1 |
Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
AUTOLEX: An Automatic Framework for Linguistic Exploration ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Differentiable Allophone Graphs for Language-Universal Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Towards Zero-shot Learning for Automatic Phonemic Transcription ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Automatic Extraction of Rules Governing Morphological Agreement ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Universal Phone Recognition with a Multilingual Allophone System ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Characterizing Sociolinguistic Variation in the Competing Vaccination Communities ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
15 |
Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations ...
|
|
|
|
Abstract:
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Recognition for four languages, namely Uyghur, Turkish, Bengali and Hindi, of which Uyghur and Bengali are low resource languages, and also perform experiments on Machine Translation. Exploiting subwords with transfer learning gives us a boost of +15.2 NER F1 for Uyghur and +9.7 F1 for Bengali. We also show improvements in the monolingual setting where we achieve (avg.) +3 F1 and (avg.) +1.35 BLEU. ... : Accepted at EMNLP 2018 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1808.09500 https://dx.doi.org/10.48550/arxiv.1808.09500
|
|
BASE
|
|
Hide details
|
|
17 |
Lexical Prefixes and Tibeto-Burman Laryngeal Contrasts
|
|
|
|
In: Mortensen, David R. (2013). Lexical Prefixes and Tibeto-Burman Laryngeal Contrasts. Proceedings of the 37th Annual Meeting of the Berkeley Linguistics Society, 37(37), 272 - 286. Retrieved from: http://www.escholarship.org/uc/item/1229x8bj (2013)
|
|
BASE
|
|
Show details
|
|
20 |
Lexical prefixes and Tibeto-Burman laryngeal contrasts
|
|
|
|
In: Annual Meeting of the Berkeley Linguistics Society; BLS 37: General Session and Parasession on Language, Gender, and Sexuality; 272-286 ; 2377-1666 ; 0363-2946 (2011)
|
|
BASE
|
|
Show details
|
|
|
|