Search Results for author: Graeme Hirst

Found 57 papers, 5 papers with code

Improving Automatic Quotation Attribution in Literary Novels

no code implementations7 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.


Knowledge Graphs meet Moral Values

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.

Knowledge Graphs

Contextualized moral inference

no code implementations25 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.

Word Embeddings

Understanding Undesirable Word Embedding Associations

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.

Test Word Embeddings

Can Character Embeddings Improve Cause-of-Death Classification for Verbal Autopsy Narratives?

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.

Classification General Classification

Are Fictional Voices Distinguishable? Classifying Character Voices in Modern Drama

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.

General Classification text-classification +2

Using context to identify the language of face-saving

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.

Argument Mining

Automated Fact-Checking of Claims in Argumentative Parliamentary Debates

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.

Binary Classification Classification +4

Towards Understanding Linear Word Analogies

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.

Listwise temporal ordering of events in clinical notes

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.

Information Retrieval Relation Extraction

Multi-task learning for interpretable cause of death classification using key phrase prediction

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.

General Classification Multi-Task Learning +1

Recognizing Reputation Defence Strategies in Critical Political Exchanges

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.

General Classification Relation +1

Cross-Lingual Sentiment Analysis Without (Good) Translation

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.

Machine Translation Sentiment Analysis +1

Labelled network subgraphs reveal stylistic subtleties in written texts

no code implementations1 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.

Machine Translation Translation

Computational Argumentation Quality Assessment in Natural Language

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.

Authorship attribution via network motifs identification

no code implementations23 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.

Extractive Summarization

Two-pass Discourse Segmentation with Pairing and Global Features

4 code implementations30 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.

Discourse Segmentation Segmentation +2

Computing Lexical Contrast

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.

Information Retrieval Machine Translation +1

Measuring Interlanguage: Native Language Identification with L1-influence Metrics

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.

Language Acquisition Machine Translation +4

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