Ekaterina Garmash


2023

pdf
Connecting degree and polarity: An artificial language learning study
Lisa Bylinina | Alexey Tikhonov | Ekaterina Garmash
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

We investigate a new linguistic generalisation in pre-trained language models (taking BERT Devlin et al. 2019 as a case study). We focus on degree modifiers (expressions like slightly, very, rather, extremely) and test the hypothesis that the degree expressed by a modifier (low, medium or high degree) is related to the modifier’s sensitivity to sentence polarity (whether it shows preference for affirmative or negative sentences or neither). To probe this connection, we apply the Artificial Language Learning experimental paradigm from psycholinguistics to a neural language model. Our experimental results suggest that BERT generalizes in line with existing linguistic observations that relate de- gree semantics to polarity sensitivity, including the main one: low degree semantics is associated with preference towards positive polarity.

2016

pdf
Ensemble Learning for Multi-Source Neural Machine Translation
Ekaterina Garmash | Christof Monz
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

In this paper we describe and evaluate methods to perform ensemble prediction in neural machine translation (NMT). We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i.e., multi-source ensembles, a method recently introduced by Firat et al. (2016). We are motivated by the observation that for different language pairs systems make different types of mistakes. We propose several methods with different degrees of parameterization to combine individual predictions of NMT systems so that they mutually compensate for each other’s mistakes and improve overall performance. We find that the biggest improvements can be obtained from a context-dependent weighting scheme for multi-source ensembles. This result offers stronger support for the linguistic motivation of using multi-source ensembles than previous approaches. Evaluation is carried out for German and French into English translation. The best multi-source ensemble method achieves an improvement of up to 2.2 BLEU points over the strongest single-source ensemble baseline, and a 2 BLEU improvement over a multi-source ensemble baseline.

2015

pdf
Bilingual Structured Language Models for Statistical Machine Translation
Ekaterina Garmash | Christof Monz
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf
Dependency-Based Bilingual Language Models for Reordering in Statistical Machine Translation
Ekaterina Garmash | Christof Monz
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)