Papers by Filip Ginter
Silver Syntax Pre-training for Cross-Domain Relation Extraction (2023.findings-acl)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is the task of extracting structured knowledge from unstructured text. |
| Approach: | They exploit the affinity between syntactic structure and semantic RE to obtain low-cost pre-training data. |
| Outcome: | The proposed model outperforms baseline models in five out of six cross-domain setups without additional annotated data. |
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection (2020.lrec-1)
Copied to clipboard
Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajič, Christopher D. Manning, Sampo Pyysalo, Sebastian Schuster, Francis Tyers, Daniel Zeman
| Challenge: | Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages. |
| Approach: | They describe version 2 of the universal guidelines and discuss major changes from UD v1 to UD 2 . they propose a morphological layer, a syntactic layer and a word segmentation layer . |
| Outcome: | The proposed treebanks are available for 90 languages and have been updated to meet the needs of multilingual parsers and researchers. |
Explaining Classes through Stable Word Attributions (2022.findings-acl)
Copied to clipboard
| Challenge: | Input saliency methods have become popular for explaining predictions of deep learning models, but there has been little work investigating methods for aggregating prediction-level explanations to the class level. |
| Approach: | They propose a method to aggregate prediction-level explanations to the class level using XLM-R and Integrated Gradients input attribution methods. |
| Outcome: | The proposed method extracts keyword lists of classes from text classification tasks and evaluates them on web register data. |
Parse Me if You Can: Artificial Treebanks for Parsing Experiments on Elliptical Constructions (L18-1)
Copied to clipboard
| Challenge: | ellipsis is a phenomenon present in many natural languages, but it complicates syntactic parsing of the content that is not omitted. |
| Approach: | They analyze outputs of state-of-the-art parsers to learn about parsing accuracy and typical errors from the perspective of elliptical constructions. |
| Outcome: | The proposed treebank is a semi-artificially constructed treebank of ellipsis. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
The FISKMÖ Project: Resources and Tools for Finnish-Swedish Machine Translation and Cross-Linguistic Research (2020.lrec-1)
Copied to clipboard
Jörg Tiedemann, Tommi Nieminen, Mikko Aulamo, Jenna Kanerva, Akseli Leino, Filip Ginter, Niko Papula
| Challenge: | Finnish and Swedish are the two official languages of Finland. |
| Approach: | They propose to compile a massive corpus of translated material between Finnish and Swedish . they also aim to develop open and freely accessible translation services for those two languages . |
| Outcome: | The project aims to develop open and freely accessible translation services for Finnish and Swedish. |
Out-of-Domain Evaluation of Finnish Dependency Parsing (2022.lrec-1)
Copied to clipboard
| Challenge: | prevailing practice in academia evaluates model performance on in-domain evaluation data . however, in many real world applications data on which model is applied may differ from training data - a problem that is not addressed by current literature. |
| Approach: | They propose to use Finnish-OOD out-of-domain treebank for out- of-domain evaluation . they propose to include sections more challenging for the general parser . |
| Outcome: | The proposed treebank includes five distinct data sources and a total of 19,382 syntactic words in 2,122 sentences. |
FinGPT: Large Generative Models for a Small Language (2023.emnlp-main)
Copied to clipboard
Risto Luukkonen, Ville Komulainen, Jouni Luoma, Anni Eskelinen, Jenna Kanerva, Hanna-Mari Kupari, Filip Ginter, Veronika Laippala, Niklas Muennighoff, Aleksandra Piktus, Thomas Wang, Nouamane Tazi, Teven Scao, Thomas Wolf, Osma Suominen, Samuli Sairanen, Mikko Merioksa, Jyrki Heinonen, Aija Vahtola, Samuel Antao, Sampo Pyysalo
| Challenge: | Neural language models excel in many tasks in NLP but are limited to smaller languages. |
| Approach: | They propose two approaches to pretrain large language models for Finnish . they train seven monolingual models from scratch and use Finnish as pretraining data . |
| Outcome: | The proposed model is based on a dataset of Finnish web crawls, news, social media and eBooks. |
Neural Dependency Parsing of Biomedical Text: TurkuNLP entry in the CRAFT Structural Annotation Task (D19-57)
Copied to clipboard
| Challenge: | Syntactic analysis (parsing) is a fundamental task in natural language processing (NLP). |
| Approach: | They propose to use the Turku neural parser to adapt it to the biomedical domain . they evaluated custom word embeddings, combination with other in-domain resources . |
| Outcome: | The proposed approach achieved a labeled attachment score of 89.7%, the best among task participants. |