Related papers: Introducing Syntactic Structures into Target Opini…

In this project, we aim to build a Text-to-Speech system able to produce speech with a controllable emotional expressiveness. We propose a methodology for solving this problem in three main steps. The first is the collection of emotional…

Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…

In Data-Oriented Parsing (DOP), an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new input sentence is constructed by combining sub-analyses from the corpus in the most probable way. This…

Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline and integrated methods fail to precisely model the innate…

Aspect-Opinion Pair Extraction (AOPE) and Aspect Sentiment Triplet Extraction (ASTE) have drawn growing attention in NLP. However, most existing approaches extract aspects and opinions independently, optionally adding pairwise relations,…

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots, and values. As we move towards adaptable dialogue…

Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues.…

The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint…

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…

Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily…

Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent…

Aspect-based Sentiment Analysis (ABSA) is a task whose objective is to classify the individual sentiment polarity of all entities, called aspects, in a sentence. The task is composed of two subtasks: Aspect Term Extraction (ATE), identify…

The Web has become the main platform where people express their opinions about entities of interest and their associated aspects. Aspect-Based Sentiment Analysis (ABSA) aims to automatically compute the sentiment towards these aspects from…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Due to the dynamic nature of human language, automatic speech recognition (ASR) systems need to continuously acquire new vocabulary. Out-Of-Vocabulary (OOV) words, such as trending words and new named entities, pose problems to modern ASR…

Acoustic word embeddings (AWEs) are vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding space. In addition to their use in speech technology applications such as spoken term…

It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic.…

Aspect term extraction aims to extract aspect terms from review texts as opinion targets for sentiment analysis. One of the big challenges with this task is the lack of sufficient annotated data. While data augmentation is potentially an…

Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method is a popular approach to addressing this task, which…