Search Results for author:
Found 118 papers, 16 papers with code
Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output
For helpful quality levels, a visualization reflecting the uncertainty of the QE model is preferred.
English to Manipuri and Mizo Post-Editing Effort and its Impact on Low Resource Machine Translation
A Computer Assisted Translation (CAT) tool is used to record the time, keystroke and other indicators to measure PE effort in terms of temporal and technical effort.
Translation Quality Estimation by Jointly Learning to Score and Rank
In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations.
TransIns: Document Translation with Markup Reinsertion
This is challenging, as markup can be nested, apply to spans contiguous in source but non-contiguous in target etc.
Going beyond zero-shot MT: combining phonological, morphological and semantic factors. The UdS-DFKI System at IWSLT 2017
This paper describes the UdS-DFKI participation to the multilingual task of the IWSLT Evaluation 2017.
UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian
This paper describes the UdS-DFKI submission to the shared task for unsupervised machine translation (MT) and very low-resource supervised MT between German (de) and Upper Sorbian (hsb) at the Fifth Conference of Machine Translation (WMT20).
Tracing Source Language Interference in Translation with Graph-Isomorphism Measures
Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language.
Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese
Translationese signals are subtle (especially for professional translation) and compete with many other signals in the data such as genre, style, author, and, in particular, topic.
RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain
Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional speech in noisy and reverberant acoustic environments.
A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Existing approaches for unsupervised bilingual lexicon induction (BLI) often depend on good quality static or contextual embeddings trained on large monolingual corpora for both languages.
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?
We demonstrate that while a simple sentence average results in a strong baseline for classification tasks, more complex combinations are necessary for semantic tasks.
Exploring Paracrawl for Document-level Neural Machine Translation
We show that document-level NMT models trained with only parallel paragraphs from Paracrawl can be used to translate real documents from TED, News and Europarl, outperforming sentence-level NMT models.
NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction.
Explaining Translationese: why are Neural Classifiers Better and what do they Learn?
Previous research did not show $(i)$ whether the difference is because of the features, the classifiers or both, and $(ii)$ what the neural classifiers actually learn.
Exploiting Social Media Content for Self-Supervised Style Transfer
Recent research on style transfer takes inspiration from unsupervised neural machine translation (UNMT), learning from large amounts of non-parallel data by exploiting cycle consistency loss, back-translation, and denoising autoencoders.
Towards Debiasing Translation Artifacts
Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets.
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification
Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts.
Mid-Air Hand Gestures for Post-Editing of Machine Translation
Here, we present the first study that investigates the usefulness of mid-air hand gestures in combination with the keyboard (GK) for text editing in PE of MT.
Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation
This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this.
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation
In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality.
A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment
We further fine-tune the target-to-source attention in the BTBA model to obtain better alignments using a full context based optimization method and self-supervised training.
Understanding Translationese in Multi-view Embedding Spaces
Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation.
Learning Hard Retrieval Decoder Attention for Transformers
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily.
Linguistically inspired morphological inflection with a sequence to sequence model
Inflection is an essential part of every human language's morphology, yet little effort has been made to unify linguistic theory and computational methods in recent years.
Transformer with Depth-Wise LSTM
In this paper, we suggest that the residual connection has its drawbacks, and propose to train Transformers with the depth-wise LSTM which regards outputs of layers as steps in time series instead of residual connections, under the motivation that the vanishing gradient problem suffered by deep networks is the same as recurrent networks applied to long sequences, while LSTM (Hochreiter and Schmidhuber, 1997) has been proven of good capability in capturing long-distance relationship, and its design may alleviate some drawbacks of residual connections while ensuring the convergence.
MMPE: A Multi-Modal Interface using Handwriting, Touch Reordering, and Speech Commands for Post-Editing Machine Translation
The shift from traditional translation to post-editing (PE) of machine-translated (MT) text can save time and reduce errors, but it also affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise helpful translation proposals.
How Human is Machine Translationese? Comparing Human and Machine Translations of Text and Speech
Some translationese features tend to appear in simultaneous interpreting with higher frequency than in human text translation, but the reasons for this are unclear.
MMPE: A Multi-Modal Interface for Post-Editing Machine Translation
On the other hand, speech and multi-modal combinations of select {\&} speech are considered suitable for replacements and insertions but offer less potential for deletion and reordering.
Learning Source Phrase Representations for Neural Machine Translation
Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks ("phrases") and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships.
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change
We propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate.
Language Data Sharing in European Public Services -- Overcoming Obstacles and Creating Sustainable Data Sharing Infrastructures
Data is key in training modern language technologies.
Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation
Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each other in a virtuous circle.
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality.
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches.
Lipschitz Constrained Parameter Initialization for Deep Transformers
In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers.
Analysing Coreference in Transformer Outputs
We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information.
Self-Induced Curriculum Learning in Neural Machine Translation
Self-supervised neural machine translation (SS-NMT) learns how to extract/select suitable training data from comparable (rather than parallel) corpora and how to translate, in a way that the two tasks support each other in a virtuous circle.
UDS--DFKI Submission to the WMT2019 Similar Language Translation Shared Task
The first edition of this shared task featured data from three pairs of similar languages: Czech and Polish, Hindi and Nepali, and Portuguese and Spanish.
The Transference Architecture for Automatic Post-Editing
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input.
Improving CAT Tools in the Translation Workflow: New Approaches and Evaluation
User feedback revealed that the users preferred using CATaLog Online over existing CAT tools in some respects, especially by selecting the output of the MT system and taking advantage of the color scheme for TM suggestions.
UdS Submission for the WMT 19 Automatic Post-Editing Task
In this paper, we describe our submission to the English-German APE shared task at WMT 2019.
