Search Results for author:
Found 336 papers, 23 papers with code
Modeling Word Formation in English--German Neural Machine Translation
This paper studies strategies to model word formation in NMT using rich linguistic information, namely a word segmentation approach that goes beyond splitting into substrings by considering fusional morphology.
Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation
Simultaneous machine translation systems rely on a policy to schedule read and write operations in order to begin translating a source sentence before it is complete.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Frugal Paradigm Completion
Lexica distinguishing all morphologically related forms of each lexeme are crucial to many language technologies, yet building them is expensive.
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
The success of the large neural language models on many NLP tasks is exciting.
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.
Metaphor Detection Using Contextual Word Embeddings From Transformers
The detection of metaphors can provide valuable information about a given text and is crucial to sentiment analysis and machine translation.
Testing the role of metadata in metaphor identification
The particular focus of our approach is on the potential influence that the metadata given in the ETS Corpus of Non-Native Written English might have on the automatic detection of metaphors in this dataset.
KIT's IWSLT 2020 SLT Translation System
This paper describes KIT{'}s submissions to the IWSLT2020 Speech Translation evaluation campaign.
Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech
In this paper we present a multidialectal corpus approach for building a text-to-speech voice for a new dialect in a language with existing resources, focusing on various South American dialects of Spanish.
CLARIN: Distributed Language Resources and Technology in a European Infrastructure
CLARIN is a European Research Infrastructure providing access to digital language resources and tools from across Europe and beyond to researchers in the humanities and social sciences.
Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems
We present free high quality multi-speaker speech corpora for Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu, which are six of the twenty two official languages of India spoken by 374 million native speakers.
Creating Expert Knowledge by Relying on Language Learners: a Generic Approach for Mass-Producing Language Resources by Combining Implicit Crowdsourcing and Language Learning
We introduce in this paper a generic approach to combine implicit crowdsourcing and language learning in order to mass-produce language resources (LRs) for any language for which a crowd of language learners can be involved.
Exploring Bilingual Word Embeddings for Hiligaynon, a Low-Resource Language
We use a publicly available Hiligaynon corpus with only 300K words, and match it with a comparable corpus in English.
LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020
We participate in both the open and closed tracks of the shared task and we show improved results of our method compared to simple vector similarity based approaches.
Developing a Corpus of Indirect Speech Act Schemas
Resolving Indirect Speech Acts (ISAs), in which the intended meaning of an utterance is not identical to its literal meaning, is essential to enabling the participation of intelligent systems in peoples{'} everyday lives.
Eidos: An Open-Source Auditory Periphery Modeling Toolkit and Evaluation of Cross-Lingual Phonemic Contrasts
While the auditory periphery mechanisms responsible for transducing the sound pressure wave into the auditory nerve discharge are relatively well understood, the models that describe them are usually very complex because they try to faithfully simulate the behavior of several functionally distinct biological units involved in hearing.
Beyond lexical semantics: notes on pragmatic frames
Framenets as an incarnation of frame semantics have been set up to deal with lexicographic issues (cf.
Voting for POS tagging of Latin texts: Using the flair of FLAIR to better Ensemble Classifiers by Example of Latin
Since most of the available Latin word embeddings were trained on either few or inaccurate data, we trained several embeddings on better data in the first step.
Modelling Frequency and Attestations for OntoLex-Lemon
Therefore, the OntoLex community has put forward the proposal for a novel module for frequency, attestation and corpus information (FrAC), that not only covers the requirements of digital lexicography, but also accommodates essential data structures for lexical information in natural language processing.
Digital Language Infrastructures -- Documenting Language Actors
The major European language infrastructure initiatives like CLARIN (Hinrichs and Krauwer, 2014), DARIAH (Edmond et al., 2017) or Europeana (Europeana Foundation, 2015) have been built by focusing in the first place on institutions of larger scale, like specialized research departments and larger official units like national libraries, etc.
Is Language Modeling Enough? Evaluating Effective Embedding Combinations
We present PubMedSection, a novel topic classification dataset focussed on the biomedical domain.
Open-Source High Quality Speech Datasets for Basque, Catalan and Galician
This paper introduces new open speech datasets for three of the languages of Spain: Basque, Catalan and Galician.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On the Influence of Coreference Resolution on Word Embeddings in Lexical-semantic Evaluation Tasks
The inclusion of CR as a pre-processing step is expected to lead to improvements in downstream tasks.
