Related papers: DIONYSUS: A Pre-trained Model for Low-Resource Dia…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Pre-trained language models (PLMs) have achieved outstanding achievements in abstractive single-document summarization (SDS). However, such benefits may not fully extend to multi-document summarization (MDS), where the handling of…

This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision. We explore and compare token-level and dialogue act-level automatic…

Existing approaches to automatic summarization assume that a length limit for the summary is given, and view content selection as an optimization problem to maximize informativeness and minimize redundancy within this budget. This framework…

Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that…

Large language models (LLMs) like Llama, Baichuan and Bloom models show remarkable ability with instruction fine-tuning in many natural language tasks. Nevertheless, for the dialogue summarization task, which aims to generate summaries for…

Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which…

Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview…

Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for…

The recent success of deep learning techniques for abstractive summarization is predicated on the availability of large-scale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can…

Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…

Summarizing sales calls is a routine task performed manually by salespeople. We present a production system which combines generative models fine-tuned for customer-agent setting, with a human-in-the-loop user experience for an interactive…

Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings,…

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…

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…

This paper presents Z-Code++, a new pre-trained language model optimized for abstractive text summarization. The model extends the state of the art encoder-decoder model using three techniques. First, we use a two-phase pre-training process…

Despite many recent advances for the design of dialogue systems, a true bottleneck remains the acquisition of data required to train its components. Unlike many other language processing applications, dialogue systems require interactions…

High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design. Existing works contribute heavy human efforts to manually labeling…

Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews…

Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with…