Articles

In this paper, we investigate the effect of layer freezing on the effectiveness of model trans- fer in the area of automatic speech recogni- tion. We experiment with Mozilla’s Deep- Speech architecture on German and Swiss Ger- man speech datasets and compare the results of either training from scratch vs. …...

When evaluating the performance of auto- matic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic perfor- mance numbers. We argue that many perfor- mance numbers reported probably underesti- mate the expected …...

Although sentiment is conceptualized as a con- tinuous variable, most text-based sentiment analyses categorize texts into discrete senti- ment categories. Compared to discrete catego- rizations, continuous sentiment estimates pro- vide much more detailed information which can be used for more fine-grained analyses by researchers and practitioners alike. Yet, exist- ing …...

Online user comments in public forums are of- ten associated with low quality, hate speech or even excessive demands for moderation. To better exploit their constructive and deliber- ate potential, we present forumBERT. forum- BERT is built on top of the BERT architec- ture and uses a shared weight and …...

We apply neural coreference resolution to German, surpassing the previous state-of-the- art performance by a wide margin of 10– 30 points F1 across three established datasets for German. This is achieved by a neural end-to-end approach, training contextual word- embeddings jointly with mention and entity similarity scores. We explore the …...

Preprocessing is essential for creating more ef- fective features and reducing noise in classifi- cation, especially in user-generated data (e.g. Twitter). How each individual preprocessing decision changes an individual classifier’s be- havior is not universal. We perform a series of ablation experiments in which we examine how classifiers behave based …...

This paper investigates the use of first per- son plural pronouns as a rhetorical device in political speeches. We present an anno- tation schema for disambiguating pronoun references and use our schema to create an annotated corpus of debates from the Ger- man Bundestag. We then use our corpus to …...

With the increasing importance of social me- dia in everyone’s life, the risk of its misuse by criminals is also increasing. In particular children are at risk of becoming victims of on- line related crime, especially sexual abuse. For example, sexual predators use online groom- ing to gain the trust …...

Due to a lack of annotated data, theories of historical syntax are often based on very small, manually compiled data sets. To enable the empirical evaluation of existing hypotheses, the present study explores the automatic recogni- tion of phrases in historical German. Using modern and historical treebanks, training data for …...

Existing datasets and methods that aim at the identification of time expressions in natural language text do not pay particular attention to expressions that are imprecise and that can- not be easily represented on a timeline. We call these vague time expressions (VTEs). We present an analysis of existing time …...

We present the results of an evaluation study in the context of lexicon-based sentiment analy- sis resources for German texts. We have set up a comprehensive compilation of 19 sentiment lexicon resources and 20 sentiment-annotated corpora available for German across multiple domains. In addition to the evaluation of the sentiment …...

We extract definitions from text books and sci- entific publications on mathematics in both, German and English, from the sub-domain of graph theory. Mathematical texts differ from other domains because sentences which appear as definitions from a linguistic perspective are not necessarily definitions in the mathematical sense. For the English …...

Emotion stimulus extraction is a fine-grained subtask of emotion analysis that focuses on identifying the description of the cause behind an emotion expression from a text passage (e.g., in the sentence “I am happy that I passed my exam” the phrase “passed my exam” cor- responds to the stimulus.). Previous …...

Emotion classification in text is typically per- formed with neural network models which learn to associate linguistic units with emo- tions. While this often leads to good predic- tive performance, it does only help to a limited degree to understand how emotions are com- municated in various domains. The emotion …...

In this research, we investigate techniques to detect hate speech in movies. We introduce a new dataset collected from the subtitles of six movies, where each utterance is annotated ei- ther as hate, offensive or normal. We apply transfer learning techniques of domain adapta- tion and fine-tuning on existing social …...

Argumentation is an important tool within hu- man interaction, not only in law and politics but also for discussing issues, expressing and exchanging opinions and coming to decisions in our everyday life. Applications for argu- mentation often require the measurement of the arguments’ similarity, to solve tasks like clustering, paraphrase …...

In this study we investigate to which degree experts and non-experts agree on questions of dificulty in a crowdsourcing experiment. We ask non-experts (second language learners of Swedish) and two groups of experts (teachers of Swedish as a second/foreign language and CEFR experts) to rank multi-word expressions in a crowdsourcing …...

AbstractAimed at generating a seed lexicon for use in downstream natural language tasks and unsupervised methods for bilingual lexicon induction have received much attention in the academic literature recently. While interesting and fully unsupervised settings are unrealistic; small amounts of bilingual data are usually available due to the existence of …...

AbstractThe paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical entries and does not require any modification to the training data or model architecture. …...

AbstractThe quality of the translations generated by Machine Translation (MT) systems has highly improved through the years and but we are still far away to obtain fully automatic high-quality translations. To generate them and translators make use of Computer-Assisted Translation (CAT) tools and among which we find the Interactive-Predictive Machine …...