The Relevance of the Source Language in Transfer Learning for ASR
COMPUTEL, 2021 This study presents new experiments on Zyrian Komi speech recognition. We use Deep-Speech to train ASR models from a language documentation corpus that contains both contemporary and archival recordings.
Nils Hjortnaes +3 more
semanticscholar +1 more source
Aspects of Syntactic Ambiguity in Arabic Language and their Impacts on the Translation of the Holy Quran [PDF]
پژوهشهای ترجمه در زبان و ادبیات عربی, 2017 Many translation theoreticians strongly support the role of collocations in translation and therefore have focused on this linguistic phenomenon in part of their studies.
Mohammad Amirifar +3 more
doaj +1 more source
Agents: An Open-source Framework for Autonomous Language Agents [PDF]
arXiv.org, 2023 Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces ...
Wangchunshu Zhou +17 more
semanticscholar +1 more source
On the Tool Manipulation Capability of Open-source Large Language Models [PDF]
arXiv.org, 2023 Recent studies on software tool manipulation with large language models (LLMs) mostly rely on closed model APIs. The industrial adoption of these models is substantially constrained due to the security and robustness risks in exposing information to ...
Qiantong Xu +5 more
semanticscholar +1 more source
CodeS: Towards Building Open-source Language Models for Text-to-SQL [PDF]
Proc. ACM Manag. DataLanguage models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language models (LLMs),
Haoyang Li +9 more
semanticscholar +1 more source
FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets [PDF]
arXiv.org, 2023 In the swiftly expanding domain of Natural Language Processing (NLP), the potential of GPT-based models for the financial sector is increasingly evident.
Neng Wang, Hongyang Yang, Chris Wang
semanticscholar +1 more source
Problem Solving of Non-equivalence Problems in English Into Indonesian Text [PDF]
, 2016 In the process of transferring one message of Source Language (SL) to Target Language (TL) in a translation must be careful by a translator, because one word may have more than one meaning.
Ninsiana, W. (Widhiya)
core +2 more sources
The problem of interference and its influence of learners native language [PDF]
Trakia Journal of Sciences, 2017 This scientific article focuses on the problem of first language interference in the process of learning English as a second language. While observing the both process of teaching and learning English as a second language, we notice the influence of ...
K. Jafarova
doaj +1 more source
Developing football language in Yorùbá
Inkanyiso, 2020 Football is a global sport; almost all cultures have catalogues of terms devised to designate its concepts. This study, which is a part of an on-going project by this researcher to develop “A metalanguage for football terms in Yorùbá” (one of the three ...
Olusanya E. Komolafe
doaj +1 more source
Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge [PDF]
Annual Conference on Innovation and Technology in Computer Science EducationLarge language models (LLMs) have shown great potential for the automatic generation of feedback in a wide range of computing contexts. However, concerns have been voiced around the privacy and ethical implications of sending student work to proprietary ...
Charles Koutcheme +5 more
semanticscholar +1 more source