Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing
This article surveys and organizes research works in a new paradigm in natural language
processing, which we dub “prompt-based learning.” Unlike traditional supervised learning …
processing, which we dub “prompt-based learning.” Unlike traditional supervised learning …
A review on language models as knowledge bases
Recently, there has been a surge of interest in the NLP community on the use of pretrained
Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs …
Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs …
Simple and accurate dependency parsing using bidirectional LSTM feature representations
E Kiperwasser, Y Goldberg - Transactions of the Association for …, 2016 - direct.mit.edu
We present a simple and effective scheme for dependency parsing which is based on
bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector …
bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector …
[PDF][PDF] A fast and accurate dependency parser using neural networks
D Chen, CD Manning - Proceedings of the 2014 conference on …, 2014 - aclanthology.org
Almost all current dependency parsers classify based on millions of sparse indicator
features. Not only do these features generalize poorly, but the cost of feature computation …
features. Not only do these features generalize poorly, but the cost of feature computation …
[PDF][PDF] An improved non-monotonic transition system for dependency parsing
M Honnibal, M Johnson - Proceedings of the 2015 conference on …, 2015 - aclanthology.org
Transition-based dependency parsers usually use transition systems that monotonically
extend partial parse states until they identify a complete parse tree. Honnibal et al.(2013) …
extend partial parse states until they identify a complete parse tree. Honnibal et al.(2013) …
Transition-based dependency parsing with stack long short-term memory
We propose a technique for learning representations of parser states in transition-based
dependency parsers. Our primary innovation is a new control structure for sequence-to …
dependency parsers. Our primary innovation is a new control structure for sequence-to …
[PDF][PDF] Parallel data, tools and interfaces in OPUS.
J Tiedemann - Lrec, 2012 - Citeseer
This paper presents the current status of OPUS, a growing language resource of parallel
corpora and related tools. The focus in OPUS is to provide freely available data sets in …
corpora and related tools. The focus in OPUS is to provide freely available data sets in …
[PDF][PDF] Universal dependency annotation for multilingual parsing
R McDonald, J Nivre… - Proceedings of the …, 2013 - aclanthology.org
We present a new collection of treebanks with homogeneous syntactic dependency
annotation for six languages: German, English, Swedish, Spanish, French and Korean. To …
annotation for six languages: German, English, Swedish, Spanish, French and Korean. To …
Constraint-based question answering with knowledge graph
WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent
knowledge-based question answering (KBQA) work. Most questions in them are …
knowledge-based question answering (KBQA) work. Most questions in them are …
Stack-pointer networks for dependency parsing
We introduce a novel architecture for dependency parsing:\emph {stack-pointer
networks}(\textbf {\textsc {StackPtr}}). Combining pointer networks~\citep …
networks}(\textbf {\textsc {StackPtr}}). Combining pointer networks~\citep …