Related papers: Integrating Syntactic and Prosodic Information for…
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…
This paper proposes an efficient example selection method for example-based word sense disambiguation systems. To construct a practical size database, a considerable overhead for manual sense disambiguation is required. Our method is…
The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…
We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…
This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We…
Modelling compositional meaning for sentences using empirical distributional methods has been a challenge for computational linguists. We implement the abstract categorical model of Coecke et al. (arXiv:1003.4394v1 [cs.CL]) using data from…
The goal of automatic dubbing is to perform speech-to-speech translation while achieving audiovisual coherence. This entails isochrony, i.e., translating the original speech by also matching its prosodic structure into phrases and pauses,…
The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive…
Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…
The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the…
Semantic Noise affects text analytics activities for the domain-specific industries significantly. It impedes the text understanding which holds prime importance in the critical decision making tasks. In this work, we formalize semantic…
Supervised topic models are often sought to balance prediction quality and interpretability. However, when models are (inevitably) misspecified, standard approaches rarely deliver on both. We introduce a novel approach, the…
Soundness and completeness with respect to equational theories for programming languages are fundamental properties in the study of categorical semantics. However, completeness results have not been established for programming languages…
In functional programming, datatypes a la carte provide a convenient modular representation of recursive datatypes, based on their initial algebra semantics. Unfortunately it is highly challenging to implement this technique in proof…
Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several…
This paper concerns the development of metatheory for extensible languages. It uses as its starting point a view that programming languages tailored to specific application domains are to be constructed by composing components from an open…
Recognizing visual entities in a natural language sentence and arranging them in a 2D spatial layout require a compositional understanding of language and space. This task of layout prediction is valuable in text-to-image synthesis as it…
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to…
The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for…