🧑‍🔬 Katja Filippova

🏛️ Affiliations

🏢GoogleMountain View · United States2010–2026 · 14 paperscurrent🎓New York UniversityNew York · United States2018–2026 · 4 paperscurrent🎓Brown UniversityProvidence · United States2026 · 1 papercurrent🏢European Media LaboratoryHeidelberg · Germany2006–2009 · 7 papers🏢GoogleZurich · Switzerland2011–2018 · 5 papers🏢Google DeepMindLondon · United Kingdom2021–2025 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

2000s

📄 Papers

The most cited first (OpenAlex and our library).

1. Sentence Compression by Deletion with LSTMs (2015 · 338 citations)
   Most deletion-based sentence compressors depend on parsers, PoS taggers, or other linguistic preprocessing.
2. The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? (2020 · 219 citations)
   This position paper asks why the NLP community keeps arguing over whether attention weights count as explanations, when an established family of tools already exists for the job attention is usually asked to do.
3. Overcoming the Lack of Parallel Data in Sentence Compression (2013 · 205 citations)
   Supervised deletion-based sentence compression has long been limited by a lack of training data. Existing parallel corpora such as Ziff-Davis and the two Edinburgh sets hold only about a thousand pairs each, which makes rich or lexicalized features impractical. Filippova and Altun propose an automatic way to harvest…
4. Tree Linearization in English: Improving Language Model Based Approaches (2009 · 57 citations)
   The paper compares two ways of turning a dependency tree into a word string in English. The standard method ("overgenerate and rank") makes all permutations allowed by a few hard constraints and picks the one a trigram language model prefers. The second method keeps the trigram model for the order inside phrases, and…

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Sentence Compression by Deletion with LSTMsConference on Empirical Methods in Natural Language Processing (EMNLP)Katja Filippova, Enrique Alfonseca, Carlos A. Colmenares, et al.2015 · 338 citations
2. The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLPJasmijn Bastings, Katja Filippova2020 · 219 citations
3. Overcoming the Lack of Parallel Data in Sentence CompressionConference on Empirical Methods in Natural Language Processing (EMNLP)Katja Filippova, Yasemin Altun2013 · 205 citations
4. Generating Constituent Order in German Clauses ↗Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics · no summary yetKatja Filippova, Michael Strube2007 · 67 citations
5. Tree Linearization in English: Improving Language Model Based ApproachesKatja Filippova, Michael StrubeEnglish · 57 citations

🤝 Co-authors here

6 co-authors with a page, the most papers together first.

• Enrique Alfonseca
• Jasmijn Bastings
• Lukasz Kaiser
• Michael Strube
• Oriol Vinyals
• Yasemin Altun

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2015, EMNLP 2013
• BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2009
• Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

🔗 Cited by

Papers of our library cite their works 284 times (of the 141,840 papers whose bibliographies we read); 37 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/katja-filippova/