http://www.semanlink.net/tag/general_nlp_tasks Documents tagged with General NLP tasks http://www.semanlink.net/doc/2023/09/maarten_grootendorst_sur_x_i 2023-09-30T14:26:24Z http://www.semanlink.net/doc/2023/06/scott_condron_sur_twitter_la 2023-06-29T23:10:18Z http://www.semanlink.net/doc/2023/04/meta_learning_for_keyphrase_ext 2023-04-07T11:44:19Z http://www.semanlink.net/doc/2022/10/maartengr_keybert_minimal_keyw 2022-10-06T14:37:52Z http://www.semanlink.net/doc/2022/09/ramsri_goutham_golla_sur_twitte 2022-09-06T23:16:54Z http://www.semanlink.net/doc/2022/05/2012_12624_learning_dense_rep In this work, we show for the first time that we can learn dense representations of phrases alone that achieve much stronger performance in open-domain QA 2022-05-11T08:53:38Z http://www.semanlink.net/doc/2022/02/2109_06304_phrase_bert_impro 2022-02-25T17:19:37Z http://www.semanlink.net/doc/2022/02/nlp_pos_part_of_speech_taggi 2022-02-16T23:01:03Z http://www.semanlink.net/doc/2022/02/part_of_speech_pos_tag_%7C_depen 2022-02-06T01:23:19Z http://www.semanlink.net/doc/2021/09/2109_08133_phrase_retrieval_l [Github](doc:2021/09/princeton_nlp_densephrases_acl) > Do we always need sentence vectors for sentence retrieval and passage vectors for passage retrieval? Our EMNLP2021 paper suggests that phrase vectors can serve as a basic building block for "multi-granularity" retrieval! [tweet](https://twitter.com/leejnhk/status/1441445536515584004) > > Phrases can be directly used as the output for question answering and slot filling tasks > > the **intuition that retrieving phrases naturally entails retrieving larger text blocks** 2021-09-30T14:50:09Z http://www.semanlink.net/doc/2021/06/yake_keyword_extraction_from_s 2021-06-10T00:51:11Z http://www.semanlink.net/doc/2021/05/large_scale_evaluation_of_keyph > Results indicate that keyphrase extraction is still an open research question, with state-of-the-art neural-based models still challenged by simple baselines on some datasets [Github](https://github.com/ygorg/JCDL_2020_KPE_Eval) 2021-05-31T11:56:12Z http://www.semanlink.net/doc/2021/05/simple_unsupervised_keyphrase_e > unsupervised method to automatically extract keyphrases from a document, that **only requires the document itself** > > 1. We extract **candidate phrases from the text, based on part-of-speech sequences**. More precisely, we keep only those phrases that consist of zero or more adjectives followed by one or multiple nouns (Wan and Xiao, 2008). > 2. We use sentence embeddings **to embed both the candidate phrases and the document itself in the same high-dimensional vector space** > 3. We rank the candidate phrases to select the output keyphrases. In addition we show how to improve the ranking step, by providing a way to tune the diversity of the extracted keyphrases. 2021-05-31T11:47:52Z http://www.semanlink.net/doc/2020/12/autophrase_automated_phrase_mi 2020-12-14T19:15:04Z http://www.semanlink.net/doc/2020/12/keyword_extraction_with_bert_%7C_ A minimal method for extracting keywords and keyphrases. [GitHub](https://github.com/MaartenGr/KeyBERT/) > uses BERT-embeddings and simple cosine similarity to find the sub-phrases in a document that are the most similar to the document itself. 