Related papers: Sound Natural: Content Rephrasing in Dialog System…
Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical…
Sentiment analysis is a natural language processing task that aims to identify and extract the emotional aspects of a text. However, many existing sentiment analysis methods primarily classify the overall polarity of a text, overlooking the…
Virtual Assistants can be quite literal at times. If the user says "tell Bob I love him," most virtual assistants will extract the message "I love him" and send it to the user's contact named Bob, rather than properly converting the message…
State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all…
Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train…
Metaphorical expressions are difficult linguistic phenomena, challenging diverse Natural Language Processing tasks. Previous works showed that paraphrasing a metaphor as its literal counterpart can help machines better process metaphors on…
Summarization of speech is a difficult problem due to the spontaneity of the flow, disfluencies, and other issues that are not usually encountered in written texts. Our work presents the first application of the BERTSum model to…
Question answering (QA) is an important use case on voice assistants. A popular approach to QA is extractive reading comprehension (RC) which finds an answer span in a text passage. However, extractive answers are often unnatural in a…
We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a live audio feed, such as a lecture or play-by-play commentary.…
Recent years have seen growing interest in conversational agents, such as chatbots, which are a very good fit for automated customer support because the domain in which they need to operate is narrow. This interest was in part inspired by…
Comprehending a dialogue requires a model to capture diverse kinds of key information in the utterances, which are either scattered around or implicitly implied in different turns of conversations. Therefore, dialogue comprehension requires…
Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks…
Recently published work on rephrasing natural text data for pre-training LLMs has shown promising results when combining the original dataset with the synthetically rephrased data. We build upon previous work by replicating existing results…
In a conversational context, a user expresses her multi-faceted information need as a sequence of natural-language questions, i.e., utterances. Starting from a given topic, the conversation evolves through user utterances and system…
Pre-trained large language models (LLM) are starting to be widely used in many applications. In this work, we explore the use of these models in interactive machine translation (IMT) environments. In particular, we have chosen mBART…
Recently advancements in sequence-to-sequence neural network architectures have led to an improved natural language understanding. When building a neural network-based Natural Language Understanding component, one main challenge is to…
We propose and demonstrate the task of giving natural language summaries of the actions of a robotic agent in a virtual environment. We explain why such a task is important, what makes it difficult, and discuss how it might be addressed. To…
We consider real world task-oriented dialog settings, where agents need to generate both fluent natural language responses and correct external actions like database queries and updates. We demonstrate that, when applied to customer support…
Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…
We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates a large set of high-quality questions…