Related papers: Stick-Breaking Embedded Topic Model with Continuou…
The society produces textual data online in several ways, e.g., via reviews and social media posts. Therefore, numerous researchers have been working on discovering patterns in textual data that can indicate peoples' opinions, interests,…
Topic discovery in scientific literature provides valuable insights for researchers to identify emerging trends and explore new avenues for investigation, facilitating easier scientific information retrieval. Many machine learning methods,…
In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because previous samples have limited replay value when learning a new task. Prior research has typically…
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…
Topic models are some of the most popular ways to represent textual data in an interpret-able manner. Recently, advances in deep generative models, specifically auto-encoding variational Bayes (AEVB), have led to the introduction of…
Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…
Sentiment analysis (SA) has become an extensive research area in recent years impacting diverse fields including ecommerce, consumer business, and politics, driven by increasing adoption and usage of social media platforms. It is…
Recently, considerable research attention has been paid to network embedding, a popular approach to construct feature vectors of vertices. Due to the curse of dimensionality and sparsity in graphical datasets, this approach has become…
Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network…
Text-speech joint spoken language modeling (SLM) aims at natural and intelligent speech-based interactions, but developing such a system may suffer from modality mismatch: speech unit sequences are much longer than text tokens. Prior work…
Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity…
We present Branch-Train-Merge (BTM), a communication-efficient algorithm for embarrassingly parallel training of large language models (LLMs). We show it is possible to independently train subparts of a new class of LLMs on different…
The proliferation of textual data on the Internet presents a unique opportunity for institutions and companies to monitor public opinion about their services and products. Given the rapid generation of such data, the text stream mining…
Lifelong learning has recently attracted attention in building machine learning systems that continually accumulate and transfer knowledge to help future learning. Unsupervised topic modeling has been popularly used to discover topics from…
Small large language models (sLLMs) offer the advantage of being lightweight and efficient, which makes them suitable for resource-constrained environments. However, sLLMs often struggle to maintain topic consistency in task-oriented…
Following a particular news story online is an important but difficult task, as the relevant information is often scattered across different domains/sources (e.g., news articles, blogs, comments, tweets), presented in various formats and…
Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate…
Most of the information on the Internet is represented in the form of microtexts, which are short text snippets such as news headlines or tweets. These sources of information are abundant, and mining these data could uncover meaningful…
Predictive queries over spatiotemporal (ST) stream data pose significant data processing and analysis challenges. ST data streams involve a set of time series whose data distributions may vary in space and time, exhibiting multiple distinct…
Application for semantic segmentation models in areas such as autonomous vehicles and human computer interaction require real-time predictive capabilities. The challenges of addressing real-time application is amplified by the need to…