Papers with FSTs
Morphology Matters: A Multilingual Language Modeling Analysis (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing studies on inflectional morphology disagree on whether or not it makes languages harder to model. |
| Approach: | They propose to use a corpus of 145 Bible translations in 92 languages to investigate whether inflectional morphology makes languages harder to model. |
| Outcome: | The proposed model trains with linguistically motivated subword segmentation strategies and reduces the impact of morphology on language modeling. |
Neural Text Normalization with Subword Units (N19-2)
Copied to clipboard
| Challenge: | Text normalization (TN) is an important step in conversational systems. |
| Approach: | They frame text normalization as a machine translation task and tackle it with sequence-to-sequence models. |
| Outcome: | The proposed model normalizes written text to its spoken form to facilitate speech recognition and text-to-speech synthesis. |
DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing large language model (LLM) agents for data science automation are limited by narrow task scopes, limited generalization across tasks and models, and over-reliance on state-of-the-art (SOTA) LLMs. |
| Approach: | They propose a notebook-centric LLM agent framework for adaptive and robust data science automation. |
| Outcome: | The proposed framework surpasses baselines such as AutoGen and TaskWeaver in performance tests across diverse data science scenarios and models. |
Composing Finite State Transducers on GPUs (P18-1)
Copied to clipboard
| Challenge: | Weighted finite state transducers (FSTs) are used in language processing . a GPU implementation of the composition operation is currently under development . |
| Approach: | They propose a GPU implementation of the composition operation for weighted finite state transducers. |
| Outcome: | The proposed approach achieves speedups of up to 6 times over the serial implementation and 4.5 times over OpenFST on the GPU. |
SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation (2024.acl-long)
Copied to clipboard
| Challenge: | Popular neural architectures lack strong structural inductive biases for seq2seq NLP tasks . previous work shows that these models struggle with systematic generalization . |
| Approach: | They propose to inject a structural inductive bias into a seq2seq model by pre-training it to simulate structural transformations on synthetic data. |
| Outcome: | The proposed method improves few-shot learning and generalization of FST-like models. |
Recovering Missing Characters in Old Hawaiian Writing (D18-1)
Copied to clipboard
| Challenge: | Modern Hawaiian orthography includes characters for long vowels and glottal stops . manual transliteration is laborious when performed manually . |
| Approach: | They propose two methods to help transliterate Hawaiian between older and newer texts automatically using finite state transducers and a recurrent neural network language model. |
| Outcome: | The proposed method solves the transliteration problem automatically using finite state transducers and a neural network language model. |
FSTs vs ICL: Generalisation in LLMs for an under-resourced language (2025.findings-emnlp)
Copied to clipboard
| Challenge: | LLMs have been widely adopted to tackle many traditional NLP tasks, but their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language. |
| Approach: | They propose a rule-based method using a finite-state transducer and an in-context learning method that provides the model with string transduction examples. |
| Outcome: | The proposed method outperforms FSTs in zero-shot settings while ICL surpasses FLMs. |
Neural Induction of Finite-State Transducers (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to construct finite-state transducers by hand are difficult and require domain knowledge and significant human effort. |
| Approach: | They propose a method for automatically constructing unweighted FSTs following the hidden state geometry learned by a recurrent neural network. |
| Outcome: | The proposed method outperforms classical transducer learning algorithms by up to 87% accuracy on held-out test sets. |