• Publications
  • Influence
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
TLDR
This paper investigates strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality and validate the new metric, namely MoverScore, on a number of text generation tasks.
Neural End-to-End Learning for Computational Argumentation Mining
TLDR
This work investigates neural techniques for end-to-end computational argumentation mining and finds that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
TLDR
This work investigates the impact of visual adversarial attacks on current NLP systems on character-, word-, and sentence-level tasks, showing that both neural and non-neural models are, in contrast to humans, extremely sensitive to such attacks, suffering performance decreases of up to 82%.
What is the Essence of a Claim? Cross-Domain Claim Identification
TLDR
While the divergent conceptualization of claims in different datasets is indeed harmful to cross-domain classification, it is shown that there are shared properties on the lexical level as well as system configurations that can help to overcome these gaps.
Concatenated p-mean Word Embeddings as Universal Cross-Lingual Sentence Representations
TLDR
It is shown that the concatenation of different types of power mean word embeddings considerably closes the gap to state-of-the-art methods monolingually and substantially outperforms these more complex techniques cross-lingually.
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization
TLDR
This work proposes SUPERT, which rates the quality of a summary by measuring its semantic similarity with a pseudo reference summary, i.e. selected salient sentences from the source documents, using contextualized embeddings and soft token alignment techniques.
ArgumenText: Searching for Arguments in Heterogeneous Sources
TLDR
This paper presents an argument retrieval system capable of retrieving sentential arguments for any given controversial topic, and finds that its system covers 89% of arguments found in expert-curated lists of arguments from an online debate portal, and also identifies additional valid arguments.
On the Linearity of Semantic Change: Investigating Meaning Variation via Dynamic Graph Models
TLDR
It is found that semantic change is linear in two senses: today’s embedding vector (= meaning) of words can be derived as linear combinations of embedding vectors of their neighbors in previous time periods.
Lexicon-assisted tagging and lemmatization in Latin: A comparison of six taggers and two lemmatization methods
We present a survey of tagging accuracies — concerning part-of-speech and full morphological tagging — for several taggers based on a corpus for medieval church Latin (see www.comphistsem.org). The
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
TLDR
An agreement score to evaluate the performance of routing processes at instance-level, an adaptive optimizer to enhance the reliability of routing, and capsule compression and partial routing to improve the scalability of capsule networks are introduced.
...
1
2
3
4
5
...