Related papers: Transfer Learning for Context-Aware Spoken Languag…

Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common…

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…

The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks. The visual and language communities have established benchmarks to compare…

Large language models (LLMs) achieve impressive performance when a task is fully specified in a single turn, yet the same models lose up to 39% of that performance when the identical task is revealed incrementally across multiple turns, a…

Recent voice assistants are usually based on the cascade spoken language understanding (SLU) solution, which consists of an automatic speech recognition (ASR) engine and a natural language understanding (NLU) system. Because such approach…

The growing interest in argument mining and computational argumentation brings with it a plethora of Natural Language Understanding (NLU) tasks and corresponding datasets. However, as with many other NLU tasks, the dominant language is…

Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for…

Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal…

Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model…

Executable semantic parsing is the task of converting natural language utterances into logical forms that can be directly used as queries to get a response. We build a transfer learning framework for executable semantic parsing. We show…

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Dialogue structure discovery is essential in dialogue generation. Well-structured topic flow can leverage background information and predict future topics to help generate controllable and explainable responses. However, most previous work…

Generated hateful and toxic content by a portion of users in social media is a rising phenomenon that motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. We not only need an…

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

With the increasing prevalence of recorded human speech, spoken language understanding (SLU) is essential for its efficient processing. In order to process the speech, it is commonly transcribed using automatic speech recognition…

This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are…

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…

Voice Assistants such as Alexa, Siri, and Google Assistant typically use a two-stage Spoken Language Understanding pipeline; first, an Automatic Speech Recognition (ASR) component to process customer speech and generate text transcriptions,…