Can we teach language models to gloss endangered languages?
- URL: http://arxiv.org/abs/2406.18895v3
- Date: Thu, 03 Oct 2024 22:06:57 GMT
- Title: Can we teach language models to gloss endangered languages?
- Authors: Michael Ginn, Mans Hulden, Alexis Palmer,
- Abstract summary: Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation.
We explore whether large language models (LLMs) can be effective at the task of interlinear glossing with in-context learning, without any traditional training.
We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all.
- Score: 10.698704803396723
- License:
- Abstract: Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.
Related papers
- LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language
Models [56.25156596019168]
This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs)
Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
arXiv Detail & Related papers (2023-11-30T03:59:31Z) - Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars.
We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English.
Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
arXiv Detail & Related papers (2023-06-20T08:27:47Z) - Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
arXiv Detail & Related papers (2023-06-13T08:08:08Z) - EXnet: Efficient In-context Learning for Data-less Text classification [0.0]
We present EXnet, a model specifically designed to perform in-context learning without limitations on the number of examples.
We argue that in-context learning is an effective method to increase task accuracy, and providing examples facilitates cross-task generalization.
With extensive experiments, we show that even our smallest model (15M parameters) generalizes to several unseen classification tasks and domains.
arXiv Detail & Related papers (2023-05-24T01:40:57Z) - Efficiently Aligned Cross-Lingual Transfer Learning for Conversational
Tasks using Prompt-Tuning [98.60739735409243]
Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks.
We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset.
To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
arXiv Detail & Related papers (2023-04-03T18:46:01Z) - Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types.
Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
arXiv Detail & Related papers (2022-10-23T00:37:08Z) - An Exploration of Prompt Tuning on Generative Spoken Language Model for
Speech Processing Tasks [112.1942546460814]
We report the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM)
Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models.
arXiv Detail & Related papers (2022-03-31T03:26:55Z) - Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for
Underdocumented Languages [6.8708103492634836]
Hundreds of underserved languages have available data sources in the form of interlinear glossed text (IGT) from language documentation efforts.
We make the case that IGT data can be leveraged successfully provided that target language expertise is available.
We illustrate each step through a case study on developing a morphological reinflection system for the Tsimchianic language Gitksan.
arXiv Detail & Related papers (2022-03-17T22:02:25Z) - Multilingual Text Classification for Dravidian Languages [4.264592074410622]
We propose a multilingual text classification framework for the Dravidian languages.
On the one hand, the framework used the LaBSE pre-trained model as the base model.
On the other hand, in view of the problem that the model cannot well recognize and utilize the correlation among languages, we further proposed a language-specific representation module.
arXiv Detail & Related papers (2021-12-03T04:26:49Z) - Prompt-Learning for Fine-Grained Entity Typing [40.983849729537795]
We investigate the application of prompt-learning on fine-grained entity typing in fully supervised, few-shot and zero-shot scenarios.
We propose a self-supervised strategy that carries out distribution-level optimization in prompt-learning to automatically summarize the information of entity types.
arXiv Detail & Related papers (2021-08-24T09:39:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.