DOCSLIB.ORG

Relational Word Embeddings

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Relational Word Embeddings Relational Word Embeddings Jose Camacho-Collados Luis Espinosa-Anke Steven Schockaert School of Computer Science and Informatics Cardiff University, United Kingdom fcamachocolladosj,espinosa-ankel,[email protected] Abstract Previous work has addressed this by incorporat- ing external knowledge graphs (Xu et al., 2014; While word embeddings have been shown to implicitly encode various forms of attribu- Celikyilmaz et al., 2015) or relations extracted tional knowledge, the extent to which they from text (Chen et al., 2016). However, the suc- capture relational information is far more lim- cess of such approaches depends on the amount ited. In previous work, this limitation has been of available relational knowledge. Moreover, they addressed by incorporating relational knowl- only consider well-defined discrete relation types edge from external knowledge bases when (e.g. is the capital of, or is a part of ), whereas learning the word embedding. Such strategies the appeal of vector space representations largely may not be optimal, however, as they are lim- comes from their ability to capture subtle aspects ited by the coverage of available resources and conflate similarity with other forms of related- of meaning that go beyond what can be expressed ness. As an alternative, in this paper we pro- symbolically. For instance, the relationship be- pose to encode relational knowledge in a sep- tween popcorn and cinema is intuitively clear, but arate word embedding, which is aimed to be it is more subtle than the assertion that “popcorn complementary to a given standard word em- is located at cinema”, which is how ConceptNet bedding. This relational word embedding is (Speer et al., 2017), for example, encodes this re- still learned from co-occurrence statistics, and lationship1. can thus be used even when no external knowl- edge base is available. Our analysis shows that In fact, regardless of how a word embedding is relational word vectors do indeed capture in- learned, if its primary aim is to capture similarity, formation that is complementary to what is en- there are inherent limitations on the kinds of re- coded in standard word embeddings. lations they can capture. For instance, such word 1 Introduction embeddings can only encode similarity preserving relations (i.e. similar entities have to be related to Word embeddings are paramount to the success of similar entities) and it is often difficult to encode current natural language processing (NLP) meth- that w is in a particular relationship while prevent- ods. Apart from the fact that they provide a con- ing the inference that words with similar vectors venient mechanism for encoding textual informa- to w are also in this relationship; e.g. Bouraoui tion in neural network models, their importance et al.(2018) found that both ( Berlin,Germany) and mainly stems from the remarkable amount of lin- (Moscow,Germany) were predicted to be instances guistic and semantic information that they capture. of the capital-of relation due to the similarity of For instance, the vector representation of the word the word vectors for Berlin and Moscow. Fur- Paris implicitly encodes that this word is a noun, thermore, while the ability to capture word analo- and more specifically a capital city, and that it gies (e.g. king-man+woman≈queen) emerged as describes a location in France. This information a successful illustration of how word embeddings arises because word embeddings are learned from can encode some types of relational information co-occurrence counts, and properties such as be- (Mikolov et al., 2013b), the generalization of this ing a capital city are reflected in such statistics. interesting property has proven to be less success- However, the extent to which relational knowledge ful than initially anticipated (Levy et al., 2014; (e.g. Trump was the successor of Obama) can be learned in this way is limited. 1http://conceptnet.io/c/en/popcorn 3286 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3286–3296 Florence, Italy, July 28 - August 2, 2019. c 2019 Association for Computational Linguistics Linzen, 2016; Rogers et al., 2017). Taking a slightly different approach, Washio This suggests that relational information has to and Kato(2018a) train a neural network to pre- be encoded separately from standard similarity- dict dependency paths from a given word pair. centric word embeddings. One appealing strategy Their approach uses standard word vectors as in- is to represent relational information by learning, put, hence relational information is encoded im- for each pair of related words, a vector that en- plicitly in the weights of the neural network, rather codes how the words are related. This strategy was than as relation vectors (although the output of this first adopted by Turney(2005), and has recently neural network, for a given word pair, can still been revisited by a number of authors (Washio