Search Results for author: Tom Hosking

Found 4 papers, 3 papers with code

Factorising Meaning and Form for Intent-Preserving Paraphrasing

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.

Paraphrase Generation Paraphrase Identification

Querent Intent in Multi-Sentence Questions

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.

Evaluating Rewards for Question Generation Models

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.

Machine Translation Policy Gradient Methods +2

Assumption Questioning: Latent Copying and Reward Exploitation in Question Generation

no code implementations27 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.

Machine Translation Policy Gradient Methods +2

Cannot find the paper you are looking for? You can Submit a new open access paper.