Page: 1 2 3 4 5 6 7 8 9... 282
81 |
Team ÚFAL at CMCL 2022 Shared Task: Figuring out the correct recipe for predicting Eye-Tracking features using Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Does Corpus Quality Really Matter for Low-Resource Languages? ...
|
|
|
|
BASE
|
|
Show details
|
|
83 |
IIITDWD-ShankarB@ Dravidian-CodeMixi-HASOC2021: mBERT based model for identification of offensive content in south Indian languages ...
|
|
|
|
BASE
|
|
Show details
|
|
84 |
mSLAM: Massively multilingual joint pre-training for speech and text ...
|
|
Bapna, Ankur; Cherry, Colin; Zhang, Yu; Jia, Ye; Johnson, Melvin; Cheng, Yong; Khanuja, Simran; Riesa, Jason; Conneau, Alexis. - : arXiv, 2022
|
|
Abstract:
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines w2v-BERT pre-training on speech with SpanBERT pre-training on character-level text, along with Connectionist Temporal Classification (CTC) losses on paired speech and transcript data, to learn a single model capable of learning from and representing both speech and text signals in a shared representation space. We evaluate mSLAM on several downstream speech understanding tasks and find that joint pre-training with text improves quality on speech translation, speech intent classification and speech language-ID while being competitive on multilingual ASR, when compared against speech-only pre-training. Our speech translation model demonstrates zero-shot text translation without seeing any text translation data, providing evidence for cross-modal alignment of representations. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2202.01374 https://dx.doi.org/10.48550/arxiv.2202.01374
|
|
BASE
|
|
Hide details
|
|
85 |
On the Representation Collapse of Sparse Mixture of Experts ...
|
|
|
|
BASE
|
|
Show details
|
|
86 |
Politics and Virality in the Time of Twitter: A Large-Scale Cross-Party Sentiment Analysis in Greece, Spain and United Kingdom ...
|
|
|
|
BASE
|
|
Show details
|
|
87 |
L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT models ...
|
|
|
|
BASE
|
|
Show details
|
|
88 |
Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
89 |
A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model ...
|
|
|
|
BASE
|
|
Show details
|
|
90 |
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Factual Consistency of Multilingual Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Examining Scaling and Transfer of Language Model Architectures for Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
93 |
MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
94 |
Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
96 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
97 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Characterizing News Portrayal of Civil Unrest in Hong Kong, 1998–2020 ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 282
|
|