Levon Haroutunian

Language Justice and Machine Translation on Social Media

Amandalynne Paullada, Levon Haroutunian

Machine translation (MT), which involves the use of algorithms to translate between languages, has advanced to a high level of quality for dozens of language pairs and is employed in an array of everyday contexts, including on social media. However, there are …

us (code pays fourni par la source)

Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach

Zhuang Li, Levon Haroutunian, Raj Tumuluri, Philip R. Cohen et autres

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 …

On the Question of Authorship in Large Language Models

Carlin Soos, Levon Haroutunian

Adoption of pre-trained large language models (LLMs) across an increasingly diverse range of tasks and domains poses significant problems for authorial attribution and other basic knowl­edge organization practices. Utilizing methods from value-sensitive design, this paper examines the theoretical, practical, and ethical issues …

Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach

Zhuang Li, Levon Haroutunian, Raj Tumuluri, Philip Cohen et autres

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 …

On the Question of Authorship in Large Language Models (LLMs)

Carlin Soos, Levon Haroutunian

The adoption of pre-trained large language models (LLMs), like ChatGPT, across an increasingly diverse range of tasks and domains poses significant challenges for authorial attribution and other basic knowledge organization practices. This paper examines the theoretical and practical issues introduced by LLMs …

us (code pays fourni par la source)

Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models

Levon Haroutunian, Zhuang Li, Lucian Galescu, Philip R. Cohen et autres

Large language models (LLMs) have demonstrated impressive capabilities in natural language generation. However, their output quality can be inconsistent, posing challenges for generating natural language from logical forms (LFs). This task requires the generated outputs to embody the exact semantics of LFs, …

Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models

Levon Haroutunian, Zhuang Li, Lucian Galescu, Philip R. Cohen et autres

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). 2023.

Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages

Carlton Downey, Shannon Drizin, Levon Haroutunian, Shivin Thukral

We show that unsupervised sequencesegmentation performance can be transferred to extremely low-resource languages by pretraining 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 …

us (code pays fourni par la source)

Ethical Considerations for Low-resourced Machine Translation

Levon Haroutunian

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 …

us (code pays fourni par la source)

Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages

C. M. Downey, Shannon Drizin, Levon Haroutunian, Shivin Thukral

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 …