2020-12-06T10:07:17Z http://www.semanlink.net/doc/2020/07/dicksontsai_stanford_nlp_local_ 2020-07-03T17:44:02Z http://www.semanlink.net/doc/2020/03/ambiversenlu_a_natural_languag 2020-03-13T10:30:41Z http://www.semanlink.net/doc/2019/08/blackstone_concept_extractor_ 2019-08-21T08:35:18Z http://www.semanlink.net/doc/2019/07/mining_quality_phrases_from_mas framework that extracts quality phrases from text corpora integrated with phrasal segmentation. > The framework requires only limited training but the quality of phrases so generated is close to human judgment. Moreover, the method is scalable: both computation time and required space grow linearly as corpus size increases [Related blog post](https://medium.com/@SherlockHumus/mining-quality-phrases-from-not-so-massive-text-corpora-part-i-b20b8336520a) Used in [this Entity Linking method](/doc/?uri=https%3A%2F%2Farxiv.org%2Fabs%2F1807.06036) 2019-07-15T13:02:36Z https://dl.acm.org/citation.cfm?id=1321475 use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation 2019-04-16T22:51:58Z http://www.semanlink.net/doc/2019/02/keywords2vec To generate a word2vec model, but using keywords instead of one word. Tokenize on stopwords + non word characters (This remembers me author of [FlashText algorithm](tag:flashtext_algorithm.html) saying he had developed it to create word2vec models) 2019-02-09T01:43:55Z http://www.semanlink.net/doc/2019/02/jeremy_howard_on_twitter_such > We found that tokenizing using stopwords + non word characters was really useful for "finding" the keywords [keywords2vec](/doc/2019/02/keywords2vec) 2019-02-09T01:42:55Z https://tech.goibibo.com/key-topics-extraction-and-contextual-sentiment-of-users-reviews-20e63c0fd7ca 2018-09-18T15:05:58Z https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3168314/ 2018-08-13T17:46:50Z https://www.researchgate.net/publication/321841361_Text_feature_extraction_based_on_deep_learning_a_review outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction 2018-08-13T14:21:24Z http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0192360 > A CNN for NLP learns which combinations of adjacent words are associated with a given concept. 2018-08-12T20:11:48Z http://www.cis.pku.edu.cn/faculty/system/zhangyan/papers/DMMOOC2017-jiang.pdf 2018-08-12T18:29:53Z http://acl2014.org/acl2014/P14-1/pdf/P14-1119.pdf [same author](/doc/?uri=http%3A%2F%2Fwww.hlt.utdallas.edu%2F%7Evince%2Fpapers%2Fcoling10-keyphrase.pdf) 2018-08-10T10:51:50Z https://arxiv.org/abs/1404.5367 Employs lexicons as part of the word embedding training: > The skip-gram model can be trained to predict not only neighboring words but also lexicon membership of the central word (or phrase). Quickly demonstrates how we can plug phrase embeddings into an existing log-linear CRF System. 2018-05-22T16:22:37Z http://aclweb.org/anthology/P14-3006 > generalized phrases are part of the inventory of linguistic units that we should compute embeddings for and we have shown that such embeddings are superior to word form embeddings in a coreference resolution task and standard paraphrase identification task 2018-05-12T16:04:39Z https://techblog.cdiscount.com/part-speech-tagging-tutorial-keras-deep-learning-library/ 2018-04-13T10:18:20Z https://guillaumegenthial.github.io/sequence-tagging-with-tensorflow.html bi-LSTM + CRF with character embeddings for NER and POS. [linked from here](http://nlp.town/blog/ner-and-the-road-to-deep-learning/) 2018-03-05T18:51:35Z https://graphaware.com/neo4j/2017/10/03/efficient-unsupervised-topic-extraction-nlp-neo4j.html 2017-10-04T23:01:42Z https://www.quora.com/What-is-a-simple-but-detailed-explanation-of-Textrank 2017-07-12T00:58:03Z https://fr.slideshare.net/andrewkoo/textrank-algorithm 2017-07-12T00:48:39Z http://textminingonline.com/dive-into-nltk-part-v-using-stanford-text-analysis-tools-in-python [en cas de pb](https://gist.github.com/alvations/e1df0ba227e542955a8a) **including how to use Java NLP Tools in python** ``` export CLASSPATH=/Users/fps/_fps/DeveloperTools/stanford-postagger-full/stanford-postagger.jar # ATTENTION, stanford-postagger.jar, pas stanford-postagger-3.8.0.jar export STANFORD_MODELS=/Users/fps/_fps/DeveloperTools/stanford-postagger-full/models python ``` ``` from nltk.tag import StanfordPOSTagger st = StanfordPOSTagger('english-bidirectional-distsim.tagger') st.tag('What is the airspeed of an unladen swallow ?'