no code implementations • 8 Mar 2012 • Saif M. Mohammad, Graeme Hirst
The ability to mimic human notions of semantic distance has widespread applications.
no code implementations • LREC 2012 • Julian Brooke, Graeme Hirst
The task of native language (L1) identification suffers from a relative paucity of useful training corpora, and standard within-corpus evaluation is often problematic due to topic bias.
no code implementations • CL 2013 • Saif M. Mohammad, Bonnie J. Dorr, Graeme Hirst, Peter D. Turney
We then present an automatic and empirical measure of lexical contrast that relies on the contrast hypothesis, corpus statistics, and the structure of a {\it Roget}-like thesaurus.
4 code implementations • 30 Jul 2014 • Vanessa Wei Feng, Graeme Hirst
Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token.
no code implementations • 23 Jul 2016 • Vanessa Queiroz Marinho, Graeme Hirst, Diego Raphael Amancio
The goal of this paper is to apply the concept of motifs, recurrent interconnection patterns, in the authorship attribution task.
no code implementations • EACL 2017 • Henning Wachsmuth, Nona Naderi, Yufang Hou, Yonatan Bilu, Vinodkumar Prabhakaran, Tim Alberdingk Thijm, Graeme Hirst, Benno Stein
Research on computational argumentation faces the problem of how to automatically assess the quality of an argument or argumentation.
no code implementations • 1 May 2017 • Vanessa Q. Marinho, Graeme Hirst, Diego R. Amancio
The vast amount of data and increase of computational capacity have allowed the analysis of texts from several perspectives, including the representation of texts as complex networks.
no code implementations • ACL 2017 • Henning Wachsmuth, Nona Naderi, Ivan Habernal, Yufang Hou, Graeme Hirst, Iryna Gurevych, Benno Stein
Argumentation quality is viewed differently in argumentation theory and in practical assessment approaches.
no code implementations • IJCNLP 2017 • Mohamed Abdalla, Graeme Hirst
Current approaches to cross-lingual sentiment analysis try to leverage the wealth of labeled English data using bilingual lexicons, bilingual vector space embeddings, or machine translation systems.
no code implementations • RANLP 2017 • Nona Naderi, Graeme Hirst
We propose a new task of automatically detecting reputation defence strategies in the field of computational argumentation.
no code implementations • RANLP 2017 • Nona Naderi, Graeme Hirst
Previous approaches to generic frame classification analyze frames at the document level.
no code implementations • WS 2018 • Serena Jeblee, Mireille Gomes, Graeme Hirst
We introduce a multi-task learning model for cause-of-death classification of verbal autopsy narratives that jointly learns to output interpretable key phrases.
1 code implementation • WS 2018 • Serena Jeblee, Graeme Hirst
We present metrics for listwise temporal ordering of events in clinical notes, as well as a baseline listwise temporal ranking model that generates a timeline of events that can be used in downstream medical natural language processing tasks.
no code implementations • ACL 2019 • Kawin Ethayarajh, David Duvenaud, Graeme Hirst
A surprising property of word vectors is that word analogies can often be solved with vector arithmetic.
no code implementations • WS 2018 • Nona Naderi, Graeme Hirst
We created a corpus of utterances that attempt to save face from parliamentary debates and use it to automatically analyze the language of reputation defence.
no code implementations • WS 2018 • Nona Naderi, Graeme Hirst
We present an automated approach to distinguish true, false, stretch, and dodge statements in questions and answers in the Canadian Parliament.
no code implementations • WS 2019 • Krishnapriya Vishnubhotla, Adam Hammond, Graeme Hirst
According to the literary theory of Mikhail Bakhtin, a dialogic novel is one in which characters speak in their own distinct voices, rather than serving as mouthpieces for their authors.
no code implementations • WS 2019 • Zhaodong Yan, Serena Jeblee, Graeme Hirst
We present two models for combining word and character embeddings for cause-of-death classification of verbal autopsy reports using the text of the narratives.
no code implementations • ACL 2019 • Kawin Ethayarajh, David Duvenaud, Graeme Hirst
Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes.
no code implementations • IJCNLP 2019 • Jing Yi Xie, Renato Ferreira Pinto Jr., Graeme Hirst, Yang Xu
We present a text-based framework for investigating moral sentiment change of the public via longitudinal corpora.
no code implementations • 25 Aug 2020 • Jing Yi Xie, Graeme Hirst, Yang Xu
Our methodology builds on recent work in contextualized language models and textual inference of moral sentiment.
1 code implementation • Joint Conference on Lexical and Computational Semantics 2020 • Ioana Hulpu{\textcommabelow{s}}, Jonathan Kobbe, Heiner Stuckenschmidt, Graeme Hirst
Operationalizing morality is crucial for understanding multiple aspects of society that have moral values at their core {--} such as riots, mobilizing movements, public debates, etc.
2 code implementations • LREC 2022 • Krishnapriya Vishnubhotla, Adam Hammond, Graeme Hirst
We present the Project Dialogism Novel Corpus, or PDNC, an annotated dataset of quotations for English literary texts.
no code implementations • 7 Jul 2023 • Krishnapriya Vishnubhotla, Frank Rudzicz, Graeme Hirst, Adam Hammond
Current models for quotation attribution in literary novels assume varying levels of available information in their training and test data, which poses a challenge for in-the-wild inference.
1 code implementation • 4 Mar 2024 • Krishnapriya Vishnubhotla, Adam Hammond, Graeme Hirst, Saif M. Mohammad
The emotional journeys of the various characters within a story are central to their appeal.