Using Crowdsourced Exercises for Vocabulary Training to Expand ConceptNet
In this work, we report on a crowdsourcing experiment conducted using the V-TREL vocabulary trainer which is accessed via a Telegram chatbot interface to gather knowledge on word relations suitable for expanding ConceptNet.
Discovering Biased News Articles Leveraging Multiple Human Annotations
Yet, political propaganda and one-sided views can be found in the news and can cause distrust in media.
TextAnnotator: A UIMA Based Tool for the Simultaneous and Collaborative Annotation of Texts
The annotation of texts and other material in the field of digital humanities and Natural Language Processing (NLP) is a common task of research projects.
Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech
This paper introduces an open-source crowd-sourced multi-speaker speech corpus along with the comprehensive set of finite-state transducer (FST) grammars for performing text normalization for the Burmese (Myanmar) language.
Reconstructing NER Corpora: a Case Study on Bulgarian
The paper reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus.
Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu
The experiments are based on recordings from an ongoing documentation project for the endangered Muyu language in New Guinea.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
TheRuSLan: Database of Russian Sign Language
The database includes lexical units (single words and phrases) from Russian sign language within one subject area, namely, {``}food products at the supermarket{''}, and was collected using MS Kinect 2. 0 device including both FullHD video and the depth map modes, which provides new opportunities for the lexicographical description of the Russian sign language vocabulary and enhances research in the field of automatic gesture recognition.
Transfer of ISOSpace into a 3D Environment for Annotations and Applications
People{'}s visual perception is very pronounced and therefore it is usually no problem for them to describe the space around them in words.
Open-source Multi-speaker Corpora of the English Accents in the British Isles
This paper presents a dataset of transcribed high-quality audio of English sentences recorded by volunteers speaking with different accents of the British Isles.
CAMeL Tools: An Open Source Python Toolkit for Arabic Natural Language Processing
We present CAMeL Tools, a collection of open-source tools for Arabic natural language processing in Python.
Consistent Unsupervised Estimators for Anchored PCFGs
Learning probabilistic context-free grammars (PCFGs) from strings is a classic problem in computational linguistics since Horning (1969).
Fact Checking or Psycholinguistics: How to Distinguish Fake and True Claims?
The goal of our paper is to compare psycholinguistic text features with fact checking approaches to distinguish lies from true statements.
BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature
The Specialized Information Service Biodiversity Research (BIOfid) has been launched to mobilize valuable biological data from printed literature hidden in German libraries for over the past 250 years.
Automatic identification of writers' intentions: Comparing different methods for predicting relationship goals in online dating profile texts
Results show that LIWC and machine learning models correlate with human evaluations in terms of content-related labels.
Saarland at MRP 2019: Compositional parsing across all graphbanks
We describe the Saarland University submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference on Computational Natural Language Learning (CoNLL).
A Personalized Data-to-Text Support Tool for Cancer Patients
In this paper, we present a novel data-to-text system for cancer patients, providing information on quality of life implications after treatment, which can be embedded in the context of shared decision making.
Generating Abstractive Summaries with Finetuned Language Models
Neural abstractive document summarization is commonly approached by models that exhibit a mostly extractive behavior.
Talking about what is not there: Generating indefinite referring expressions in Minecraft
When generating technical instructions, it is often necessary to describe an object that does not exist yet.
Best practices for the human evaluation of automatically generated text
Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated.
v-trel: Vocabulary Trainer for Tracing Word Relations - An Implicit Crowdsourcing Approach
In this paper, we present our work on developing a vocabulary trainer that uses exercises generated from language resources such as ConceptNet and crowdsources the responses of the learners to enrich the language resource.
Know Your Graph. State-of-the-Art Knowledge-Based WSD
This paper introduces several improvements over the current state of the art in knowledge-based word sense disambiguation.
Combining Lexical Substitutes in Neural Word Sense Induction
Word Sense Induction (WSI) is the task of grouping of occurrences of an ambiguous word according to their meaning.
Predicting Sentiment of Polish Language Short Texts
In the second we train models on all available data except the given test collection, which we use for testing (one vs rest cross-domain).
Graph Embeddings for Frame Identification
Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource.
The LMU Munich Unsupervised Machine Translation System for WMT19
We describe LMU Munich{'}s machine translation system for German→Czech translation which was used to participate in the WMT19 shared task on unsupervised news translation.
Combining Local and Document-Level Context: The LMU Munich Neural Machine Translation System at WMT19
We describe LMU Munich{'}s machine translation system for English→German translation which was used to participate in the WMT19 shared task on supervised news translation.
