Martin Schmitt

I am a PhD student in Natural Language Processing and Machine Learning at CIS (Center for Information and Language Processing), Munich University (LMU Munich), supervised by Prof. Dr. Hinrich Schütze.
My current research focus lies in computational models of context-sensitive relation inference.

Research interests

Deep Learning and Neural Networks for NLP
Machine Learning for Knowledge Graphs (cf. the MLWin project)
Representation Learning (Character, Word, Phrase Embeddings)
Character-Level Models
Lexical Semantics
Multimodal Learning (esp. Visual Grounding)
Common Sense Reasoning

Publications

Martin Schmitt and Hinrich Schütze.
Language Models for Lexical Inference in Context.
In: Proceedings of the 2021 Conference of the European Chapter of the Association for Computational Linguistics (EACL),
Online, April 2019.
preprint

Philipp Dufter, Martin Schmitt, and Hinrich Schütze.
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention.
In: Proceedings of the 28th International Conference on Computational Linguistics (COLING, Short Paper),
Online, December 2020. (Acceptance rate: 26.2%)
paper bib

Martin Schmitt, Sahand Sharifzadeh, Volker Tresp, and Hinrich Schütze.
An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing.
In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP),
Online, November 2020. (Acceptance rate: 24.6%)
paper bib code data slides video

Marina Speranskaya, Martin Schmitt and Benjamin Roth.
Ranking vs. Classifying: Measuring Knowledge Base Completion Quality.
In: 2nd Conference on Automated Knowledge Base Construction (AKBC), 2020.
paper bib data

Martin Schmitt and Hinrich Schütze.
SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference.
In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL),
Florence, Italy, July 2019. (Acceptance rate: 25.7%)
paper bib code data poster page video

Stefan Evert, Philipp Heinrich, Klaus Henselmann, Ulrich Rabenstein, Elisabeth Scherr, Martin Schmitt and Lutz Schröder.
Combining Machine Learning and Semantic Features in the Classification of Corporate Disclosures.
In: Journal of Logic, Language and Information (JoLLI), 2019. (Impact factor: 0.536)
preprint bib view online

Martin Schmitt, Simon Steinheber, Konrad Schreiber and Benjamin Roth.
Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks .
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP, Short Paper),
Brussels, Belgium, November 2018. (Acceptance rate: 23.2%)
paper bib poster page

Philipp Dufter, Mengjie Zhao, Martin Schmitt, Alexander Fraser and Hinrich Schütze.
Embedding Learning Through Multilingual Concept Induction.
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL),
Melbourne, Australia, July 2018. (Acceptance rate: 25.3%)
paper bib

Honors and Awards

I was awarded a Ph.D. scholarship by the German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes).