Maciej Janicki


2023

pdf
Detection and attribution of quotes in Finnish news media: BERT vs. rule-based approach
Maciej Janicki | Antti Kanner | Eetu Mäkelä
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)

We approach the problem of recognition and attribution of quotes in Finnish news media. Solving this task would create possibilities for large-scale analysis of media wrt. the presence and styles of presentation of different voices and opinions. We describe the annotation of a corpus of media texts, numbering around 1500 articles, with quote attribution and coreference information. Further, we compare two methods for automatic quote recognition: a rule-based one operating on dependency trees and a machine learning one built on top of the BERT language model. We conclude that BERT provides more promising results even with little training data, achieving 95% F-score on direct quote recognition and 84% for indirect quotes. Finally, we discuss open problems and further associated tasks, especially the necessity of resolving speaker mentions to entity references.

2022

pdf
Optimizing the weighted sequence alignment algorithm for large-scale text similarity computation
Maciej Janicki
Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities

We present an optimized implementation of the weighted sequence alignment algorithm (a.k.a. weighted edit distance) in a scenario where the items to align are numeric vectors and the substitution weights are determined by their cosine similarity. The optimization relies on using vector and matrix operations provided by numeric computation libraries (including GPU acceleration) instead of loops. The resulting algorithm provides an efficient way of aligning large sets of texts represented as sequences of continuous-space numeric vectors (embeddings). The optimization made it possible to compute alignment-based similarity for all pairs of texts in a large corpus of Finnic oral folk poetry for the purpose of studying intertextuality in the oral tradition.

2019

pdf
Finite State Transducer Calculus for Whole Word Morphology
Maciej Janicki
Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing

The research on machine learning of morphology often involves formulating morphological descriptions directly on surface forms of words. As the established two-level morphology paradigm requires the knowledge of the underlying structure, it is not widely used in such settings. In this paper, we propose a formalism describing structural relationships between words based on theories of morphology that reject the notions of internal word structure and morpheme. The formalism covers a wide variety of morphological phenomena (including non-concatenative ones like stem vowel alternation) without the need of workarounds and extensions. Furthermore, we show that morphological rules formulated in such way can be easily translated to FSTs, which enables us to derive performant approaches to morphological analysis, generation and automatic rule discovery.

pdf
Semi-Supervised Induction of POS-Tag Lexicons with Tree Models
Maciej Janicki
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)

We approach the problem of POS tagging of morphologically rich languages in a setting where only a small amount of labeled training data is available. We show that a bigram HMM tagger benefits from re-training on a larger untagged text using Baum-Welch estimation. Most importantly, this estimation can be significantly improved by pre-guessing tags for OOV words based on morphological criteria. We consider two models for this task: a character-based recurrent neural network, which guesses the tag from the string form of the word, and a recently proposed graph-based model of morphological transformations. In the latter, the unknown POS tags can be modeled as latent variables in a way very similar to Hidden Markov Tree models and an analogue of the Forward-Backward algorithm can be formulated, which enables us to compute expected values over unknown taggings. We evaluate both the quality of the induced tag lexicon and its impact on the HMM’s tagging accuracy. In both tasks, the graph-based morphology model performs significantly better than the RNN predictor. This confirms the intuition that morphologically related words provide useful information about an unknown word’s POS tag.

2013

pdf
Unsupervised Learning of A-Morphous Inflection with Graph Clustering
Maciej Janicki
Proceedings of the Student Research Workshop associated with RANLP 2013