Papers by Matīss Rikters
Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process (2026.acl-long)
Copied to clipboard
Tomoki Tsujimura, Matīss Rikters, Masaki Asada, Shusaku Egami, Tatsuya Ishigaki, Ken Yano, Hiroya Takamura
| Challenge: | Large language models have been shown remarkable ability to understand given contexts. |
| Approach: | They propose a method to evaluate whether beliefs held by LLMs remain consistent . they propose to use multiple choice question answering format to assess belief consistency . |
| Outcome: | The proposed method evaluates the consistency of LLMs in a multiple-choice question answering format. |
Designing the Business Conversation Corpus (D19-52)
Copied to clipboard
| Challenge: | Existing parallel corpora for machine translation of written text and monologues are limited. |
| Approach: | They propose to introduce a Japanese-English business conversation parallel corpus into machine translation training scenarios and show how it improves machine translation quality. |
| Outcome: | The proposed corpus is used in a Japanese-English business conversation training scenario and shows how it performs. |
Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages (L18-1)
Copied to clipboard
| Challenge: | Using multilingual and multi-way neural machine translation approaches is a major advantage . training NMT systems for individual language pairs takes significantly more time than training of SMT systems . |
| Approach: | They propose to employ multilingual and multi-way neural machine translation approaches for morphologically rich languages such as Estonian and Russian. |
| Outcome: | The proposed approach improves translation quality by +3.27 BLEU points over baseline models. |
Machine Translation for Livonian: Catering to 20 Speakers (2022.acl-short)
Copied to clipboard
| Challenge: | Livonian is one of the most endangered languages in Europe with just a tiny handful of speakers and virtually no publicly available corpora. |
| Approach: | They aim to develop machine translation between Livonian and English using a linguistic similarity test and a dataset of parallel and monolingual data. |
| Outcome: | The proposed systems and the collected data, including a manually translated and verified translation benchmark, are publicly released via OPUS and Huggingface repositories. |