Compiling Language Models from a Linguistically Motivated Unification Grammar
Manny Rayner, Beth Ann Hockey, Frankie James, Elizabeth O. Bratt, Sharon Goldwater, Mark Gawron
Abstract
Systems now exist which are able to compile unification grammars into language models that can be included in a speech recognizer, but it is so far unclear whether non-trivial linguistically principled grammars can be used for this purpose. We describe a series of experiments which investigate the question empirically, by incrementally constructing a grammar and discovering what problems emerge when successively larger versions are compiled into finite state graph representations and used as language models for a medium-vocabulary recognition task.
Create a lesson
Related papers
Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models
Giovana Kerche Bonás, Thiago Laitz, Thales Sales Almeida et al.
RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs
Defne Circi, Krystelle Lionti, Sarathkrishna Swaminathan et al.
Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions
Siddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla
Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses
Shiran Liu, Gaohui Xu, Sergio Burdisso et al.
PAT: A Personality-Driven Augmentation and Transfer Learning Framework for Depression Detection on Social Media
Shengwu Zheng, Yuzhe Ding, Xiaohui Liang et al.
Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models
S. M. Mahbub Uddin Ahmed