Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Dipti Misra Sharma"'
Autor:
Pruthwik Mishra, Gaurav Saxena, Dipti Misra Sharma, Ben Ambridge, Soumitra Samanta, Rukmini Bhaya Nair, Bhuvana Narasimhan, Ramya Maitreyee
Publikováno v:
Open Research Europe, Vol 3 (2023)
Background: A question that lies at the very heart of language acquisition research is how children learn semi-regular systems with exceptions (e.g., the English plural rule that yields cats, dogs, etc, with exceptions feet and men). We investigated
Externí odkaz:
https://doaj.org/article/e1851cc46f1047598d63e54f0674b879
Autor:
Pruthwik Mishra, Gaurav Saxena, Dipti Misra Sharma, Ben Ambridge, Soumitra Samanta, Rukmini Bhaya Nair, Bhuvana Narasimhan, Ramya Maitreyee
Publikováno v:
Open Research Europe, Vol 3 (2023)
Background: A question that lies at the very heart of language acquisition research is how children learn semi-regular systems with exceptions (e.g., the English plural rule that yields cats, dogs, etc, with exceptions feet and men). We investigated
Externí odkaz:
https://doaj.org/article/839517e5023a419db777d7387da65355
Autor:
Stewart McCauley, Seth Campbell, Dipti Misra Sharma, Ruth Berman, Kumiko Fukumura, Rukmini Bhaya Nair, Margarita Julajuj Mendoza, Ben Ambridge, Laura Doherty, Tomoko Tatsumi, Ramya Maitreyee, Pedro Mateo Pedro, Shira Zicherman, Amy Bidgood, Ayuno Kawakami, Bhuvana Narasimhan, Clifton Pye, Dani Bekman, Inbal Arnon, Sindy Fabiola Can Pixabaj, Amir Efrati, Soumitra Samanta, Mario Marroquín Pelíz
Publikováno v:
Open Research Europe, Vol 1 (2022)
How do language learners avoid the production of verb argument structure overgeneralization errors (*The clown laughed the man c.f. The clown made the man laugh), while retaining the ability to apply such generalizations productively when appropriate
Externí odkaz:
https://doaj.org/article/93ca9d87448e4fc19619d2b7fe897fbe
Autor:
Ambridge, Ben, Saxena, Gaurav, Samanta, Soumitra, Bhuvana Narasimhan, Maitreyee, Ramya, Dipti Misra Sharma, Rukmini Bhaya Nair, Pruthwik Mishra
This registration includes the stimuli, data and statistical analyses R code for the paper titled "Children learn ergative case marking in Hindi using statistical pre-emption and clause-level semantics (intentionality): Evidence from acceptability ju
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29e155cf33ff9538640c77d51110f557
Autor:
Ramya Maitreyee, Gaurav Saxena, Bhuvana Narasimhan, Dipti Misra Sharma, Pruthwik Mishra, Rukmini Bhaya Nair, Soumitra Samanta, Ben Ambridge
Publikováno v:
Open Research Europe
Background: A question that lies at the very heart of language acquisition research is how children learn semi-regular systems with exceptions (e.g., the English plural rule that yields cats, dogs, etc, with exceptions feet and men). We investigated
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ef079bd435820c25b2a7353398ff370
https://doi.org/10.12688/openreseurope.15611.1
https://doi.org/10.12688/openreseurope.15611.1
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8a235d7d4337963d12a26ff60d8aef3
Publikováno v:
WAT@ACL/IJCNLP
This paper describes the work and the systems submitted by the IIIT-Hyderbad team in the WAT 2021 MultiIndicMT shared task. The task covers 10 major languages of the Indian subcontinent. For the scope of this task, we have built multilingual systems
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e884325c95f5e911e03896257bca53e3
https://doi.org/10.18653/v1/2021.wat-1.25
https://doi.org/10.18653/v1/2021.wat-1.25
Publikováno v:
RANLP
India is known as the land of many tongues and dialects. Neural machine translation (NMT) is the current state-of-the-art approach for machine translation (MT) but performs better only with large datasets which Indian languages usually lack, making t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2fd9bce4e5cfcc13ce1eeb25ed396c8
https://doi.org/10.26615/978-954-452-072-4_083
https://doi.org/10.26615/978-954-452-072-4_083
Publikováno v:
RANLP
In this paper, we present a novel approachfor domain adaptation in Neural MachineTranslation which aims to improve thetranslation quality over a new domain.Adapting new domains is a highly challeng-ing task for Neural Machine Translation onlimited da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::270b72effe415f1956c4ad936bdca6f8
https://doi.org/10.26615/978-954-452-072-4_004
https://doi.org/10.26615/978-954-452-072-4_004
Publikováno v:
DSAA
We propose MEE, an approach for automatic Machine Translation (MT) evaluation which leverages the similarity between embeddings of words in candidate and reference sentences to assess translation quality. Unigrams are matched based on their surface f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05f82715562153cd44630a1a84f4d737
https://doi.org/10.1109/dsaa49011.2020.00042
https://doi.org/10.1109/dsaa49011.2020.00042