Search Results for author: Matīss Rikters

Found 14 papers, 8 papers with code

Machine Translation for Livonian: Catering to 20 Speakers

no code implementations ACL 2022 Matīss Rikters, Marili Tomingas, Tuuli Tuisk, Valts Ernštreits, Mark Fishel

Livonian is one of the most endangered languages in Europe with just a tiny handful of speakers and virtually no publicly available corpora.

Cross-Lingual Transfer Machine Translation +2

The University of Tokyo’s Submissions to the WAT 2020 Shared Task

no code implementations AACL (WAT) 2020 Matīss Rikters, Toshiaki Nakazawa, Ryokan Ri

The paper describes the development process of the The University of Tokyo’s NMT systems that were submitted to the WAT 2020 Document-level Business Scene Dialogue Translation sub-task.

NMT Translation

What Food Do We Tweet about on a Rainy Day?

no code implementations11 Apr 2023 Maija Kāle, Matīss Rikters

Food choice is a complex phenomenon shaped by factors such as taste, ambience, culture or weather.

Cultural Vocal Bursts Intensity Prediction

How Masterly Are People at Playing with Their Vocabulary? Analysis of the Wordle Game for Latvian

no code implementations4 Oct 2022 Matīss Rikters, Sanita Reinsone

In this paper, we describe adaptation of a simple word guessing game that occupied the hearts and minds of people around the world.

Revisiting Context Choices for Context-aware Machine Translation

no code implementations7 Sep 2021 Matīss Rikters, Toshiaki Nakazawa

One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence.

Machine Translation Translation

Fragmented and Valuable: Following Sentiment Changes in Food Tweets

1 code implementation9 Jun 2021 Maija Kāle, Matīss Rikters

We analysed sentiment and frequencies related to smell, taste and temperature expressed by food tweets in the Latvian language.

Cultural Vocal Bursts Intensity Prediction

Document-aligned Japanese-English Conversation Parallel Corpus

1 code implementation WMT (EMNLP) 2020 Matīss Rikters, Ryokan Ri, Tong Li, Toshiaki Nakazawa

Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main methods and data sets focus on SL evaluation.

Machine Translation Translation

Designing the Business Conversation Corpus

1 code implementation WS 2019 Matīss Rikters, Ryokan Ri, Tong Li, Toshiaki Nakazawa

While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues remains challenging even for modern systems.

 Ranked #1 on Machine Translation on Business Scene Dialogue JA-EN (using extra training data)

Machine Translation Translation

What Can We Learn From Almost a Decade of Food Tweets

1 code implementation10 Jul 2020 Uga Sproģis, Matīss Rikters

We present the Latvian Twitter Eater Corpus - a set of tweets in the narrow domain related to food, drinks, eating and drinking.

Question Answering Sentiment Analysis

Impact of Corpora Quality on Neural Machine Translation

1 code implementation19 Oct 2018 Matīss Rikters

Large parallel corpora that are automatically obtained from the web, documents or elsewhere often exhibit many corrupted parts that are bound to negatively affect the quality of the systems and models that learn from these corpora.

Machine Translation Translation

Debugging Neural Machine Translations

1 code implementation8 Aug 2018 Matīss Rikters

In this paper, we describe a tool for debugging the output and attention weights of neural machine translation (NMT) systems and for improved estimations of confidence about the output based on the attention.

Machine Translation NMT +1

Confidence through Attention

3 code implementations MTSummit 2017 Matīss Rikters, Mark Fishel

Attention distributions of the generated translations are a useful bi-product of attention-based recurrent neural network translation models and can be treated as soft alignments between the input and output tokens.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.