Abstract
This paper describes a builder entry, named “strawman”, to the sentence-level sentiment analysis task of the “Build It, Break It” shared task of the First Workshop on Building Linguistically Generalizable NLP Systems. The goal of a builder is to provide an automated sentiment analyzer that would serve as a target for breakers whose goal is to find pairs of minimally-differing sentences that break the analyzer.- Anthology ID:
- W17-5409
- Volume:
- Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 59–60
- Language:
- URL:
- https://aclanthology.org/W17-5409
- DOI:
- 10.18653/v1/W17-5409
- Cite (ACL):
- Kyunghyun Cho. 2017. Strawman: An Ensemble of Deep Bag-of-Ngrams for Sentiment Analysis. In Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems, pages 59–60, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Strawman: An Ensemble of Deep Bag-of-Ngrams for Sentiment Analysis (Cho, 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W17-5409.pdf
- Code
- kyunghyuncho/strawman