English
Related papers

Related papers: A Multi-head-based architecture for effective morp…

200 papers

Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search. We link this problem to the classic problem of Chinese word segmentation and show…

Computation and Language · Computer Science 2021-02-22 Hao Zhang , Jae Ro , Richard Sproat

Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful SFT dataset, while their definitions remain obscure and lack…

Computation and Language · Computer Science 2023-08-16 Keming Lu , Hongyi Yuan , Zheng Yuan , Runji Lin , Junyang Lin , Chuanqi Tan , Chang Zhou , Jingren Zhou

Training recurrent neural networks on long texts, in particular scholarly documents, causes problems for learning. While hierarchical attention networks (HANs) are effective in solving these problems, they still lose important information…

Neural language models (LMs) have shown to benefit significantly from enhancing word vectors with subword-level information, especially for morphologically rich languages. This has been mainly tackled by providing subword-level information…

Computation and Language · Computer Science 2019-10-28 Yash Shah , Ishan Tarunesh , Harsh Deshpande , Preethi Jyothi

We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…

Machine Learning · Computer Science 2025-02-11 Artem Basharin , Andrei Chertkov , Ivan Oseledets

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…

Computation and Language · Computer Science 2022-06-02 Andrea Lekkas , Peter Schneider-Kamp , Isabelle Augenstein

We introduce GigaEmbeddings, a novel framework for training high-performance Russian-focused text embeddings through hierarchical instruction tuning of the decoder-only LLM designed specifically for Russian language (GigaChat-3B). Our…

Computation and Language · Computer Science 2025-10-28 Egor Kolodin , Daria Khomich , Nikita Savushkin , Anastasia Ianina , Fyodor Minkin

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form. Using Universal Dependencies, we apply inference-time perturbations: full token scrambling,…

Computation and Language · Computer Science 2026-03-03 Anna Feldman , Libby Barak , Jing Peng

Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Nicola Messina , Giuseppe Amato , Fabrizio Falchi , Claudio Gennaro , Stéphane Marchand-Maillet

Topic modeling has been one of the most active research areas in machine learning in recent years. Hierarchical latent tree analysis (HLTA) has been recently proposed for hierarchical topic modeling and has shown superior performance over…

Computation and Language · Computer Science 2020-07-13 Leonard K. M. Poon , Nevin L. Zhang , Haoran Xie , Gary Cheng

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch

Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more. For most languages, this tokenization step straightforward.…

Computation and Language · Computer Science 2022-03-22 Idan Brusilovsky , Reut Tsarfaty

The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these models is the presence of rich initial word encodings.…

Computation and Language · Computer Science 2018-05-23 Bernd Bohnet , Ryan McDonald , Goncalo Simoes , Daniel Andor , Emily Pitler , Joshua Maynez

In this work, we adhere to explore a Multi-Tasking learning (MTL) based network to perform document attribute classification such as the font type, font size, font emphasis and scanning resolution classification of a document image. To…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Tanmoy Mondal , Abhijit Das , Zuheng Ming

There are a plethora of methods and algorithms that solve the classical multi-label document classification. However, when it comes to deployment and usage in an industry setting, most, if not all the contemporary approaches fail to address…

Computation and Language · Computer Science 2023-01-18 Arshad Javeed

Large language models (LLMs) have become the cornerstone of modern AI. However, the existing paradigm of next-token prediction fundamentally limits their ability to form coherent, high-level concepts, making it a critical barrier to…

Machine Learning · Computer Science 2025-06-16 Michael K. Chen , Xikun Zhang , Jiaxing Huang , Dacheng Tao

With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological…

Computation and Language · Computer Science 2021-09-15 Ayyoob Imani , Masoud Jalili Sabet , Lütfi Kerem Şenel , Philipp Dufter , François Yvon , Hinrich Schütze

Neural morphological tagging has been regarded as an extension to POS tagging task, treating each morphological tag as a monolithic label and ignoring its internal structure. We propose to view morphological tags as composite labels and…

Computation and Language · Computer Science 2018-10-23 Alexander Tkachenko , Kairit Sirts

With growing amounts of available textual data, development of algorithms capable of automatic analysis, categorization and summarization of these data has become a necessity. In this research we present a novel algorithm for keyword…

Computation and Language · Computer Science 2021-12-01 Matej Martinc , Blaž Škrlj , Senja Pollak

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…

Computation and Language · Computer Science 2014-01-23 Tahira Naseem , Benjamin Snyder , Jacob Eisenstein , Regina Barzilay