1 |
Giant Pigeon and Small Person: Prompting Visually Grounded Models about the Size of Objects ...
|
|
Zhang, Yi. - : Purdue University Graduate School, 2022
|
|
BASE
|
|
Show details
|
|
2 |
Giant Pigeon and Small Person: Prompting Visually Grounded Models about the Size of Objects ...
|
|
Zhang, Yi. - : Purdue University Graduate School, 2022
|
|
BASE
|
|
Show details
|
|
3 |
Dialogue Meaning Representation for Task-Oriented Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Profiling and functional characterization of maternal mRNA translation during mouse maternal-to-zygotic transition
|
|
|
|
In: Sci Adv (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings ...
|
|
|
|
Abstract:
Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment becomes more complex as we additionally take context into consideration. In this work, we propose using Optimal Transport (OT) as an alignment objective during fine-tuning to further improve multilingual contextualized representations for downstream cross-lingual transfer. This approach does not require word-alignment pairs prior to fine-tuning that may lead to sub-optimal matching and instead learns the word alignments within context in an unsupervised manner. It also allows different types of mappings due to soft matching between source and target sentences. We benchmark our proposed method on two tasks (XNLI and XQuAD) and achieve improvements over baselines as well as competitive results compared to similar recent works. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2110.02887 https://arxiv.org/abs/2110.02887
|
|
BASE
|
|
Hide details
|
|
8 |
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
What is Your Article Based On? Inferring Fine-grained Provenance ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
INTERNATIONAL INDIAN GRADUATE STUDENTS’ EXPERIENCES WITH ACADEMIC ADVISING AT A PUBLIC RESEARCH UNIVERSITY IN TEXAS
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Dataset of materia medica in Sowa Rigpa: Tibetan medicine botanicals and Gawé Dorjé’s classification system
|
|
|
|
In: Data Brief (2020)
|
|
BASE
|
|
Show details
|
|
17 |
Improving Online Students’ Quality of Relationships, Academic Success, and Overall Satisfaction: A Comparative Study between Undergraduates Who Use and Who Do Not Use Student Affairs Resources
|
|
|
|
BASE
|
|
Show details
|
|
18 |
A CASE STUDY OF THE EFL LEARNER'S NEEDS ANALYSIS BASED ON KRASHEN'S MONITOR THEORY ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A CASE STUDY OF THE EFL LEARNER'S NEEDS ANALYSIS BASED ON KRASHEN'S MONITOR THEORY ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Additional file 1: of SWOT analysis on snail control measures applied in the national schistosomiasis control programme in the Peopleâ s Republic of China ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|