Topic models help users understand large document collections; however, topic
models do not always find the ``right'' topics. While classical probabilistic
and anchor-based topic models have interactive variants to guide models toward
better topics, such interactions are not available for neural topic models such
as the embedded topic model (\abr{etm}). We correct this lacuna by adding an
intuitive interaction to neural topic models: users can label a topic with a
word, and topics are updated so that the topic words are close to the label.
This allows a user to refine topics based on their information need. While,
interactivity is intuitive for \abr{etm}, we extend this framework to work with
other neural topic models as well. We develop an interactive interface which
allows users to interact and relabel topic models as they see fit. We evaluate
our method through a human study, where users can relabel topics to find
relevant documents. Using our method, user labeling improves document rank
scores, helping to find more relevant documents to a given query when compared
to no user labeling.

通过为神经主题模型添加一种直观的交互方式，即用户可以为主题标记一个词语，并更新主题词使其靠近标记词，从而允许用户根据信息需求优化主题，我们的研究方法通过人机研究评估，证明用户标记能够改善文件排序得分，帮助找到更相关的文档。

有标记的交互式主题模型

Labeled Interactive Topic Models

We investigate the problem of sentence-level supporting argument detection
from relevant documents for user-specified claims. A dataset containing claims
and associated citation articles is collected from online debate website
idebate.org. We then manually label sentence-level supporting arguments from
the documents along with their types as study, factual, opinion, or reasoning.
We further characterize arguments of different types, and explore whether
leveraging type information can facilitate the supporting arguments detection
task. Experimental results show that LambdaMART (Burges, 2010) ranker that uses
features informed by argument types yields better performance than the same
ranker trained without type information.

本研究介绍了如何利用 LambdaMART 排名算法和特征类型信息来检测来自相关文档的用户声明的句子级支持论点，实验结果表明使用特征类型信息的 LambdaMART 排名器优于没有使用类型信息的排名器。