Levon Haroutunian


2024

pdf bib
Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
Zhuang Li | Levon Haroutunian | Raj Tumuluri | Philip Cohen | Reza Haf
Findings of the Association for Computational Linguistics: EACL 2024

Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive. However, relying solely on smaller language models for post-editing can limit the LLMs’ ability to generalize across domains. Moreover, the editing strategies in these methods are not optimally designed for text generation tasks. To address these limitations, we propose a neural programmer-interpreter approach that preserves the domain generalization ability of LLMs while editing their output. The editing actions in this framework are specifically devised for text generation. Extensive experiments demonstrate that the programmer-interpreter significantly enhances GPT-3.5’s performance in logical form-to-text conversion and low-resource machine translation, surpassing other state-of-the-art (SOTA) LLM post-editing methods in cross-domain settings.

2023

pdf bib
Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models
Levon Haroutunian | Zhuang Li | Lucian Galescu | Philip Cohen | Raj Tumuluri | Gholamreza Haffari
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

2022

pdf bib
Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages
C. Downey | Shannon Drizin | Levon Haroutunian | Shivin Thukral
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We show that unsupervised sequence-segmentation performance can be transferred to extremely low-resource languages by pre-training a Masked Segmental Language Model (Downey et al., 2021) multilingually. Further, we show that this transfer can be achieved by training over a collection of low-resource languages that are typologically similar (but phylogenetically unrelated) to the target language. In our experiments, we transfer from a collection of 10 Indigenous American languages (AmericasNLP, Mager et al., 2021) to K’iche’, a Mayan language. We compare our multilingual model to a monolingual (from-scratch) baseline, as well as a model pre-trained on Quechua only. We show that the multilingual pre-trained approach yields consistent segmentation quality across target dataset sizes, exceeding the monolingual baseline in 6/10 experimental settings. Our model yields especially strong results at small target sizes, including a zero-shot performance of 20.6 F1. These results have promising implications for low-resource NLP pipelines involving human-like linguistic units, such as the sparse transcription framework proposed by Bird (2020).

pdf bib
Ethical Considerations for Low-resourced Machine Translation
Levon Haroutunian
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

This paper considers some ethical implications of machine translation for low-resourced languages. I use Armenian as a case study and investigate specific needs for and concerns arising from the creation and deployment of improved machine translation between English and Armenian. To do this, I conduct stakeholder interviews and construct Value Scenarios (Nathan et al., 2007) from the themes that emerge. These scenarios illustrate some of the potential harms that low-resourced language communities may face due to the deployment of improved machine translation systems. Based on these scenarios, I recommend 1) collaborating with stakeholders in order to create more useful and reliable machine translation tools, and 2) determining which other forms of language technology should be developed alongside efforts to improve machine translation in order to mitigate harms rendered to vulnerable language communities. Both of these goals require treating low-resourced machine translation as a language-specific, rather than language-agnostic, task.