539 research outputs found
Sort by
Coreference meets Universal Dependencies – a pilot experiment on harmonizing coreference datasets for 11 languages
No full textWe describe a pilot experiment aimed at harmonizing diverse data resources that contain coreference-related annotations. We converted 17 existing datasets for 11 languages into a common annotation scheme based on Universal Dependencies, and released a subset of the resulting collection publicly under the name CorefUD 0.1 via the LINDAT-CLARIAH-CZ repository (http://hdl.handle.net/11234/1-3510)
ELITR Coordination Experience
No full textDescribing our experience from the coordination of the EU project ELITR for grant applicants
WMT21 Marian translation model (ca-oc multi-task)
No full textMarian NMT model for Catalan to Occitan translation. It is a multi-task model, producing also a phonemic transcription of the Catalan source. The model was submitted to WMT'21 Shared Task on Multilingual Low-Resource Translation for Indo-European Languages as a CUNI-Contrastive system for Catalan to Occitan
Explainable Quality Estimation: CUNI Eval4NLP Submission
No full textThis paper describes our participating system in the shared task Explainable quality estimation of 2nd Workshop on Evaluation & Comparison of NLP Systems. The task of quality estimation (QE, a.k.a. reference-free evaluation) is to predict the quality of MT output at inference time without access to reference translations. In this proposed work, we first build a word-level quality estimation model, then we finetune this model for sentence-level QE. Our proposed models achieve near state-of-the-art results. In the word-level QE, we place 2nd and 3rd on the supervised Ro-En and Et-En test sets. In the sentence-level QE, we achieve a relative improvement of 8.86% (Ro-En) and 10.6% (Et-En) in terms of the Pearson correlation coefficient over the baseline model
CUNI systems for WMT21: Terminology translation Shared Task
No full textThis paper describes Charles University submission for Terminology translation Shared Task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high overall translation quality. We competed in English-French language pair. Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms. We lemmatize the terms both during the training and inference, to allow the model to learn how to produce correct surface forms of the words, when they differ from the forms provided in the terminology database. Our submission ranked second in Exact Match metric which evaluates the ability of the model to produce desired terms in the translation
WMT21 Marian translation models (ca-ro,it,oc)
No full textMarian multilingual translation model from Catalan into Romanian, Italian and Occitan. This model is an updated version (trained for 2.1M updates) of the model submitted to WMT'21 Shared Task on Multilingual Low-Resource Translation for Indo-European Languages as a CUNI-Primary system for Catalan to Romanian and Italian (trained for 430k updates)
ParCzech 3.0
No full textThe ParCzech 3.0 corpus is the third version of ParCzech consisting of stenographic protocols that record the Chamber of Deputies’ meetings held in the 7th term (2013-2017) and the current 8th term (2017-Mar 2021). The protocols are provided in their original HTML format, Parla-CLARIN TEI format, and the format suitable for Automatic Speech Recognition. The corpus is automatically enriched with the morphological, syntactic, and named-entity annotations using the procedures UDPipe 2 and NameTag 2. The audio files are aligned with the texts in the annotated TEI files
More Data and New Tools. Advances in Parsing the Index Thomisticus Treebank
No full textThis paper investigates the recent advances in parsing the Index Thomisticus Treebank, which encompasses Medieval Latin texts by Thomas Aquinas. The research focuses on two types of variables. On the one hand, it examines the impact that a larger dataset has on the results of parsing; on the other hand, performances of new parsers are analysed with respect to less recent tools. Term of comparison to determine the effective parsing advances are the results in parsing the Index Thomisticus Treebank described in a previous work. First, the best performing parser among those concerned in that study is tested on a larger dataset than the one originally used. Then, some parser combinations that were developed in the same study are evaluated as well, assessing that more training data result in more accurate performances. Finally, to examine the impact that newly available tools have on parsing results, we train, test, and evaluate two neural parsers chosen among those best performing in the CoNLL 2018 Shared Task. Our experiments reach the highest accuracy rates achieved so far in automatic syntactic parsing of the Index Thomisticus Treebank and of Latin overall
Report on the SIGDial 2021 Special Session on Summarization of Dialogues and Multi-Party Meetings (SummDial)
No full textThe SummDial special session on summarization of dialogues and multi-party meetings was held virtually within the SIGDial 2021 conference on July 29, 2021. SummDial @ SIGDial 2021 aimed to bring together the speech, dialogue, and summarization communities to foster cross-pollination of ideas and fuel the discussions/collaborations to attempt this crucial and timely problem. When the pandemic has restricted most of our in-person interactions, the current scenario has forced people to go virtual, resulting in an information overload from frequent dialogues and meetings in the virtual environment. Summarization could help reduce the cognitive burden on the participants; however, multi-party speech summarization comes with its own set of challenges. The SummDial special session aimed to leverage the community intelligence to find effective solutions while also brainstorming the future of AI interventions in meetings and dialogues. We report the findings of the special session in this article. We organized the SummDial special session under the aegis of the EU-funded H2020 European Live Translator (ELITR) project
An Empirical Performance Analysis of State-of-the-Art Summarization Models for Automatic Minuting
No full textA significant portion of the working population has their mainstream interaction virtually
these days. Meetings are being organized and
recorded daily in volumes likely exceeding
what can be ever comprehended. With the
deluge of meetings, it is important to identify
and jot down the essential items discussed in
the meeting, usually referred to as the minutes. The task of minuting is diverse and
depends on the goals, style, procedure, and
category of the meeting. Automatic Minuting is close to summarization; however, not
exactly the same. In this work, we evaluate the current state-of-the-art summarization
models for automatically generating meeting
minutes. We provide empirical baselines to
motivate the community to work on this very
timely, relevant yet challenging problem. We
conclude that off-the-shelf text summarization models are not the best candidates for
generating minutes which calls for further research on meeting-specific summarization or
minuting models. We found that Transformerbased models perform comparatively better
than other categories of summarization algorithms; however, they are still far from
generating a good multi-party meeting summary/minutes. We release our experimental
code at https://github.com/ELITR/
Minuting_Baseline_Experiments