and be seen as a relation vector). An advantage of Kato, 2018a; Jameel et al., 2018; Espinosa Anke this approach, compared to methods that explic- and Schockaert, 2018; Washio and Kato, 2018b; itly construct relation vectors, is that evidence ob- Joshi et al., 2019). However, in many applications, tained for one word is essentially shared with sim- word vectors are easier to deal with than vector ilar words (i.e. words whose standard word vec- representations of word pairs. tor is similar). Among others, this means that The research question we consider in this pa- their approach can in principle model relational per is whether it is possible to learn word vectors knowledge for word pairs that never co-occur in that capture relational information. Our aim is for the same sentence. A related approach, presented such relational word vectors to be complementary in (Washio and Kato, 2018b), uses lexical patterns, to standard word vectors. To make relational in- as in the LRA method, and trains a neural network formation available to NLP models, it then suffices to predict vector encodings of these patterns from to use a standard architecture and replace normal two given word vectors. In this case, the word vec- word vectors by concatenations of standard and tors are updated together with the neural network relational word vectors. In particular, we show and an LSTM to encode the patterns. Finally, sim- that such relational word vectors can be learned ilar approach is taken by the Pair2Vec method pro- directly from a given set of relation vectors. posed in (Joshi et al., 2019), where the focus is on learning relation vectors that can be used for 2 Related Work cross-sentence attention mechanisms in tasks such as question answering and textual entailment. Relation Vectors. A number of approaches have Despite the fact that such methods learn word been proposed that are aimed at learning relation vectors from which relation vectors can be pre- vectors for a given set of word pairs (a,b), based dicted, it is unclear to what extent these word vec- on sentences in which these word pairs co-occur. tors themselves capture relational knowledge. In For instance, Turney(2005) introduced a method particular, the aforementioned methods have thus called Latent Relational Analysis (LRA), which far only been evaluated in settings that rely on relies on first identifying a set of sufficiently fre- the predicted relation vectors. Since these pre- quent lexical patterns and then constructs a ma- dictions are made by relatively sophisticated neu- trix which encodes for each considered word pair ral network architectures, it is possible that most (a,b) how frequently each pattern P appears in of the relational knowledge is still captured in the between a and b in sentences that contain both weights of these networks, rather than in the word words. Relation vectors are then obtained us- vectors. Another problem with these existing ap- ing singular value decomposition. More recently, proaches is that they are computationally very ex- Jameel et al.(2018) proposed an approach inspired pensive to train; e.g. the Pair2Vec model is re- by the GloVe word embedding model (Pennington ported to need 7-10 days of training on unspecified et al., 2014) to learn relation vectors based on co- hardware2. In contrast, the approach we propose occurrence statistics between the target word pair in this paper is computationally much simpler, (a; b) and other words. Along similar lines, Es- while resulting in relational word vectors that en- pinosa Anke and Schockaert(2018) learn relation code relational information more accurately than vectors based on the distribution of words occur- those of the Pair2Vec model in lexical semantics ring in sentences that contain a and b by averag- tasks, as we will see in Section5. ing the word vectors of these co-occurring words. Knowledge-Enhanced Word Embeddings. Sev- Then, a conditional autoencoder is used to obtain lower-dimensional relation vectors. 2github.com/mandarjoshi90/pair2vec 3287 eral authors have tried to improve word embed- tors we mainly follow the initialization method of dings by incorporating external knowledge bases. Camacho-Collados et al.(2019,R ELATIVEinit) ex- For example, some authors have proposed models cept for an important difference explained below which combine the loss function of a word em- regarding the symmetry of the relations. Other re- bedding model, to ensure that word vectors are lation embedding methods could be used as well, predictive of their context words, with the loss e.g., (Jameel et al., 2018; Washio and Kato, 2018b; function of a knowledge graph embedding model, Espinosa Anke and Schockaert, 2018; Joshi et al., to encourage the word vectors to additionally be 2019), but this method has the advantage of being predictive of a given set of relational facts (Xu highly efficient. In the following we describe this et al., 2014; Celikyilmaz et al., 2015; Chen et al., procedure for learning relation vectors: we first 2016).
