MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

1 code implementation • SCiL 2020 • Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Lawrence S. Moss, Sandra Kuebler

We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus.

Data Augmentation Natural Language Inference

Detecting Linguistic Traces of Depression in Topic-Restricted Text: Attending to Self-Stigmatized Depression with NLP

no code implementations • COLING 2018 • JT Wolohan, Misato Hiraga, Atreyee Mukherjee, Zeeshan Ali Sayyed, Matthew Millard

We find significant differences in the language used by depressed users under the two conditions as well as a difference in the ability of machine learning algorithms to correctly detect depression.

BIG-bench Machine Learning

Similarity Based Genre Identification for POS Tagging Experts \& Dependency Parsing

no code implementations • RANLP 2017 • Atreyee Mukherjee, S K{\"u}bler, ra

The results show that the choice of similarity metric has an effect on results and that we can reach comparable accuracies to the joint topic modeling in POS tagging and dependency parsing, thus providing a viable and efficient approach to POS tagging and parsing a sentence by its genre expert.

Dependency Parsing Domain Adaptation +3

Creating POS Tagging and Dependency Parsing Experts via Topic Modeling

no code implementations • EACL 2017 • Atreyee Mukherjee, S K{\"u}bler, ra, Matthias Scheutz

Part of speech (POS) taggers and dependency parsers tend to work well on homogeneous datasets but their performance suffers on datasets containing data from different genres.

Dependency Parsing Domain Adaptation +3

POS Tagging Experts via Topic Modeling

no code implementations • WS 2016 • Atreyee Mukherjee, S K{\"u}bler, ra, Matthias Scheutz

Domain Adaptation Part-Of-Speech Tagging +3