Related papers: Learning-by-Narrating: Narrative Pre-Training for …
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to…
Video understanding has long suffered from reliance on large labeled datasets, motivating research into zero-shot learning. Recent progress in language modeling presents opportunities to advance zero-shot video analysis, but constructing an…
Dialogue disentanglement aims to group utterances in a long and multi-participant dialogue into threads. This is useful for discourse analysis and downstream applications such as dialogue response selection, where it can be the first step…
Training machines to understand natural language and interact with humans is an elusive and essential task of artificial intelligence. A diversity of dialogue systems has been designed with the rapid development of deep learning techniques,…
Training machines to understand natural language and interact with humans is an elusive and essential task of artificial intelligence. A diversity of dialogue systems has been designed with the rapid development of deep learning techniques,…
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…
Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a…
In dialogue systems, utterances with similar semantics may have distinctive emotions under different contexts. Therefore, modeling long-range contextual emotional relationships with speaker dependency plays a crucial part in dialogue…
Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training. However, even with the help of the powerful PrLMs, it is…
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…
We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating target captions in training data, the proposed method trains a…
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems…
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…
Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to…
For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only…
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…
We introduce a method for improving the structural understanding abilities of language models. Unlike previous approaches that finetune the models with task-specific augmentation, we pretrain language models on a collection of task-agnostic…
Neural conversational models require substantial amounts of dialogue data for their parameter estimation and are therefore usually learned on large corpora such as chat forums or movie subtitles. These corpora are, however, often…
While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method…