{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/145034"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/145034","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Syntactic Transfer for Low-Resource Machine Translation with Contextual Parameter Generation","abstract":"The advent of large pretrained models has led to paradigm-shifting improvements throughout natural language processing. For many tasks, state-of-the-art results are now achieved by taking one of these large pretrained models and adapting it in some way for use on the desired task. While this approach has been successful on a broad range of tasks, that success is not evenly distributed within tasks—most of the gains are in high-resource settings, i.e., tasks and languages for which there is a large amount of labeled data available. Some tasks—and many languages—lack sufficient labeled data for these approaches to work well. Recently, there has been much interest in methods that could potentially close this gap and improve performance in low-resource settings. In this work, I demonstrate a novel method for adapting large pretrained models that involves dynamically generating additional parameters for the model based on an informative representation of the task and show that this method works especially well on the task of low-resource machine translation.","abstract_html":"The advent of large pretrained models has led to paradigm-shifting improvements throughout natural language processing. For many tasks, state-of-the-art results are now achieved by taking one of these large pretrained models and adapting it in some way for use on the desired task. While this approach has been successful on a broad range of tasks, that success is not evenly distributed within tasks—most of the gains are in high-resource settings, i.e., tasks and languages for which there is a large amount of labeled data available. Some tasks—and many languages—lack sufficient labeled data for these approaches to work well. Recently, there has been much interest in methods that could potentially close this gap and improve performance in low-resource settings. In this work, I demonstrate a novel method for adapting large pretrained models that involves dynamically generating additional parameters for the model based on an informative representation of the task and show that this method works especially well on the task of low-resource machine translation.","abstract_has_math":false,"creators":["O'Connor, Joe"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Andreas, Jacob"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:22:15Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/145034","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Andreas, Jacob"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["O'Connor, Joe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T16:28:37Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T16:28:37Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/145034"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The advent of large pretrained models has led to paradigm-shifting improvements throughout natural language processing. For many tasks, state-of-the-art results are now achieved by taking one of these large pretrained models and adapting it in some way for use on the desired task. While this approach has been successful on a broad range of tasks, that success is not evenly distributed within tasks—most of the gains are in high-resource settings, i.e., tasks and languages for which there is a large amount of labeled data available. Some tasks—and many languages—lack sufficient labeled data for these approaches to work well. Recently, there has been much interest in methods that could potentially close this gap and improve performance in low-resource settings. In this work, I demonstrate a novel method for adapting large pretrained models that involves dynamically generating additional parameters for the model based on an informative representation of the task and show that this method works especially well on the task of low-resource machine translation."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Syntactic Transfer for Low-Resource Machine Translation with Contextual Parameter Generation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Andreas, Jacob"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["O'Connor, Joe"],"dc:date.accessioned":["2022-08-29T16:28:37Z"],"dc:date.available":["2022-08-29T16:28:37Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["The advent of large pretrained models has led to paradigm-shifting improvements throughout natural language processing. For many tasks, state-of-the-art results are now achieved by taking one of these large pretrained models and adapting it in some way for use on the desired task. While this approach has been successful on a broad range of tasks, that success is not evenly distributed within tasks—most of the gains are in high-resource settings, i.e., tasks and languages for which there is a large amount of labeled data available. Some tasks—and many languages—lack sufficient labeled data for these approaches to work well. Recently, there has been much interest in methods that could potentially close this gap and improve performance in low-resource settings. In this work, I demonstrate a novel method for adapting large pretrained models that involves dynamically generating additional parameters for the model based on an informative representation of the task and show that this method works especially well on the task of low-resource machine translation."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/145034"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Syntactic Transfer for Low-Resource Machine Translation with Contextual Parameter Generation"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:15Z"}