Related papers: Generic Dependency Modeling for Multi-Party Conver…

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…

In their usual form, representation independence metatheorems provide an external guarantee that two implementations of an abstract interface are interchangeable when they are related by an operation-preserving correspondence. If our…

Prior human-robot interaction (HRI) research has primarily focused on single-user interactions, where robots do not need to consider the timing or recipient of their responses. However, in multi-party interactions, such as at malls and…

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Modelling persuasion strategies as predictors of task outcome has several real-world applications and has received considerable attention from the computational linguistics community. However, previous research has failed to account for the…

In recent years, several high-performance conversational systems have been proposed based on the Transformer encoder-decoder model. Although previous studies analyzed the effects of the model parameters and the decoding method on subjective…

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions.…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Emotional voice conversion aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity. The prior studies on emotional voice conversion are mostly carried out under the…

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict…

This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer…

Cross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning…

In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and…

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing as sequence…

Response-free item difficulty modelling promises to reduce reliance on response-based calibration but is intrinsically difficult on reading-comprehension multiple-choice items, where difficulty depends on inferential demands across wording…

Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such…