Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Lopez, Adam A."'
Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs). After such a disruptive change to our understanding of the field, what is left to do?
Externí odkaz:
http://arxiv.org/abs/2311.05020
Sigmoid output layers are widely used in multi-label classification (MLC) tasks, in which multiple labels can be assigned to any input. In many practical MLC tasks, the number of possible labels is in the thousands, often exceeding the number of inpu
Externí odkaz:
http://arxiv.org/abs/2310.10443
Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with transfer l
Externí odkaz:
http://arxiv.org/abs/2305.12709
Sentiment analysis (SA) systems are used in many products and hundreds of languages. Gender and racial biases are well-studied in English SA systems, but understudied in other languages, with few resources for such studies. To remedy this, we build a
Externí odkaz:
http://arxiv.org/abs/2305.11673
Classifiers in natural language processing (NLP) often have a large number of output classes. For example, neural language models (LMs) and machine translation (MT) models both predict tokens from a vocabulary of thousands. The Softmax output layer o
Externí odkaz:
http://arxiv.org/abs/2203.06462
Autor:
Goldfarb-Tarrant, Seraphina, Marchant, Rebecca, Sanchez, Ricardo Muñoz, Pandya, Mugdha, Lopez, Adam
Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a variety of metr
Externí odkaz:
http://arxiv.org/abs/2012.15859
We present LemMED, a character-level encoder-decoder for contextual morphological analysis (combined lemmatization and tagging). LemMED extends and is named after two other attention-based models, namely Lematus, a contextual lemmatizer, and MED, a m
Externí odkaz:
http://arxiv.org/abs/2010.10921
Autor:
Saphra, Naomi, Lopez, Adam
Recent work in NLP shows that LSTM language models capture hierarchical structure in language data. In contrast to existing work, we consider the \textit{learning} process that leads to their compositional behavior. For a closer look at how an LSTM's
Externí odkaz:
http://arxiv.org/abs/2010.04650
Can artificial neural networks learn to represent inflectional morphology and generalize to new words as human speakers do? Kirov and Cotterell (2018) argue that the answer is yes: modern Encoder-Decoder (ED) architectures learn human-like behavior w
Externí odkaz:
http://arxiv.org/abs/2005.08826
Autor:
Saphra, Naomi, Lopez, Adam
Recent work in NLP shows that LSTM language models capture compositional structure in language data. For a closer look at how these representations are composed hierarchically, we present a novel measure of interdependence between word meanings in an
Externí odkaz:
http://arxiv.org/abs/2004.13195