Load more

Recommended publications
  • Automatic Correction of Real-Word Errors in Spanish Clinical Texts
    sensors Article Automatic Correction of Real-Word Errors in Spanish Clinical Texts Daniel Bravo-Candel 1,Jésica López-Hernández 1, José Antonio García-Díaz 1 , Fernando Molina-Molina 2 and Francisco García-Sánchez 1,* 1 Department of Informatics and Systems, Faculty of Computer Science, Campus de Espinardo, University of Murcia, 30100 Murcia, Spain; [email protected] (D.B.-C.); [email protected] (J.L.-H.); [email protected] (J.A.G.-D.) 2 VÓCALI Sistemas Inteligentes S.L., 30100 Murcia, Spain; [email protected] * Correspondence: [email protected]; Tel.: +34-86888-8107 Abstract: Real-word errors are characterized by being actual terms in the dictionary. By providing context, real-word errors are detected. Traditional methods to detect and correct such errors are mostly based on counting the frequency of short word sequences in a corpus. Then, the probability of a word being a real-word error is computed. On the other hand, state-of-the-art approaches make use of deep learning models to learn context by extracting semantic features from text. In this work, a deep learning model were implemented for correcting real-word errors in clinical text. Specifically, a Seq2seq Neural Machine Translation Model mapped erroneous sentences to correct them. For that, different types of error were generated in correct sentences by using rules. Different Seq2seq models were trained and evaluated on two corpora: the Wikicorpus and a collection of three clinical datasets. The medicine corpus was much smaller than the Wikicorpus due to privacy issues when dealing Citation: Bravo-Candel, D.; López-Hernández, J.; García-Díaz, with patient information.
    [Show full text]
  • ACL 2019 Social Media Mining for Health Applications (#SMM4H)
    ACL 2019 Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task Proceedings of the Fourth Workshop August 2, 2019 Florence, Italy c 2019 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 [email protected] ISBN 978-1-950737-46-8 ii Preface Welcome to the 4th Social Media Mining for Health Applications Workshop and Shared Task - #SMM4H 2019. The total number of users of social media continues to grow worldwide, resulting in the generation of vast amounts of data. Popular social networking sites such as Facebook, Twitter and Instagram dominate this sphere. According to estimates, 500 million tweets and 4.3 billion Facebook messages are posted every day 1. The latest Pew Research Report 2, nearly half of adults worldwide and two- thirds of all American adults (65%) use social networking. The report states that of the total users, 26% have discussed health information, and, of those, 30% changed behavior based on this information and 42% discussed current medical conditions. Advances in automated data processing, machine learning and NLP present the possibility of utilizing this massive data source for biomedical and public health applications, if researchers address the methodological challenges unique to this media. In its fourth iteration, the #SMM4H workshop takes place in Florence, Italy, on August 2, 2019, and is co-located with the
    [Show full text]
  • Mapping the Hyponymy Relation of Wordnet Onto
    Under review as a conference paper at ICLR 2019 MAPPING THE HYPONYMY RELATION OF WORDNET ONTO VECTOR SPACES Anonymous authors Paper under double-blind review ABSTRACT In this paper, we investigate mapping the hyponymy relation of WORDNET to feature vectors. We aim to model lexical knowledge in such a way that it can be used as input in generic machine-learning models, such as phrase entailment predictors. We propose two models. The first one leverages an existing mapping of words to feature vectors (fastText), and attempts to classify such vectors as within or outside of each class. The second model is fully supervised, using solely WORDNET as a ground truth. It maps each concept to an interval or a disjunction thereof. On the first model, we approach, but not quite attain state of the art performance. The second model can achieve near-perfect accuracy. 1 INTRODUCTION Distributional encoding of word meanings from the large corpora (Mikolov et al., 2013; 2018; Pen- nington et al., 2014) have been found to be useful for a number of NLP tasks. These approaches are based on a probabilistic language model by Bengio et al. (2003) of word sequences, where each word w is represented as a feature vector f(w) (a compact representation of a word, as a vector of floating point values). This means that one learns word representations (vectors) and probabilities of word sequences at the same time. While the major goal of distributional approaches is to identify distributional patterns of words and word sequences, they have even found use in tasks that require modeling more fine-grained relations between words than co-occurrence in word sequences.
