Related papers: Thread Reconstruction in Conversational Data using…
As the online world continues its exponential growth, interpersonal communication has come to play an increasingly central role in opinion formation and change. In order to help users better engage with each other online, we study a…
Although pre-trained language models (PLMs) have achieved great success and become a milestone in NLP, abstractive conversational summarization remains a challenging but less studied task. The difficulty lies in two aspects. One is the lack…
Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level…
Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret.…
Discussion forums provide a channel for students to engage with peers and course material outside of class, accessible even to commuter and non-traditional populations. As such, forums can build classroom community as well as aid learning,…
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…
With recent trends indicating cyber crimes increasing in both frequency and cost, it is imperative to develop new methods that leverage data-rich hacker forums to assist in combating ever evolving cyber threats. Defining interactions within…
The proliferation of social media platforms has afforded social scientists unprecedented access to vast troves of data on human interactions, facilitating the study of online behavior at an unparalleled scale. These platforms typically…
Context modeling has a pivotal role in open domain conversation. Existing works either use heuristic methods or jointly learn context modeling and response generation with an encoder-decoder framework. This paper proposes an explicit…
In this paper, we propose a deep, globally normalized topic model that incorporates structural relationships connecting documents in socially generated corpora, such as online forums. Our model (1) captures discursive interactions along…
In practice, developers search for related earlier bugs and their associated discussion threads when faced with a new bug to repair. Typically, these discussion threads consist of comments and even bug-fixing comments intended to capture…
Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to…
The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content. This work presents techniques for classifying linked content spread on forum websites --…
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…
Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, including political science, digital humanities and sociological…
We propose Sentence Level Recurrent Topic Model (SLRTM), a new topic model that assumes the generation of each word within a sentence to depend on both the topic of the sentence and the whole history of its preceding words in the sentence.…
The social Web is a widely used platform for online discussion. Across social media, users can start discussions by posting a topical image, url, or message. Upon seeing this initial post, other users may add their own comments to the post,…
In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework…
In this paper, we present a set of measures to quantify certain properties of threaded discussions, which are ubiquitous in online learn-ing platforms. In particular, we address how to measure the redundancy of posts, the compactness of…
Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve…