Papers with FST
Neural Search Space in Gboard Decoder (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Gboard decoder uses context, a lexicon and language models to provide a user-friendly keyboard. |
| Approach: | They propose a Neural Search Space which replaces an N-gram LM with a neural network LM and dynamically constructs the search space during decoding. |
| Outcome: | The proposed system improves the quality of the decoded keyboards on various locales with acceptable latency increases. |
Improving Formality Style Transfer with Context-Aware Rule Injection (2021.acl-long)
Copied to clipboard
| Challenge: | Existing language models pre-trained on large-scale corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text. |
| Approach: | They propose a method for formality style transfer by injecting multiple rules into an end-to-end BERT-based encoder and decoder model. |
| Outcome: | The proposed method outperforms existing rule-based FST approaches on tweet sentiment analysis tasks. |
Semi-Supervised Formality Style Transfer with Consistency Training (2022.acl-long)
Copied to clipboard
| Challenge: | Formality style transfer (FST) is a task that involves paraphrasing an informal sentence into a formal one without altering its meaning. |
| Approach: | They propose a semi-supervised framework to better utilize source-side unlabeled sentences based on consistency training. |
| Outcome: | The proposed framework can achieve state-of-the-art results even with less than 40% of the parallel data. |
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. |
An Expanded Finite-State Transducer for Tsuut’ina Verbs (2022.lrec-1)
Copied to clipboard
| Challenge: | a finite state transducer (FST) for the transitive verb system of Tsuut'ina (ISO 639-3: srs) is described for the Dene (Athabaskan) language spoken in Alberta, Canada. |
| Approach: | They describe the expansion of a finite state transducer (FST) for the transitive verb system of Tsuut'ina (ISO 639-3: srs) Dene languages have unique templatic morphology, in which lexical, inflectional and derivational tiers are interlaced. |
| Outcome: | The proposed model can handle a great range of common and rare argument structure types, including ditransitive and uniquely Dene object experiencer verbs. |
Bootstrapping Techniques for Polysynthetic Morphological Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | Polysynthetic languages have exceptionally large and sparse vocabularies due to the number of morpheme slots and combinations in a word. |
| Approach: | They propose linguistically-informed approaches for bootstrapping a neural morphological analyzer . they use a finite state transducer to train an encoder-decoder model . |
| Outcome: | The proposed method improves on a polysynthetic language's model by "hallucinating" missing linguistic structure and resampling from a Zipf distribution to simulate a more natural distribution of morphemes. |
A Mapudüngun FST Morphological Analyser and its Web Interface (2022.lrec-1)
Copied to clipboard
| Challenge: | a computational tool for Mapudüngun language is developed using finite state technology . it is the first of its kind for the language and is available as a web service for free . |
| Approach: | They propose to develop a morphological and phonological machine for Mapudüngun using finite state technology. |
| Outcome: | The proposed system is the first of its kind for the Mapuche language and is available for public use through a web interface. |
Criteria for Useful Automatic Romanization in South Asian Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of possible criteria for systems that transliterate South Asian languages are considered . romanization is the special case where the target script is the Latin script. |
| Approach: | They propose a set of criteria for systems that transliterate South Asian languages . criteria include fidelity to human linguistic behavior, processing utility for people, invertibility . they then propose several algorithms that address different criteria . |
| Outcome: | The proposed algorithms address linguistic considerations in the context of Brahmic scripts and languages that use them, such as Hindi and Malayalam. |
Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech (2020.lrec-1)
Copied to clipboard
Yin May Oo, Theeraphol Wattanavekin, Chenfang Li, Pasindu De Silva, Supheakmungkol Sarin, Knot Pipatsrisawat, Martin Jansche, Oddur Kjartansson, Alexander Gutkin
| Challenge: | Using crowd-sourced speech corpus and finite-state transducer grammars, we build a text-to-speech system for Burmese, a tonal Southeast Asian language from the Sino-Tibetan family. |
| Approach: | They propose an open-source crowd-sourced multi-speaker speech corpus and finite-state grammars for performing grapheme-to-phoneme conversion for Burmese. |
| Outcome: | The proposed system performs well for Burmese in a low-resource setting. |
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. |