    [Show full text]
  • Pairwise Fasttext Classifier for Entity Disambiguation
    Pairwise FastText Classifier for Entity Disambiguation a,b b b Cheng Yu , Bing Chu , Rohit Ram , James Aichingerb, Lizhen Qub,c, Hanna Suominenb,c a Project Cleopatra, Canberra, Australia b The Australian National University c DATA 61, Australia [email protected] {u5470909,u5568718,u5016706, Hanna.Suominen}@anu.edu.au [email protected] deterministically. Then we will evaluate PFC’s Abstract performance against a few baseline methods, in- cluding SVC3 with hand-crafted text features. Fi- For the Australasian Language Technology nally, we will discuss ways to improve disambig- Association (ALTA) 2016 Shared Task, we uation performance using PFC. devised Pairwise FastText Classifier (PFC), an efficient embedding-based text classifier, 2 Pairwise Fast-Text Classifier (PFC) and used it for entity disambiguation. Com- pared with a few baseline algorithms, PFC Our Pairwise FastText Classifier is inspired by achieved a higher F1 score at 0.72 (under the the FastText. Thus this section starts with a brief team name BCJR). To generalise the model, description of FastText, and proceeds to demon- we also created a method to bootstrap the strate PFC. training set deterministically without human labelling and at no financial cost. By releasing 2.1 FastText PFC and the dataset augmentation software to the public1, we hope to invite more collabora- FastText maps each vocabulary to a real-valued tion. vector, with unknown words having a special vo- cabulary ID. A document can be represented as 1 Introduction the average of all these vectors. Then FastText will train a maximum entropy multi-class classi- The goal of the ALTA 2016 Shared Task was to fier on the vectors and the output labels.
    [Show full text]
  • Fasttext.Zip: Compressing Text Classification Models
    Under review as a conference paper at ICLR 2017 FASTTEXT.ZIP: COMPRESSING TEXT CLASSIFICATION MODELS Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herve´ Jegou´ & Tomas Mikolov Facebook AI Research fajoulin,egrave,bojanowski,matthijs,rvj,[email protected] ABSTRACT We consider the problem of producing compact architectures for text classifica- tion, such that the full model fits in a limited amount of memory. After consid- ering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quan- tization artefacts. Combined with simple approaches specifically adapted to text classification, our approach derived from fastText requires, at test time, only a fraction of the memory compared to the original FastText, without noticeably sacrificing quality in terms of classification accuracy. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy. 1 INTRODUCTION Text classification is an important problem in Natural Language Processing (NLP). Real world use- cases include spam filtering or e-mail categorization. It is a core component in more complex sys- tems such as search and ranking. Recently, deep learning techniques based on neural networks have achieved state of the art results in various NLP applications. One of the main successes of deep learning is due to the effectiveness of recurrent networks for language modeling and their application to speech recognition and machine translation (Mikolov, 2012).
    [Show full text]
  • Question Embeddings for Semantic Answer Type Prediction
    Question Embeddings for Semantic Answer Type Prediction Eleanor Bill1 and Ernesto Jiménez-Ruiz2 1, 2 City, University of London, London, EC1V 0HB Abstract. This paper considers an answer type and category prediction challenge for a set of natural language questions, and proposes a question answering clas- sification system based on word and DBpedia knowledge graph embeddings. The questions are parsed for keywords, nouns and noun phrases before word and knowledge graph embeddings are applied to the parts of the question. The vectors produced are used to train multiple multi-layer perceptron models, one for each answer type in a multiclass one-vs-all classification system for both answer cat- egory prediction and answer type prediction. Different combinations of vectors and the effect of creating additional positive and negative training samples are evaluated in order to find the best classification system. The classification system that predict the answer category with highest accuracy are the classifiers trained on knowledge graph embedded noun phrases vectors from the original training data, with an accuracy of 0.793. The vector combination that produces the highest NDCG values for answer category accuracy is the word embeddings from the parsed question keyword and nouns parsed from the original training data, with NDCG@5 and NDCG@10 values of 0.471 and 0.440 respectively for the top five and ten predicted answer types. Keywords: Semantic Web, knowledge graph embedding, answer type predic- tion, question answering. 1 Introduction 1.1 The SMART challenge The challenge [1] provided a training set of natural language questions alongside a sin- gle given answer category (Boolean, literal or resource) and 1-6 given answer types.