Detection of Adverse Drug Reaction in Tweets Using a Combination of Heterogeneous Word Embeddings
This paper details our approach to the task of detecting reportage of adverse drug reaction in tweets as part of the 2019 social media mining for healthcare applications shared task.
The Meaning of ``Most'' for Visual Question Answering Models
The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms.
A Dataset for Noun Compositionality Detection for a Slavic Language
This paper presents the first gold-standard resource for Russian annotated with compositionality information of noun compounds.
A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance
We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input.
PROMT Systems for WMT 2019 Shared Translation Task
This paper describes the PROMT submissions for the WMT 2019 Shared News Translation Task.
On the Compositionality Prediction of Noun Phrases using Poincar\'e Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar{\'e} embeddings in addition to the distributional information to detect compositionality for noun phrases.
Improving Neural Entity Disambiguation with Graph Embeddings
Entity Disambiguation (ED) is the task of linking an ambiguous entity mention to a corresponding entry in a knowledge base.
Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation
Mining parallel sentences from comparable corpora is important.
Large-Scale Transfer Learning for Natural Language Generation
Large-scale pretrained language models define state of the art in natural language processing, achieving outstanding performance on a variety of tasks.
TARGER: Neural Argument Mining at Your Fingertips
We present TARGER, an open source neural argument mining framework for tagging arguments in free input texts and for keyword-based retrieval of arguments from an argument-tagged web-scale corpus.
Better OOV Translation with Bilingual Terminology Mining
In our experiments we use a system trained on Europarl and mine sentences containing medical terms from monolingual data.
Graph-Based Meaning Representations: Design and Processing
This tutorial is on representing and processing sentence meaning in the form of labeled directed graphs.
HHU at SemEval-2019 Task 6: Context Does Matter - Tackling Offensive Language Identification and Categorization with ELMo
We present our results for OffensEval: Identifying and Categorizing Offensive Language in Social Media (SemEval 2019 - Task 6).
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities
Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora.
Neural GRANNy at SemEval-2019 Task 2: A combined approach for better modeling of semantic relationships in semantic frame induction
We describe our solutions for semantic frame and role induction subtasks of SemEval 2019 Task 2.
Scalable Methods for Annotating Legal-Decision Corpora
Recent research has demonstrated that judicial and administrative decisions can be predicted by machine-learning models trained on prior decisions.
Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging
We tackle the important task of part-of-speech tagging using a neural model in the zero-resource scenario, where we have no access to gold-standard POS training data.
CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter
The goal of this paper is to detect (A) Hate speech against immigrants and women, (B) Aggressive behavior and target classification, both for English and Spanish.
Enriching the WebNLG corpus
This paper describes the enrichment of WebNLG corpus (Gardent et al., 2017a, b), with the aim to further extend its usefulness as a resource for evaluating common NLG tasks, including Discourse Ordering, Lexicalization and Referring Expression Generation.
E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language
In natural language generation (NLG), the task is to generate utterances from a more abstract input, such as structured data.
Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem
An increasing amount of research tackles the challenge of text generation from abstract ontological or semantic structures, which are in their very nature potentially large connected graphs.
Debugging Sequence-to-Sequence Models with Seq2Seq-Vis
Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks.
Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods
The current study investigated novel techniques and methods for trainable approaches to data-to-text generation.
Training for Diversity in Image Paragraph Captioning
Image paragraph captioning models aim to produce detailed descriptions of a source image.
Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments
We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7. 02 BLEU for coreference and 1. 89 BLEU for coherence on subtitles translation.
IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis
Sentiment analysis has immense implications in e-commerce through user feedback mining.
The LMU Munich Unsupervised Machine Translation Systems
We describe LMU Munich{'}s unsupervised machine translation systems for English↔German translation.
LMU Munich's Neural Machine Translation Systems at WMT 2018
The systems were used for our participation in the WMT18 biomedical translation task and in the shared task on machine translation of news.
Complementary Strategies for Low Resourced Morphological Modeling
Morphologically rich languages are challenging for natural language processing tasks due to data sparsity.
The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018
We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German.
PROMT Systems for WMT 2018 Shared Translation Task
This paper describes the PROMT submissions for the WMT 2018 Shared News Translation Task.
Automatic Identification of Drugs and Adverse Drug Reaction Related Tweets
We describe our submissions to the Third Social Media Mining for Health Applications Shared Task.
An Unsupervised System for Parallel Corpus Filtering
In this paper we describe LMU Munich{'}s submission for the \textit{WMT 2018 Parallel Corpus Filtering} shared task which addresses the problem of cleaning noisy parallel corpora.
