1 |
Embracing Ambiguity: Shifting the Training Target of NLI Models ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers
|
|
|
|
In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) ; 12th Conference on Language Resources and Evaluation (LREC 2020) ; https://hal.archives-ouvertes.fr/hal-03272825 ; 12th Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Keyphrase Generation for Scientific Document Retrieval
|
|
|
|
In: The 58th Annual Meeting of the Association for Computational Linguistics (ACL) ; https://hal.archives-ouvertes.fr/hal-02556086 ; The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2020, Online, United States. ⟨10.18653/v1/2020.acl-main.105⟩ (2020)
|
|
BASE
|
|
Show details
|
|
5 |
A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Multi-sense Embeddings through a Word Sense Disambiguation Process
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Leveraging Monolingual Data for Crosslingual Compositional Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Co-occurrence-based indicators for authorship analysis
|
|
|
|
Abstract:
Along with its methodological development, authorship analysis has expanded in scope to new application areas like authorship profiling and computational sociolinguistics as well as conventional ones like authorship attribution. For these new applications, providing a new interpretation of text through the textual characteristics is as important as improving the classification performance between the authors, which was the aim in conventional applications. Lexical indicators were one of the most frequently used characteristics in conventional applications as they were effective at discriminating between authors, but most of the previously used indicators were based on the frequencies of morphemes, and reflected only limited aspects of the writing styles of the authors. In order to use these types of characteristics for new applications, we need to develop indicators reflecting other various aspects of the authors writing styles that are useful for interpretation as well as classification. As such, we propose the use of two types of co-occurrence-based indicators, namely network indicators and a co-occurrence-based concentration indicator in this field. Experimental results using the Aozora Bunko corpora, along with qualitative analyses, showed that our indicators were very effective at capturing aspects of the styles of the authors as well as for improving the classification performance. We concluded that our indicators successfully supplement previously used indicators and are useful for various new applications in authorship analysis.
|
|
Keyword:
Original Articles
|
|
URL: http://llc.oxfordjournals.org/cgi/content/short/27/2/197 https://doi.org/10.1093/llc/fqs011
|
|
BASE
|
|
Hide details
|
|
11 |
Looking for Transliterations in a Trilingual English, French and Japanese Specialised Comparable Corpus
|
|
|
|
In: LREC Workshop on Comparable Corpora (LREC'08) ; Language Resources and Evaluation Conference ; https://hal.archives-ouvertes.fr/hal-00417726 ; Language Resources and Evaluation Conference, May 2008, Marrakech, Morocco. pp.4 (2008)
|
|
BASE
|
|
Show details
|
|
|
|