    [Show full text]
  • Data Driven Value Creation
    DATA DRIVEN VALUE CREATION DATA SCIENCE & ANALYTICS | DATA MANAGEMENT | VISUALIZATION & DATA EXPERIENCE D ONE, Sihlfeldstrasse 58, 8003 Zürich, d-one.ai Agenda Time Content Who 9.00 Introduction Philipp 9.30 Hands-On 1: How to kick-start NLP Jacqueline 10.15 Break / Letting People Catch up All ;-) 10.45 About ELK Philipp 11.00 Hands-On 2: Deep Dive Jacqueline 12.15 Wrap up / Discussion All 2 Today’s hosts Philipp Thomann Jacqueline Stählin Here today & tomorrow morning Here today & Monday till Wednesday 3 Setup Course Git - https://github.com/d-one/NLPeasy-workshop For infos during Workshop - https://tlk.io/amld2020-nlpeasy 4 «Making sense of data is the winning competence in all industries.» 5 Data drives Transformation 6 About ■ Zurich-based, established in 2005 with focus: data-driven value creation ■ 50 data professionals with excellent business and technical understanding & network ■ International & Swiss clients ■ In selected cases: investor for data-driven start-ups 7 Capabilities Business Consulting - Guide on data journey - Use cases, roadmap - Transformation and change - Building capabilities Machine Learning / AI Data Architecture - Ideation, implementation, - Data strategy operationalization Passionate - Enterprise requirements - Algorithms, modelling, NLP & - Information factory - Image recognition, visual analytics Down to - BI and analytics - Text analytics - Data science laboratory earth Data Management Data Experience - Data supply chain - From data to Insights to action - Data integration and modelling - Business report
    [Show full text]
  • Two Models for Named Entity Recognition in Spanish
    Two Models for Named Entity Recognition in Spanish. Submission to the CAPITEL Shared Task at IberLEF 2020 Elena Álvarez-Melladoa aInformation Sciences Institute, University of Southern California Abstract This paper documents two sequence-labeling models for NER in Spanish: a conditional random field model with handcrafted features and a BiLSTM-CRF model with word and character embeddings. Both models were trained and tested using CAPITEL (an annotated corpus of newswire written in European Spanish) and were submitted to the shared task on Spanish NER at IberLEF 2020. The best result was obtained by the CRF model, which produced an F1 score of 84.39 on the test set and was ranked #6 on the shared task. Keywords Spanish NER, CRF, BiLSTM-CRF 1. Introduction and Previous Work Named entity recognition (NER) is the task of extracting relevant spans of text (such as person names, location names, organization names) from a given document. NER has usually been framed as a sequence labeling problem [1]. Consequently, different sequence labeling approaches have been applied to NER, such as hidden Markov models [2], maxent Markov models [3] or conditional random field [4, 5]. More recently, different neural architectures have also been applied to NER [6, 7]. In this paper, we explore two sequence-labeling models to perform NER on CAPITEL, an annotated corpus of journalistic texts written in European Spanish. The explored models are a CRF model with handcrafted features and a BiLSTM-CRF model with word and character embeddings. Both models were submitted to the CAPITEL shared task on Spanish NER at IberLEF 2020 [8].
    [Show full text]
  • Learning Word Vectors for 157 Languages
    Learning Word Vectors for 157 Languages Edouard Grave1;∗ Piotr Bojanowski1;∗ Prakhar Gupta1;2 Armand Joulin1 Tomas Mikolov1 1Facebook AI Research 2EPFL fegrave,bojanowski,ajoulin,[email protected], [email protected] Abstract Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is to train them on very large corpora, and use these pre-trained models in downstream tasks. In this paper, we describe how we trained such high quality word representations for 157 languages. We used two sources of data to train these models: the free online encyclopedia Wikipedia and data from the common crawl project. We also introduce three new word analogy datasets to evaluate these word vectors, for French, Hindi and Polish. Finally, we evaluate our pre-trained word vectors on 10 languages for which evaluation datasets exists, showing very strong performance compared to previous models. Keywords: word vectors, word analogies, fasttext 1. Introduction are available at https://fasttext.cc. Distributed word representations, also known as word vec- Related work. In previous work, word vectors pre- tors, have been widely used in natural language processing, trained on large text corpora have been released along- leading to state of the art results for many tasks. Publicly side open source implementation of word embedding mod- available models, which are pre-trained on large amounts els. English word vectors trained on a part of the of data, have become a standard tool for many NLP appli- Google News dataset (100B tokens) were published with cations, but are mostly available for English.