JU-Saarland Submission to the WMT2019 English--Gujarati Translation Shared Task
In this paper we describe our joint submission (JU-Saarland) from Jadavpur University and Saarland University in the WMT 2019 news translation shared task for English{--}Gujarati language pair within the translation task sub-track.
DFKI-NMT Submission to the WMT19 News Translation Task
This paper describes the DFKI-NMT submission to the WMT19 News translation task.
UDS--DFKI Submission to the WMT2019 Czech--Polish Similar Language Translation Shared Task
The first edition of this shared task featured data from three pairs of similar languages: Czech and Polish, Hindi and Nepali, and Portuguese and Spanish.
USAAR-DFKI -- The Transference Architecture for English--German Automatic Post-Editing
In this paper we present an English{--}German Automatic Post-Editing (APE) system called transference, submitted to the APE Task organized at WMT 2019.
Self-Supervised Neural Machine Translation
We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations.
Integrating Artificial and Human Intelligence for Efficient Translation
Current advances in machine translation increase the need for translators to switch from traditional translation to post-editing of machine-translated text, a process that saves time and improves quality.
INFODENS: An Open-source Framework for Learning Text Representations
The advent of representation learning methods enabled large performance gains on various language tasks, alleviating the need for manual feature engineering.
A Transformer-Based Multi-Source Automatic Post-Editing System
The proposed model is an extension of the transformer architecture: two separate self-attention-based encoders encode the machine translation output (mt) and the source (src), followed by a joint encoder that attends over a combination of these two encoded sequences (encsrc and encmt) for generating the post-edited sentence.
Code-Mixed Question Answering Challenge: Crowd-sourcing Data and Techniques
As a first step towards fostering research which supports CM in NLP applications, we systematically crowd-sourced and curated an evaluation dataset for factoid question answering in three CM languages - Hinglish (Hindi+English), Tenglish (Telugu+English) and Tamlish (Tamil+English) which belong to two language families (Indo-Aryan and Dravidian).
Exploring the Use of Text Classification in the Legal Domain
In this paper, we investigate the application of text classification methods to support law professionals.
The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction
In this research we investigate the impact of mismatches in the density and type of error between training and test data on a neural system correcting preposition and determiner errors.
Predicting the Law Area and Decisions of French Supreme Court Cases
In this paper, we investigate the application of text classification methods to predict the law area and the decision of cases judged by the French Supreme Court.
Massively Multilingual Neural Grapheme-to-Phoneme Conversion
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification
First, we systematically study the NMT context vectors, i. e. output of the encoder, and their power as an interlingua representation of a sentence.
How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?
In this paper, we study the impact of noisy input.
Common Round: Application of Language Technologies to Large-Scale Web Debates
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking.
Neural Automatic Post-Editing Using Prior Alignment and Reranking
APE translations produced by our system show statistically significant improvements over the first-stage MT, phrase-based APE and the best reported score on the WMT 2016 APE dataset by a previous neural APE system.
An Extensive Empirical Evaluation of Character-Based Morphological Tagging for 14 Languages
This paper investigates neural character-based morphological tagging for languages with complex morphology and large tag sets.
CATaLog Online: A Web-based CAT Tool for Distributed Translation with Data Capture for APE and Translation Process Research
We present a free web-based CAT tool called CATaLog Online which provides a novel and user-friendly online CAT environment for post-editors/translators.
Multi-Engine and Multi-Alignment Based Automatic Post-Editing and its Impact on Translation Productivity
In the paper we show that parallel system combination in the APE stage of a sequential MT-APE combination yields substantial translation improvements both measured in terms of automatic evaluation metrics as well as in terms of productivity improvements measured in a post-editing experiment.
Modeling Diachronic Change in Scientific Writing with Information Density
In this paper we investigate the introduction of information theory inspired features to study long term diachronic change on three levels: lexis, part-of-speech and syntax.
Neural Morphological Tagging from Characters for Morphologically Rich Languages
We systematically explore a variety of neural architectures (DNN, CNN, CNNHighway, LSTM, BLSTM) to obtain character-based word vectors combined with bidirectional LSTMs to model across-word context in an end-to-end setting.
CATaLog Online: Porting a Post-editing Tool to the Web
The tool features a number of editing and log functions similar to the desktop version of CATaLog enhanced with several new features that we describe in detail in this paper.
Fostering the Next Generation of European Language Technology: Recent Developments ― Emerging Initiatives ― Challenges and Opportunities
META-NET is a European network of excellence, founded in 2010, that consists of 60 research centres in 34 European countries.
The Strategic Impact of META-NET on the Regional, National and International Level
This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics.
Arabic Word Generation and Modelling for Spell Checking
Furthermore, from a large list of valid forms and invalid forms we create a character-based tri-gram language model to approximate knowledge about permissible character clusters in Arabic, creating a novel method for detecting spelling errors.
A Richly Annotated, Multilingual Parallel Corpus for Hybrid Machine Translation
This corpus aims to serve as a basic resource for further research on whether hybrid machine translation algorithms and system combination techniques can benefit from additional (linguistically motivated, decoding, and runtime) information provided by the different systems involved.
Irish Treebanking and Parsing: A Preliminary Evaluation
This paper describes the early stages in the development of new language resources for Irish ― namely the first Irish dependency treebank and the first Irish statistical dependency parser.
The ML4HMT Workshop on Optimising the Division of Labour in Hybrid Machine Translation
We describe the Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid Machine Translation (ML4HMT) which aims to foster research on improved system combination approaches for machine translation (MT).
Automatic Extraction and Evaluation of Arabic LFG Resources
We utilize this annotation to automatically acquire grammatical function (dependency) based subcategorization frames and paths linking long-distance dependencies (LDDs).
