The Stanford CoreNLP Natural Language Processing Toolkit
By Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, David McClosky. 2014
7,642 citations recorded by the source corpus.
We describe the design and use of the Stanford CoreNLP toolkit, an extensible pipeline that provides core natural language analysis. This toolkit is quite widely used, both in the research NLP community and also among commercial and government users of open source NLP technology. We suggest that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Yejin Choi
- Graham Neubig
- Caiming Xiong
- Yoshua Bengio
In Natural Language Processing
- Mohit Bansal
- Luke S. Zettlemoyer
- Graham Neubig
- Jianfeng Gao
- Yejin Choi
- Percy Liang
- Christopher D. Manning
- Noah A. Smith
Citations in the corpus
- A Deep Reinforced Model for Abstractive Summarization (2017, methodology): “We to-kenize the input and abstract pairs with the Stanford tokenizer (Manning et al., 2014).”
- SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, methodology): “SIF: PTB tokenization provided by Stanford CoreNLP (Manning et al., 2014) with post-processing based on dev OOVs; Word2vec: Similar to FastText, to our knownledge, the preprocessing for the pre-trained Word2vec embeddings is not publicly described.”
- ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension (2018, background): “(3) for each candidate passage, the second part of its corresponding news article was split into sentences by Stanford CoreNLP (Manning et al., 2014).”
- CoQA: A Conversational Question Answering Challenge (2018, methodology): “Therefore, we select passages with multiple entities, events, and pronominal references using Stanford CoreNLP (Manning et al., 2014).”
- The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives (2019, methodology): “For each of the selected tokens described above (“main” tokens), we pick tokens which potentially could be confused with the token under 7 We use the part-of-speech tagger from Stanford CoreNLP (Manning et al., 2014). consideration (“contrastive” tokens).”
- A Surprisingly Robust Trick for the Winograd Schema Challenge (2019, methodology): “We use the Stanford POS tagger (Manning et al., 2014) for finding nouns.”
- Creating Training Corpora for NLG Micro-Planners (2017, methodology): “We use the Stanford Part-Of-Speech Tagger and Parser version 3.5.2 (dated 2015-04-20, Manning et al. 2014) to tokenize and to perform sentence segmentation on text.”
- A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, methodology): “We use the state-of-the-art sentiment analysis model (Manning et al., 2014) which assigns a numerical value from 1 to 5 to a sentence.”
- HuggingFace's Transformers: State-of-the-art Natural Language Processing (2019, neutral): “Two core libraries are NLTK (Loper and Bird, 2002) and Stanford CoreNLP (Manning et al., 2014), which collect a variety of different approaches to NLP in a single package.”
- FEVER: a Large-scale Dataset for Fact Extraction and VERification (2018, methodology): “We used the June 2017 Wikipedia dump and processed it with Stanford CoreNLP (Manning et al., 2014)1, and used the sentences from the introductory sections of the 50,000 most popular pages.”
- Reading Wikipedia to Answer Open-Domain Questions (2017, methodology): “We apply the Stanford CoreNLP toolkit (Manning et al., 2014) for tokenization and also generating lemma, part-of-speech, and named entity manual features.”
- Key-Value Memory Networks for Directly Reading Documents (2016, methodology): “We first employ coreference resolution via the Stanford NLP Toolkit (Manning et al. , 2014) to reduce ambiguity by replacing pronominal (“he”, “it”) and nominal (“the film”) references with their representative entities.”
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (2018, methodology): “8 We use Stanford CoreNLP 3.8.0 (Manning et al., 2014) for word and sentence tokenization.”
- A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers (2020, methodology): “We first use Stanford CoreNLP (Manning et al., 2014) to tokenize and tag POSs, and then use NLTK (Bird et al., 2004) to lemmatize each token.”
- Multimodal Transformer for Unaligned Multimodal Language Sequences (2019, background): “This rich information provides us the benefit of understanding human behaviors and intents (Manning et al., 2014).”
- Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, methodology): “Multimodal prompt engineering can be viewed as a systems approach that re-visits classic NLP pipelines (Manning et al., 2014) but with a modern twist – large pretrained (Bommasani et al.”