.split()) st = StanfordPOSTagger('french.tagger') st.tag('Les plats servis sont toujours les mêmes et la qualité des plats est en nette baisse'.split()) ``` [('Les', 'DET'), ('plats', 'NOUN'), ('servis', 'ADJ'), ('sont', 'VERB'), ('toujours', 'ADV'), ('les', 'DET'), ('mêmes', 'ADJ'), ('et', 'CONJ'), ('la', 'DET'), ('qualité', 'NOUN'), ('des', 'DET'), ('plats', 'NOUN'), ('est', 'VERB'), ('en', 'ADP'), ('nette', 'ADJ'), ('baisse', 'NOUN')] 2017-07-11T18:16:16Z https://github.com/nltk/nltk/wiki/Installing-Third-Party-Software 2017-07-11T18:14:58Z http://www.nltk.org/_modules/nltk/tag/stanford.html 2017-07-11T16:13:00Z http://rdrpostagger.sourceforge.net/ approach to automatically construct tagging rules in the form of a binary tree. Python and java 2017-07-11T15:46:46Z http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/ 2017-07-11T15:44:58Z http://www.nltk.org/api/nltk.tag.html#module-nltk.tag.stanford A module for interfacing with the Stanford taggers. 2017-07-11T15:43:03Z https://nlp.stanford.edu/software/tagger.shtml 2017-07-11T15:25:58Z https://stackoverflow.com/questions/15388831/what-are-all-possible-pos-tags-of-nltk 2017-07-11T14:50:14Z https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html Alphabetical list of part-of-speech tags used in the Penn Treebank Project 2017-07-11T14:48:26Z http://radimrehurek.com/gensim/models/phrases.html Automatically detect common phrases – aka multi-word expressions, word n-gram collocations – from a stream of sentences. [see also](http://www.markhneedham.com/blog/2015/02/12/pythongensim-creating-bigrams-over-how-i-met-your-mother-transcripts/#disqus_thread) 2017-07-10T19:05:37Z https://stackoverflow.com/questions/9663918/how-can-i-tag-and-chunk-french-text-using-nltk-and-python?rq=1 2017-06-29T11:54:27Z https://www.researchgate.net/post/Are_there_any_efficient_stemming_algorithms_in_addition_to_the_Porter_and_Carry_algorithms 2017-06-28T16:57:04Z https://www.microsoft.com/en-us/research/publication/a-ranking-approach-to-keyphrase-extraction/ Previously, automatic keyphrase extraction was formalized as classification and learning methods for classification were utilized. This paper points out that it is more essential to **cast the keyphrase extraction problem as ranking** and employ a **learning to rank** method to perform the task. As example, it employs Ranking SVM, a state-of-art method of learning to rank, in keyphrase extraction 2017-06-27T12:47:09Z http://sujitpal.blogspot.fr/2013/03/implementing-rake-algorithm-with-nltk.html 2017-06-26T14:56:18Z http://www.nzdl.org/Kea/index.html can be used for free indexing or for indexing with a controlled vocabulary. Java implementation 2017-06-26T14:52:19Z https://github.com/aneesha/RAKE 2017-06-26T14:43:49Z http://www.hlt.utdallas.edu/~vince/papers/acl14-keyphrase-poster.jpg 2017-06-20T14:04:04Z http://www.aclweb.org/anthology/P/P14/P14-1119.xhtml 2017-06-20T14:01:17Z http://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf paper, description of the TextRank algorithm 2017-06-14T01:16:22Z http://www.hlt.utdallas.edu/~vince/papers/coling10-keyphrase.pdf evaluation and analysis of Unsupervised Keyphrase Extraction algorithms on a variety of standard evaluation dataset. Author Kazi Saidul Hasan provides C++ [implementations of the discussed algos](http://www.hlt.utdallas.edu/~saidul/code.html) (Tf-Idf, TextRank, SingleRank, ExpandRank) [by same author](/doc/?uri=http%3A%2F%2Facl2014.org%2Facl2014%2FP14-1%2Fpdf%2FP14-1119.pdf) 