Related papers: Restructuring Conversations using Discourse Relati…
We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…
Extracting individual sentences from a document as evidence or reasoning steps is commonly done in many NLP tasks. However, extracted sentences often lack context necessary to make them understood, e.g., coreference and background…
The increased prevalence of online meetings has significantly enhanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the…
Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall…
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction. We adapt an existing in-domain relation learner (Chen et al., 2011) by exploiting a set of…
Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method…
Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…
Existing graph- and hypergraph-based algorithms for document summarization represent the sentences of a corpus as the nodes of a graph or a hypergraph in which the edges represent relationships of lexical similarities between sentences.…
We present Contextual Query Rewrite (CQR) a dataset for multi-domain task-oriented spoken dialogue systems that is an extension of the Stanford dialog corpus (Eric et al., 2017a). While previous approaches have addressed the issue of…
Neural abstractive summarization models make summaries in an end-to-end manner, and little is known about how the source information is actually converted into summaries. In this paper, we define input sentences that contain essential…
In this paper, we propose a novel architecture for direct extractive speech-to-speech summarization, ESSumm, which is an unsupervised model without dependence on intermediate transcribed text. Different from previous methods with text…
Existing summarization systems mostly generate summaries purely relying on the content of the source document. However, even for humans, we usually need some references or exemplars to help us fully understand the source document and write…
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…
Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to…
Neural network-based approaches have become widespread for abstractive text summarization. Though previously proposed models for abstractive text summarization addressed the problem of repetition of the same contents in the summary, they…
Recent years have brought about an interest in the challenging task of summarizing conversation threads (meetings, online discussions, etc.). Such summaries help analysis of the long text to quickly catch up with the decisions made and thus…
As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However,…
Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the…
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional…
Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement…