Related papers: BBScoreV2: Learning Time-Evolution and Latent Alig…

Latent Dirichlet Allocation (LDA) mining thematic structure of documents plays an important role in nature language processing and machine learning areas. However, the probability distribution from LDA only describes the statistical…

This work considers stationary vector count time series models defined via deterministic functions of a latent stationary vector Gaussian series. The construction is very general and ensures a pre-specified marginal distribution for the…

Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models. However, such feedback is known to introduce systematic biases into the training process and it obscures a…

Effective user modeling requires distinguishing between short-term and long-term preference evolution. While item embeddings have become a key component of recommender systems, standard approaches like Item2Vec treat user histories as…

Recent advances in retrieval models based on learned sparse representations generated by transformers have led us to, once again, consider score-at-a-time query evaluation techniques for the top-k retrieval problem. Previous studies…

End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…

This paper presents a state-of-the-art solution to the LongEval CLEF 2023 Lab Task 2: LongEval-Classification. The goal of this task is to improve and preserve the performance of sentiment analysis models across shorter and longer time…

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…

Automatic pronunciation evaluation plays an important role in pronunciation training and second language education. This field draws heavily on concepts from automatic speech recognition (ASR) to quantify how close the pronunciation of…

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts…

Current sentence embedding evaluations typically rely on static test beds like the Massive Text Embedding Benchmark (MTEB). While invaluable, repeated tuning on a fixed suite can inflate reported scores and obscure real-world robustness. We…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Latent variable models have been a preferred choice in conversational modeling compared to sequence-to-sequence (seq2seq) models which tend to generate generic and repetitive responses. Despite so, training latent variable models remains to…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

Deep directed generative models have attracted much attention recently due to their expressive representation power and the ability of ancestral sampling. One major difficulty of learning directed models with many latent variables is the…

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…

Modeling nonstationary processes is of paramount importance to many scientific disciplines including environmental science, ecology, and finance, among others. Consequently, flexible methodology that provides accurate estimation across a…