Search Results for author:
Found 60 papers, 8 papers with code
A Dataset of Offensive Language in Kosovo Social Media
Social media are a central part of people’s lives.
Exploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation
They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference
Similar to the previous version, this corpus has been created to address translation of coreference across languages, a phenomenon still challenging for machine translation (MT) and other multilingual natural language processing (NLP) applications.
The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task
Our baseline systems are transformer-big models that are pre-trained on the WMT’19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data.
Referential Cohesion A Challenge for Machine Translation Evaluation
The realisation of those cohesive structures is subject to different constraints and varying preferences in different languages.
A Mention-Based System for Revision Requirements Detection
Exploring aspects of sentential meaning that are implicit or underspecified in context is important for sentence understanding.
Coreference Strategies in English-German Translation
We present a study focusing on variation of coreferential devices in English original TED talks and news texts and their German translations.
What Are They Filtering Out? A Survey of Filtering Strategies for Harm Reduction in Pretraining Datasets
Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets.
A comparison of data filtering techniques for English-Polish LLM-based machine translation in the biomedical domain
Large Language Models (LLMs) have become state-of-the-art in Machine Translation (MT), often trained on massive bilingual parallel corpora scraped from the web, that contain low-quality entries and redundant information, leading to significant computational challenges.
Mention Attention for Pronoun Translation
Our proposed model outperforms the baseline Transformer model in terms of APT and BLEU scores, this confirms our hypothesis that we can improve pronoun translation by paying additional attention to source mentions, and shows that our introduced additional modules do not have negative effect on the general translation quality.
With Good MT There is No Need For End-to-End: A Case for Translate-then-Summarize Cross-lingual Summarization
Recent work has suggested that end-to-end system designs for cross-lingual summarization are competitive solutions that perform on par or even better than traditional pipelined designs.
A Dataset for the Detection of Dehumanizing Language
Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people.
Parallel Data Helps Neural Entity Coreference Resolution
Coreference resolution is the task of finding expressions that refer to the same entity in a text.
Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity
We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages.
deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature.
Experimental Standards for Deep Learning in Natural Language Processing Research
The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well.
Unsupervised Discovery of Unaccusative and Unergative Verbs
We present an unsupervised method to detect English unergative and unaccusative verbs.
Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout.
How to Write a Bias Statement: Recommendations for Submissions to the Workshop on Gender Bias in NLP
At the Workshop on Gender Bias in NLP (GeBNLP), we'd like to encourage authors to give explicit consideration to the wider aspects of bias and its social implications.
Principal Word Vectors
The effect of these generalizations on the word vectors is intrinsically studied with regard to the spread and the discriminability of the word vectors.
Exploiting Cross-Lingual Hints to Discover Event Pronouns
Non-nominal co-reference is much less studied than nominal coreference, partly because of the lack of annotated corpora.
Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction
We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction.
Getting Gender Right in Neural Machine Translation
Our contribution is two-fold: (1) the compilation of large datasets with speaker information for 20 language pairs, and (2) a simple set of experiments that incorporate gender information into NMT for multiple language pairs.
Gendered Ambiguous Pronoun (GAP) Shared Task at the Gender Bias in NLP Workshop 2019
The 1st ACL workshop on Gender Bias in Natural Language Processing included a shared task on gendered ambiguous pronoun (GAP) resolution.
Entity Decisions in Neural Language Modelling: Approaches and Problems
We explore different approaches to explicit entity modelling in language models (LM).
Cross-lingual Incongruences in the Annotation of Coreference
In the present paper, we deal with incongruences in English-German multilingual coreference annotation and present automated methods to discover them.
Discourse-Related Language Contrasts in English-Croatian Human and Machine Translation
We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations.
A Pronoun Test Suite Evaluation of the English--German MT Systems at WMT 2018
We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition.
Pronoun Translation in English-French Machine Translation: An Analysis of Error Types
Pronouns are a long-standing challenge in machine translation.
Automatic Reference-Based Evaluation of Pronoun Translation Misses the Point
We compare the performance of the APT and AutoPRF metrics for pronoun translation against a manually annotated dataset comprising human judgements as to the correctness of translations of the PROTEST test suite.
Universal Word Segmentation: Implementation and Interpretation
Word segmentation is a low-level NLP task that is non-trivial for a considerable number of languages.
Forms of Anaphoric Reference to Organisational Named Entities: Hoping to widen appeal, they diversified
Proper names of organisations are a special case of collective nouns.
Event versus entity co-reference: Effects of context and form of referring expression
Anaphora resolution systems require both an enumeration of possible candidate antecedents and an identification process of the antecedent.
Recall is the Proper Evaluation Metric for Word Segmentation
We extensively analyse the correlations and drawbacks of conventionally employed evaluation metrics for word segmentation.
Discovery of Discourse-Related Language Contrasts through Alignment Discrepancies in English-German Translation
In this paper, we analyse alignment discrepancies for discourse structures in English-German parallel data {--} sentence pairs, in which discourse structures in target or source texts have no alignment in the corresponding parallel sentences.
Predicting Pronouns with a Convolutional Network and an N-gram Model
This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction.
Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction
We describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction.
What is it? Disambiguating the different readings of the pronoun `it'
In this paper, we address the problem of predicting one of three functions for the English pronoun {`}it{'}: anaphoric, event reference or pleonastic.
Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
We present a character-based model for joint segmentation and POS tagging for Chinese.
A Neural Model for Part-of-Speech Tagging in Historical Texts
Historical texts are challenging for natural language processing because they differ linguistically from modern texts and because of their lack of orthographical and grammatical standardisation.
PROTEST: A Test Suite for Evaluating Pronouns in Machine Translation
We present PROTEST, a test suite for the evaluation of pronoun translation by MT systems.
Learning Structural Kernels for Natural Language Processing
Structural kernels are a flexible learning paradigm that has been widely used in Natural Language Processing.
ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT
We present ParCor, a parallel corpus of texts in which pronoun coreference ― reduced coreference in which pronouns are used as referring expressions ― has been annotated.
