Related papers: Automatically Generating Engaging Presentation Sli…
Recently, ``textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In…
Presentation slides are a primary medium for data-driven reporting, yet keeping complex, analytics-style decks up to date remains labor-intensive. Existing automation methods mostly follow fixed template filling and cannot support dynamic…
Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…
Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…
This paper describes a system that generates speaker-annotated transcripts of meetings by using a microphone array and a 360-degree camera. The hallmark of the system is its ability to handle overlapped speech, which has been an unsolved…
Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in…
Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization…
Templates serve as a good starting point to implement a design (e.g., banner, slide) but it takes great effort from designers to manually create. In this paper, we present Desigen, an automatic template creation pipeline which generates…
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare…
Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting in severe sparsity that undermines the effectiveness of…
We present a tool for reasoning in and about propositional sequent calculi. One aim is to support reasoning in calculi that contain a hundred rules or more, so that even relatively small pen and paper derivations become tedious and error…
The objective of stylized speech-driven facial animation is to create animations that encapsulate specific emotional expressions. Existing methods often depend on pre-established emotional labels or facial expression templates, which may…
Hierarchies of concepts are useful in many applications from navigation to organization of objects. Usually, a hierarchy is created in a centralized manner by employing a group of domain experts, a time-consuming and expensive process. The…
Interactive documents help readers engage with complex ideas through dynamic visualization, interactive animations, and exploratory interfaces. However, creating such documents remains costly, as it requires both domain expertise and web…
Academic presentation videos have become an essential medium for research communication, yet producing them remains highly labor-intensive, often requiring hours of slide design, recording, and editing for a short 2 to 10 minutes video.…
Despite the significant improvements that representation learning via self-supervision has led to when learning from unlabeled data, no methods exist that explain what influences the learned representation. We address this need through our…
Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process, today's language models are trained to generate only the…
Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic…
Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…
Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…