Satoru Ozaki


2023

pdf bib
CANDS: A Computational Implementation of Collins and Stabler (2016)
Satoru Ozaki | Yohei Oseki
Proceedings of the Society for Computation in Linguistics 2023

2022

pdf bib
How well do LSTM language models learn filler-gap dependencies?
Satoru Ozaki | Dan Yurovsky | Lori Levin
Proceedings of the Society for Computation in Linguistics 2022

2021

pdf bib
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models
Kaixin Ma | Filip Ilievski | Jonathan Francis | Satoru Ozaki | Eric Nyberg | Alessandro Oltramari
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training. Recent works only propose lightweight model updates as models may already possess useful knowledge from past experience, but a challenge remains in understanding what parts and to what extent models should be refined for a given task. In this paper, we investigate what models learn from commonsense reasoning datasets. We measure the impact of three different adaptation methods on the generalization and accuracy of models. Our experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.

2020

pdf bib
Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations
Xingyuan Zhao | Satoru Ozaki | Antonios Anastasopoulos | Graham Neubig | Lori Levin
Proceedings of the 28th International Conference on Computational Linguistics

Interlinear Glossed Text (IGT) is a widely used format for encoding linguistic information in language documentation projects and scholarly papers. Manual production of IGT takes time and requires linguistic expertise. We attempt to address this issue by creating automatic glossing models, using modern multi-source neural models that additionally leverage easy-to-collect translations. We further explore cross-lingual transfer and a simple output length control mechanism, further refining our models. Evaluated on three challenging low-resource scenarios, our approach significantly outperforms a recent, state-of-the-art baseline, particularly improving on overall accuracy as well as lemma and tag recall.

pdf bib
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings
Naoki Otani | Satoru Ozaki | Xingyuan Zhao | Yucen Li | Micaelah St Johns | Lori Levin
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Cross-lingual word embedding (CWE) algorithms represent words in multiple languages in a unified vector space. Multi-Word Expressions (MWE) are common in every language. When training word embeddings, each component word of an MWE gets its own separate embedding, and thus, MWEs are not translated by CWEs. We propose a simple method for word translation of MWEs to and from English in ten languages: we first compile lists of MWEs in each language and then tokenize the MWEs as single tokens before training word embeddings. CWEs are trained on a word-translation task using the dictionaries that only contain single words. In order to evaluate MWE translation, we created bilingual word lists from multilingual WordNet that include single-token words and MWEs, and most importantly, include MWEs that correspond to single words in another language. We release these dictionaries to the research community. We show that the pre-tokenization of MWEs as single tokens performs better than averaging the embeddings of the individual tokens of the MWE. We can translate MWEs at a top-10 precision of 30-60%. The tokenization of MWEs makes the occurrences of single words in a training corpus more sparse, but we show that it does not pose negative impacts on single-word translations.