Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (1)
Filters
Clear All

Digital Humanities and Cultural Heritage Publications UG

Filters
Clear All

Digital Humanities and Cultural Heritage Publications UG

The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
91 research outcomes, page 1 of 10
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Isabel Papadimitriou; Dan Jurafsky;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data induce generalizable structural...

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Ziyi Yang; Chenguang Zhu; Robert Gmyr; Michael Zeng; Xuedong Huang; Eric Darve;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    Text summarization aims to extract essential information from a piece of text and transform the text into a concise version. Existing unsupervised abstractive summarization models leverage recurrent neural networks framework while the recently proposed transformer exhib...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Allen Nie; Reuben Cohn-Gordon; Christopher Potts;
    Persistent Identifiers

    Comment: 15 pages, 7 figures. EMNLP 2020 Findings Accepted

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Xikun Zhang; Deepak Ramachandran; Ian Tenney; Yanai Elazar; Dan Roth;
    Publisher: Association for Computational Linguistics

    Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained la...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Emrah Budur; Rıza Özçelik; Tunga Güngör; Christopher Potts;
    Persistent Identifiers

    Large annotated datasets in NLP are overwhelmingly in English. This is an obstacle to progress in other languages. Unfortunately, obtaining new annotated resources for each task in each language would be prohibitively expensive. At the same time, commercial machine tran...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Atticus Geiger; Kyle Richardson; Christopher Potts;
    Persistent Identifiers

    We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation methods of (1) challenge test sets and (2) systematic generalization tas...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Weixin Liang; James Zou; Zhou Yu;
    Persistent Identifiers

    Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine commun...

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Bhargav Srinivasa Desikan; Tasker Hull; Ethan O. Nadler; Douglas Guilbeault; Aabir Abubaker Kar; Mark Chu; Donald Ruggiero Lo Sardo;
    Persistent Identifiers

    Popular approaches to natural language processing create word embeddings based on textual co-occurrence patterns, but often ignore embodied, sensory aspects of language. Here, we introduce the Python package comp-syn, which provides grounded word embeddings based on the...

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Kawin Ethayarajh; Dan Jurafsky;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics
    Project: NSERC

    Comment: EMNLP 2020 (updated with additional references)

    Add to ORCID
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Dan Iter; Kelvin Guu; Larry Lansing; Dan Jurafsky;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics

    Comment: AC2020

    Add to ORCID
91 research outcomes, page 1 of 10