2017-06-14T00:51:23Z http://bdewilde.github.io/blog/2014/09/23/intro-to-automatic-keyphrase-extraction/ Candidate identification - remove stop words and punctuation, filtering for words with certain part of speech / POS patterns, using external knowledge bases like wordnet or wikipedia as references of good/bad keyphrases Keyphrase selection - frequency stats (TF-IDT, BM25). Not very good (the best keyphrases aren’t necessarily the most frequent within a document) - unsupervised - graph based ranking: - the importance of a candidate is determined by its relatedness to other candidates - frequency of co-occurence - semantic relatedness - a doc is represented as a graph (nodes = candidates) - algos: - TextRank - DivRank - topic-based clustering - supervised - previously seen as a classification problem, - KEA - now seen as a ranking problem - ranking SVM finally, some sample code in python 2017-06-14T00:08:15Z http://blogs.lessthandot.com/index.php/artificial-intelligence/automated-keyword-extraction-tf-idf-rake-and-textrank/ 2017-06-13T23:23:35Z https://rare-technologies.com/text-summarization-with-gensim/ 2017-06-02T01:02:20Z https://www.airpair.com/nlp/keyword-extraction-tutorial 2 tools: - simple keyword extraction with a Python library (RAKE) - Java tool (Maui) that uses a machine-learning technique. Focus on 2 tasks: - Extracting the most significant words and phrases that appear in given text - Identifying a set of topics from a predefined vocabulary that match a given text Typical steps: - Candidate selection (extract all possible words, phrases, terms or concepts that can potentially be keywords). - Properties calculation (for each candidate, properties that indicate that it may be a keyword) - Scoring and selecting keywords RAKE: finding multi-word phrases containing frequent words. +: simplicity, ease of use -: limited accuracy, parameter configuration requirement, throws away many valid phrases, doesn’t normalize candidates (no stemming). Maui: ("Multi-purpose automatic topic indexing"). Based on [Weka](/semanlink/tag/weka) (GPL, java, maven, github). Compared to RAKE: - Extract keywords not just from text, but also with a reference to a controlled vocabulary - Improve the accuracy by training Maui on manually chosen keywords - but requires a training model. Maui can use a controlled vocabulary expressed in SKOS - so I could use it in semanlink! 2017-05-24T18:20:50Z http://blog.swayy.co/post/61672584784/an-algorithm-for-generating-automatic-hashtags pretty basic, use word frequency, stemming and stopwords. 2017-05-24T18:07:27Z https://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/ based on simple POS tagging (using the Brown corpus), less accurate than the default NLTK tools, but faster 2017-05-24T17:58:13Z https://medium.com/@acrosson/extract-subject-matter-of-documents-using-nlp-e284c1c61824 2017-05-24T17:32:42Z http://scikit-learn.org/stable/auto_examples/model_selection/grid_search_text_feature_extraction.html#example-model-selection-grid-search-text-feature-extraction-py 2016-01-12T00:45:15Z http://scikit-learn.org/stable/tutorial/text_analytics/working_with_text_data.html scikit-learn tutorial about analysing a collection of labelled text documents : - load the file contents and the categories - extract feature vectors (count, tf, tf-idf) - train a linear model to perform categorization - use a grid search strategy (to find a good configuration of both the feature extraction components and the classifier) 2015-10-21T10:08:08Z http://fr.slideshare.net/julienplu/extraction-de-lasemantique 2014-06-18T09:29:38Z http://tartarus.org/martin/PorterStemmer/ 2012-03-18T12:29:41Z