activity
20162022
most citedHierarchical Transformers for Multi-Document Summarization

34 citations · 155 across the 23 of their papers we have counts for

collaborators
Showing cs.CLShow all

55 papers · 1 filter

cs.CL20222 cited

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation

Shashi Narayan, Gonçalo Simões, Yao Zhao +4

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding str…

cs.CL20221 cited

Hierarchical Sketch Induction for Paraphrase Generation

Tom Hosking, Hao Tang, Mirella Lapata

We propose a generative model of paraphrase generation, that encourages syntactic diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical Refinement Qu…

cs.CL20222 cited

Data-to-text Generation with Variational Sequential Planning

Ratish Puduppully, Yao Fu, Mirella Lapata

We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple…

cs.CL2022

Models and Datasets for Cross-Lingual Summarisation

Laura Perez-Beltrachini, Mirella Lapata

We present a cross-lingual summarisation corpus with long documents in a source language associated with multi-sentence summaries in a target language. The corpus covers twelve lan…

cs.CL2021

Learning Opinion Summarizers by Selecting Informative Reviews

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Opinion summarization has been traditionally approached with unsupervised, weakly-supervised and few-shot learning techniques. In this work, we collect a large dataset of summaries…

cs.CL2021

Memory-Based Semantic Parsing

Parag Jain, Mirella Lapata

We present a memory-based model for context-dependent semantic parsing. Previous approaches focus on enabling the decoder to copy or modify the parse from the previous utterance, a…