1 |
English machine reading comprehension: new approaches to answering multiple-choice questions
|
|
Dzendzik, Daria. - : Dublin City University. School of Computing, 2021. : Dublin City University. ADAPT, 2021
|
|
In: Dzendzik, Daria (2021) English machine reading comprehension: new approaches to answering multiple-choice questions. PhD thesis, Dublin City University. (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Improving Unsupervised Question Answering via Summarization-Informed Question Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
|
|
|
|
In: http://infoscience.epfl.ch/record/289182 (2021)
|
|
BASE
|
|
Show details
|
|
11 |
English Machine Reading Comprehension Datasets: A Survey ; Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Annotating verbal MWEs in Irish for the PARSEME Shared Task 1.2
|
|
|
|
In: Walsh, Abigail, Lynn, Teresa and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) Annotating verbal MWEs in Irish for the PARSEME Shared Task 1.2. In: Joint Workshop on Multiword Expressions and Electronic Lexicons, 13 Dec 2020, Barcelona, Spain (Online). (2020)
|
|
BASE
|
|
Show details
|
|
13 |
Improving document-level sentiment analysis with user and product context
|
|
|
|
In: Lyu, Chenyang, Foster, Jennifer orcid:0000-0002-7789-4853 and Graham, Yvette (2020) Improving document-level sentiment analysis with user and product context. In: Proceedings of the 28th International Conference on Computational Linguistics, 8-13 Dec 20, Barcelona, Spain (Online). (2020)
|
|
Abstract:
Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text available at the time of sentiment prediction that may prove meaningful for guiding prediction. Firstly, we incorporate all available historical review text belonging to the author of the review in question. Secondly, we investigate the inclusion of historical reviews associated with the current product (written by other users). We achieve this by explicitly storing representations of reviews written by the same user and about the same product and force the model to memorize all reviews for one particular user and product. Additionally, we drop the hierarchical architecture used in previous work to enable words in the text to directly attend to each other. Experiment results on IMDB, Yelp 2013 and Yelp 2014 datasets show improvement to state-of-the-art of more than 2 percentage points in the best case.
|
|
Keyword:
Computational linguistics
|
|
URL: http://doras.dcu.ie/25959/
|
|
BASE
|
|
Hide details
|
|
14 |
How to make neural natural language generation as reliable as templates in task-oriented dialogue
|
|
|
|
In: Elder, Henry, O'Connor, Alexander orcid:0000-0003-0301-999X and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) How to make neural natural language generation as reliable as templates in task-oriented dialogue. In: 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 16-20 Nov 2020, Online. (2020)
|
|
BASE
|
|
Show details
|
|
15 |
Treebank embedding vectors for out-of-domain dependency parsing
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Barry, James orcid:0000-0003-3051-585X and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) Treebank embedding vectors for out-of-domain dependency parsing. In: 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 05-10 Jul 2020, Online (virtual conference). (2020)
|
|
BASE
|
|
Show details
|
|
16 |
Q. Can knowledge graphs be used to answer Boolean questions? A. It’s complicated!
|
|
|
|
In: Dzendzik, Daria, Vogel, Carl orcid:0000-0001-8928-8546 and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) Q. Can knowledge graphs be used to answer Boolean questions? A. It’s complicated! In: First Workshop on Insights from Negative Results in NLP, 10 Nov 2020, Online. (2020)
|
|
BASE
|
|
Show details
|
|
18 |
Annotated corpora and tools of the PARSEME Shared Task on Semi-Supervised Identification of Verbal Multiword Expressions (edition 1.2)
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Annotating Verbal MWEs in Irish for the PARSEME Shared Task 1.2 ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|