Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (4)
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
278 research outcomes, page 1 of 28
  • publication . Preprint . Part of book or chapter of book . 2021
    Open Access English
    Authors:
    Zhiqiang Hu; Roy Ka-Wei Lee; Lei Wang; Ee-Peng Lim; Bo Dai;
    Persistent Identifiers

    Authorship attribution (AA), which is the task of finding the owner of a given text, is an important and widely studied research topic with many applications. Recent works have shown that deep learning methods could achieve significant accuracy improvement for the AA ta...

    Add to ORCID
  • publication . Conference object . Preprint . 2021
    Open Access
    Authors:
    Rui Cao; Roy Ka-Wei Lee; Tuan-Anh Hoang;
    Persistent Identifiers
    Publisher: ACM

    Comment: Paper Accepted for 12th International ACM Conference on Web Science

    Add to ORCID
  • publication . Preprint . Article . 2021
    Open Access English
    Authors:
    Aditya Ohri; Tanya Schmah;
    Persistent Identifiers
    Project: NSERC

    We have implemented a machine translation system, the PolyMath Translator, for LaTeX documents containing mathematical text. The current implementation translates English LaTeX to French LaTeX, attaining a BLEU score of 53.5 on a held-out test corpus of mathematical sen...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Nathaniel Weir; João Sedoc; Benjamin Van Durme;
    Persistent Identifiers

    We present COD3S, a novel method for generating semantically diverse sentences using neural sequence-to-sequence (seq2seq) models. Conditioned on an input, seq2seq models typically produce semantically and syntactically homogeneous sets of sentences and thus perform poo...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Patrick Huber; Giuseppe Carenini;
    Persistent Identifiers

    The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RST-style discourse parsing. In this work, we present a novel scalable methodology to automatically generate discourse treebanks using distant ...

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Najoung Kim; Tal Linzen;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    Comment: Accepted to EMNLP 2020

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    M. Sreedhar; Kun Ni; Siva Reddy;
    Persistent Identifiers
    Project: NSERC

    Comment: Accepted for publication at Findings of EMNLP 2020

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Patrick Xia; João Sedoc; Benjamin Van Durme;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    Comment: EMNLP 2020

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Wen Xiao; Patrick Huber; Giuseppe Carenini;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization. With the goal of analyzing and pruning the parameter-heavy self-attention mechanism, there are multip...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Huda Khayrallah; João Sedoc;
    Persistent Identifiers

    Non-task-oriented dialog models suffer from poor quality and non-diverse responses. To overcome limited conversational data, we apply Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020), and use a paraphraser to simulate multiple responses per training...

    Add to ORCID
278 research outcomes, page 1 of 28