Aggression Detection in Social Media: Using Deep Neural Networks, Data Augmentation, and Pseudo Labeling
On this task, we investigate the efficacy of deep neural network models of varying complexity.
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning
{\%} Combining these techniques, we are able to provide an adapted speech translation system for several European languages.
Evaluating the text quality, human likeness and tailoring component of PASS: A Dutch data-to-text system for soccer
We present an evaluation of PASS, a data-to-text system that generates Dutch soccer reports from match statistics which are automatically tailored towards fans of one club or the other.
Transfer Learning for Entity Recognition of Novel Classes
Our results empirically demonstrate when each of the published approaches tends to do well.
Entity Extraction using GAN
Named Entity Recognition (NER)
+2
LTV: Labeled Topic Vector
In this paper we present LTV, a website and API that generates labeled topic classifications based on the Dewey Decimal Classification (DDC), an international standard for topic classification in libraries.
Aspect-based summarization of pros and cons in unstructured product reviews
In the second evaluation, the gold-standard pros and cons were assessed along with the system output.
DeepPavlov: Open-Source Library for Dialogue Systems
It supports modular as well as end-to-end approaches to implementation of conversational agents.
The Annotated Transformer
A major goal of open-source NLP is to quickly and accurately reproduce the results of new work, in a manner that the community can easily use and modify.
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
We present a system description of the OpenNMT Neural Machine Translation entry for the WNMT 2018 evaluation.
Discourse Coherence: Concurrent Explicit and Implicit Relations
Theories of discourse coherence posit relations between discourse segments as a key feature of coherent text.
Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach
This study describes the approach developed by the Tilburg University team to the shallow task of the Multilingual Surface Realization Shared Task 2018 (SR18).
Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable
Bilingual tasks, such as bilingual lexicon induction and cross-lingual classification, are crucial for overcoming data sparsity in the target language.
Addressing Noise in Multidialectal Word Embeddings
Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling.
UMD at SemEval-2018 Task 10: Can Word Embeddings Capture Discriminative Attributes?
We describe the University of Maryland{'}s submission to SemEval-018 Task 10, {``}Capturing Discriminative Attributes{''}: given word triples (w1, w2, d), the goal is to determine whether d is a discriminating attribute belonging to w1 but not w2.
Modeling Second-Language Learning from a Psychological Perspective
Psychological research on learning and memory has tended to emphasize small-scale laboratory studies.
Evaluating bilingual word embeddings on the long tail
Bilingual word embeddings are useful for bilingual lexicon induction, the task of mining translations of given words.
ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings
In this paper we describe our system for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1. 1) and noisy data (subtask 1. 2).
Noise-Robust Morphological Disambiguation for Dialectal Arabic
User-generated text tends to be noisy with many lexical and orthographic inconsistencies, making natural language processing (NLP) tasks more challenging.
Using Language Learner Data for Metaphor Detection
This article describes the system that participated in the shared task on metaphor detection on the Vrije University Amsterdam Metaphor Corpus (VUA).
PunFields at SemEval-2018 Task 3: Detecting Irony by Tools of Humor Analysis
The paper describes our search for a universal algorithm of detecting intentional lexical ambiguity in different forms of creative language.
Complex Word Identification: Convolutional Neural Network vs. Feature Engineering
We describe the systems of NLP-CIC team that participated in the Complex Word Identification (CWI) 2018 shared task.
Multi-Module Recurrent Neural Networks with Transfer Learning
This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection.
Detecting Figurative Word Occurrences Using Recurrent Neural Networks
The paper addresses detection of figurative usage of words in English text.
Literal, Metphorical or Both? Detecting Metaphoricity in Isolated Adjective-Noun Phrases
The paper addresses the classification of isolated Polish adjective-noun phrases according to their metaphoricity.
NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis
In this paper, we describe a deep learning framework for analyzing the customer feedback as part of our participation in the shared task on Customer Feedback Analysis at the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017).
Event Ordering with a Generalized Model for Sieve Prediction Ranking
Within this prediction reranking framework, we propose an alternative scoring function, showing an 8. 8{\%} relative gain over the original CAEVO.
Entity-Centric Information Access with Human in the Loop for the Biomedical Domain
In this paper, we describe the concept of entity-centric information access for the biomedical domain.
Coarse-to-Fine Attention Models for Document Summarization
Sequence-to-sequence models with attention have been successful for a variety of NLP problems, but their speed does not scale well for tasks with long source sequences such as document summarization.
Ranked #25 on
Document Summarization
on CNN / Daily Mail