Search Results - MIT Press

Decoding Dynamic Brain Patterns from Evoked Responses: A Tutorial on Multivariate Pattern Analysis Applied to Time Series Neuroimaging Data by Grootswagers, Tijl, Wardle, Susan G, Carlson, Thomas A

“…Multivariate pattern analysis (MVPA) or brain decoding methods have become standard practice in analyzing fMRI data. Although decoding methods have been…”
Get more information

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot by Zhou, Li, Gao, Jianfeng, Li, Di, Shum, Heung-Yeung

“…This article describes the development of Microsoft , the most popular social chatbot in the world. XiaoIce is uniquely designed as an artifical intelligence…”
Get full text

Particle Swarm Optimization for Single Objective Continuous Space Problems: A Review by Bonyadi, Mohammad Reza, Michalewicz, Zbigniew

“…This paper reviews recent studies on the Particle Swarm Optimization (PSO) algorithm. The review has been focused on high impact recent articles that have…”
Get more information

Universal Dependencies by de Marneffe, Marie-Catherine, Manning, Christopher D., Nivre, Joakim, Zeman, Daniel

“…Universal dependencies (UD) is a framework for morphosyntactic annotation of human language, which to date has been used to create treebanks for more than 100…”
Get full text

ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models by Xue, Linting, Barua, Aditya, Constant, Noah, Al-Rfou, Rami, Narang, Sharan, Kale, Mihir, Roberts, Adam, Raffel, Colin

“…Most widely used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, models that operate directly…”
Get full text

SpanBERT: Improving Pre-training by Representing and Predicting Spans by Joshi, Mandar, Chen, Danqi, Liu, Yinhan, Weld, Daniel S., Zettlemoyer, Luke, Levy, Omer

“…We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous…”
Get full text

Natural Questions: A Benchmark for Question Answering Research by Kwiatkowski, Tom, Palomaki, Jennimaria, Redfield, Olivia, Collins, Michael, Parikh, Ankur, Alberti, Chris, Epstein, Danielle, Polosukhin, Illia, Devlin, Jacob, Lee, Kenton, Toutanova, Kristina, Jones, Llion, Kelcey, Matthew, Chang, Ming-Wei, Dai, Andrew M., Uszkoreit, Jakob, Le, Quoc, Petrov, Slav

“…We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search…”
Get full text

Combined Electrophysiological and Behavioral Evidence for the Suppression of Salient Distractors by Gaspelin, Nicholas, Luck, Steven J

“…Researchers have long debated how salient-but-irrelevant features guide visual attention. Pure stimulus-driven theories claim that salient stimuli…”
Get more information

WHO CREATES JOBS? SMALL VERSUS LARGE VERSUS YOUNG by Haltiwanger, John, Jarmin, Ron S., Miranda, Javier

“…The view that small businesses create the most jobs remains appealing to policymakers and small business advocates. Using data from the Census Bureau's…”
Get full text

Deep Learning for Text Style Transfer: A Survey by Jin, Di, Jin, Zhijing, Hu, Zhiting, Vechtomova, Olga, Mihalcea, Rada

“…Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness,…”
Get full text

Are We Ready for Real-world Neuroscience? by Matusz, Pawel J, Dikker, Suzanne, Huth, Alexander G, Perrodin, Catherine

“…Real-world environments are typically dynamic, complex, and multisensory in nature and require the support of top-down attention and memory mechanisms for us…”
Get more information

How Can We Know What Language Models Know? by Jiang, Zhengbao, Xu, Frank F., Araki, Jun, Neubig, Graham

“…Recent work has presented intriguing results examining the knowledge contained in language models (LMs) by having the LM fill in the blanks of prompts such as…”
Get full text

Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond by Artetxe, Mikel, Schwenk, Holger

“…We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in…”
Get full text

Survey of Low-Resource Machine Translation by Haddow, Barry, Bawden, Rachel, Barone, Antonio Valerio Miceli, Helcl, Jindřich, Birch, Alexandra

“…We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the…”
Get full text

A Structured Review of the Validity of BLEU by Reiter, Ehud

“…The BLEU metric has been widely used in NLP for over 15 years to evaluate NLP systems, especially in machine translation and natural language generation. I…”
Get full text

MOEA/D with adaptive weight adjustment by Qi, Yutao, Ma, Xiaoliang, Liu, Fang, Jiao, Licheng, Sun, Jianyong, Wu, Jianshe

“…Recently, MOEA/D (multi-objective evolutionary algorithm based on decomposition) has achieved great success in the field of evolutionary multi-objective…”
Get more information

Neural Network Acceptability Judgments by Warstadt, Alex, Singh, Amanpreet, Bowman, Samuel R.

“…This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their…”
Get full text

Parsing Argumentation Structures in Persuasive Essays by Stab, Christian, Gurevych, Iryna

“…In this article, we present a novel approach for parsing argumentation structures. We identify argument components using sequence labeling at the token level…”
Get full text

Scopus as a curated, high-quality bibliometric data source for academic research in quantitative science studies by Baas, Jeroen, Schotten, Michiel, Plume, Andrew, Côté, Grégoire, Karimi, Reza

“…Scopus is among the largest curated abstract and citation databases, with a wide global and regional coverage of scientific journals, conference proceedings,…”
Get full text

What Weights Work for You? Adapting Weights for Any Pareto Front Shape in Decomposition-Based Evolutionary Multiobjective Optimisation by Li, Miqing, Yao, Xin

“…The quality of solution sets generated by decomposition-based evolutionary multi-objective optimisation (EMO) algorithms depends heavily on the consistency…”
Get more information