1 code implementation • NAACL 2019 • Tom Hosking, Sebastian Riedel
Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation.
Ranked #12 on Question Generation on SQuAD1.1
1 code implementation • ACL 2022 • 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.
Ranked #1 on Paraphrase Generation on Paralex
1 code implementation • ACL 2021 • Tom Hosking, Mirella Lapata
We propose a method for generating paraphrases of English questions that retain the original intent but use a different surface form.
Ranked #2 on Paraphrase Generation on Paralex
1 code implementation • 19 May 2023 • Tom Hosking, Hao Tang, Mirella Lapata
We propose a method for unsupervised opinion summarization that encodes sentences from customer reviews into a hierarchical discrete latent space, then identifies common opinions based on the frequency of their encodings.
1 code implementation • 28 Sep 2023 • Tom Hosking, Phil Blunsom, Max Bartolo
We critically analyse the use of human feedback for both training and evaluation, to verify whether it fully captures a range of crucial error criteria.
1 code implementation • COLING (LAW) 2020 • Laurie Burchell, Jie Chi, Tom Hosking, Nina Markl, Bonnie Webber
Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit.
1 code implementation • 9 Jul 2023 • Tom Sherborne, Tom Hosking, Mirella Lapata
Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e. g., English) to low-resource languages with scarce training data.
1 code implementation • 1 Mar 2024 • Tom Hosking, Hao Tang, Mirella Lapata
We show that HIRO learns an encoding space that is more semantically structured than prior work, and generates summaries that are more representative of the opinions in the input reviews.
no code implementations • 27 Sep 2018 • Tom Hosking, Sebastian Riedel
Question generation is an important task for improving our ability to process natural language data, with additional challenges over other sequence transformation tasks.