drift ◽  
Relevant Context ◽  
Customer Services

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.

Multi-task Learning for Multi-turn Dialogue Generation with Topic Drift Modeling

2021 ◽  
Author(s):  
Hongwei Zeng ◽  
Zhenjie Hong ◽  
Jun Liu ◽  
Bifan Wei
Keyword(s):  
Task Learning ◽  
Topic Drift

A Improved Topics Search Algorithm Based on PSO Strategy for Web Mining

2010 ◽  
Vol 439-440 ◽  
pp. 1481-1486
Author(s):  
Hua Qun Zhan
Keyword(s):  
Web Mining ◽  
Search Algorithm ◽  
Pso Algorithm ◽  
Information Collection ◽  
Web Pages ◽  
Web Page ◽  
Content Relevance ◽  
Topic Drift ◽  
Hits Algorithm ◽  
The Web

HITS algorithm assigns same weight to links between Web pages,which results in topic drift. In this paper,a new focused crawling approach based on PSO Algorithm is proposed（PSOHITS）. The method electively seeks out pages that are relevant to a pre-defined set of topics using PSO Algorithm,increases the crawling chance of the web page following the web page with the low content-relevance,and broadens the relevant-searching scope of crawlers.Meanwhile,the hyperlink metadata is used to predict the topic-relevance of the web page pointed and quickens the information crawling. Experiments show that the proposed algorithm can improve relevance ratio by 15%~36%.Furthermore,it can well avoid topic drift and improve the accuracy of information collection. It has important theoretical and practical values for search engines research.

TOPIC TRACKING WITH IMPROVED REPRESENTATION MODEL AND JOINT TRACKING METHOD

2010 ◽  
Vol 08 (06) ◽  
pp. 913-930 ◽  
Author(s):  
XIAOYAN ZHANG ◽  
TING WANG
Keyword(s):  
Evaluation Method ◽  
Topic Model ◽  
Specific Information ◽  
Weighting Method ◽  
Tracking Method ◽  
Representation Model ◽  
New Information ◽  
Topic Drift ◽  
Topic Tracking ◽  
Joint Tracking

Topic tracking is to monitor a stream of stories to find additional stories on a topic identified by several samples. However, the predefined information about a tracked topic does not provide enough information to deal with the new information occurred in the tracking procedure. To overcome this problem, we proposed a joint tracking method using both the topic-specific information from the predefined information and the non-topic-specific information from the data on other topics. Besides, to overcome the limitation of the representation model and the topic drift problem, we have also used two other improvements: a topic-based weighting method is used to measure the features of both tracked topics and single testing stories; a dynamic topic model is extended with the information brought by the incoming related stories and the noise is filtered out with the information in the incoming unrelated stories. The implemented tracking systems are evaluated on the Chinese subset of TDT4 corpus by the TDT2003 evaluation method. The experimental results indicate that the above methods all improve the tracking performance. More importantly, these techniques are complementary to one another and not mutually exclusive.

scholarly journals Research and Implementation of Basic Education Resource Retrieval Strategy Based on the Relationship among Knowledge Points

2018 ◽  
Vol 173 ◽  
pp. 03057
Author(s):  
Zhen Yang
Keyword(s):  
Basic Education ◽  
Keyword Search ◽  
Knowledge Extraction ◽  
Retrieval Strategy ◽  
User Intention ◽  
Retrieval Accuracy ◽  
Search Results ◽  
Topic Drift ◽  
Education Resource ◽  
The Relationship

In order to solve the lack of knowledge relevance and topic drift in traditional keyword search, this paper proposed knowledge extraction strategy based knowledge point association and recognition of user intention based user intention theme map and the mapping from resource to knowledge points strategy .It realized the knowledge sestematic and relevant of the search results and improved the retrieval accuracy.

Detecting topic drift

2009 ◽  
pp. 113-130 ◽  
Author(s):  
Dan Knights ◽  
Mike Mozer ◽  
Nicolas Nicolov
Keyword(s):  
Topic Drift
Sign in / Sign up

Export Citation Format

Share Document