TY - GEN
T1 - Decoding the Hierarchy
T2 - 47th European Conference on Information Retrieval, ECIR 2025
AU - Torba, Fatos
AU - Gravier, Christophe
AU - Laclau, Charlotte
AU - Kammoun, Abderrhammen
AU - Subercaze, Julien
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - Hierarchical multi-label text classification (HMTC) aims to predict multiple labels from a tree-like hierarchy for a given input text. Recent approaches frame HMTC as a seq2seq problem, where the objective is to predict the sequence of associated labels, regardless of their order or position in the hierarchy. Despite promising results, these approaches rely solely on attention mechanisms from previously generated tokens. This limit prevents them from acquiring information about the global hierarchy and may lead to the accumulation of errors as the model learns hierarchical cues among labels. We propose a novel HMTC model based on a hybrid version of the encoder-decoder architecture where the decoder is pre-populated with the entire label embeddings. By leveraging the decoder’s Cross-Attention and Hierarchical Self-Attention mechanisms, we achieve a label representation that benefits from instance and global label-wise information. Empirical experiments on four HMTC benchmark datasets demonstrated the effectiveness of our approach by settling new state-of-the-art results. Code (https://github.com/FatosTorba/HLPD) and datasets are made available to facilitate the reproducibility and future work.
AB - Hierarchical multi-label text classification (HMTC) aims to predict multiple labels from a tree-like hierarchy for a given input text. Recent approaches frame HMTC as a seq2seq problem, where the objective is to predict the sequence of associated labels, regardless of their order or position in the hierarchy. Despite promising results, these approaches rely solely on attention mechanisms from previously generated tokens. This limit prevents them from acquiring information about the global hierarchy and may lead to the accumulation of errors as the model learns hierarchical cues among labels. We propose a novel HMTC model based on a hybrid version of the encoder-decoder architecture where the decoder is pre-populated with the entire label embeddings. By leveraging the decoder’s Cross-Attention and Hierarchical Self-Attention mechanisms, we achieve a label representation that benefits from instance and global label-wise information. Empirical experiments on four HMTC benchmark datasets demonstrated the effectiveness of our approach by settling new state-of-the-art results. Code (https://github.com/FatosTorba/HLPD) and datasets are made available to facilitate the reproducibility and future work.
KW - Hierarchical Multi-label Text Classification
KW - Hierarchical Self-Attention Mechanism
KW - Reproducibility
KW - Seq2Seq
UR - https://www.scopus.com/pages/publications/105003300592
U2 - 10.1007/978-3-031-88708-6_26
DO - 10.1007/978-3-031-88708-6_26
M3 - Conference contribution
AN - SCOPUS:105003300592
SN - 9783031887079
T3 - Lecture Notes in Computer Science
SP - 405
EP - 420
BT - Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Proceedings
A2 - Hauff, Claudia
A2 - Macdonald, Craig
A2 - Jannach, Dietmar
A2 - Kazai, Gabriella
A2 - Nardini, Franco Maria
A2 - Pinelli, Fabio
A2 - Silvestri, Fabrizio
A2 - Tonellotto, Nicola
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 6 April 2025 through 10 April 2025
ER -