    [Show full text]
  • Developing Amaia: a Conversational Agent for Helping Portuguese Entrepreneurs—An Extensive Exploration of Question-Matching Approaches for Portuguese
    information Article Developing Amaia: A Conversational Agent for Helping Portuguese Entrepreneurs—An Extensive Exploration of Question-Matching Approaches for Portuguese José Santos 1 , Luís Duarte 1 , João Ferreira 1 , Ana Alves 1,2 and Hugo Gonçalo Oliveira 1,* 1 CISUC, DEI, University of Coimbra, 3030-290 Coimbra, Portugal; [email protected] (J.S.); [email protected] (L.D.); [email protected] (J.F.); [email protected] (A.A.) 2 Instituto Superior de Engenharia de Coimbra (ISEC), Instituto Politécnico de Coimbra, 3030-199 Coimbra, Portugal * Correspondence: [email protected] Received: 31 July 2020; Accepted: 28 August 2020; Published: 1 September 2020 Abstract: This paper describes how we tackled the development of Amaia, a conversational agent for Portuguese entrepreneurs. After introducing the domain corpus used as Amaia’s Knowledge Base (KB), we make an extensive comparison of approaches for automatically matching user requests with Frequently Asked Questions (FAQs) in the KB, covering Information Retrieval (IR), approaches based on static and contextual word embeddings, and a model of Semantic Textual Similarity (STS) trained for Portuguese, which achieved the best performance. We further describe how we decreased the model’s complexity and improved scalability, with minimal impact on performance. In the end, Amaia combines an IR library and an STS model with reduced features. Towards a more human-like behavior, Amaia can also answer out-of-domain questions, based on a second corpus integrated in the KB. Such interactions are identified with a text classifier, also described in the paper. Keywords: semantic textual similarity; question answering; conversational agents; machine learning; information retrieval; text classification 1.
    [Show full text]
  • Download (435Kb)
    City Research Online City, University of London Institutional Repository Citation: Bill, E. and Jimenez-Ruiz, E. ORCID: 0000-0002-9083-4599 (2020). Question embeddings for semantic answer type prediction. Proceedings of the SeMantic AnsweR Type prediction task (SMART) at ISWC 2020 Semantic Web Challenge, 2774, pp. 71-80. This is the published version of the paper. This version of the publication may differ from the final published version. Permanent repository link: https://openaccess.city.ac.uk/id/eprint/25566/ Link to published version: Copyright: City Research Online aims to make research outputs of City, University of London available to a wider audience. Copyright and Moral Rights remain with the author(s) and/or copyright holders. URLs from City Research Online may be freely distributed and linked to. Reuse: Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. City Research Online: http://openaccess.city.ac.uk/ [email protected] Question Embeddings for Semantic Answer Type Prediction Eleanor Bill1 and Ernesto Jiménez-Ruiz2 1, 2 City, University of London, London, EC1V 0HB Abstract. This paper considers an answer type and category prediction challenge for a set of natural language questions, and proposes a question answering clas- sification system based on word and DBpedia knowledge graph embeddings. The questions are parsed for keywords, nouns and noun phrases before word and knowledge graph embeddings are applied to the parts of the question.
    [Show full text]
  • A Survey of Embeddings in Clinical Natural Language Processing Kalyan KS, S
    This paper got published in Journal of Biomedical Informatics. Updated version is available @ https://doi.org/10.1016/j.jbi.2019.103323 SECNLP: A Survey of Embeddings in Clinical Natural Language Processing Kalyan KS, S. Sangeetha Text Analytics and Natural Language Processing Lab Department of Computer Applications National Institute of Technology Tiruchirappalli, INDIA. [email protected], [email protected] ABSTRACT Traditional representations like Bag of words are high dimensional, sparse and ignore the order as well as syntactic and semantic information. Distributed vector representations or embeddings map variable length text to dense fixed length vectors as well as capture prior knowledge which can transferred to downstream tasks. Even though embedding has become de facto standard for representations in deep learning based NLP tasks in both general and clinical domains, there is no survey paper which presents a detailed review of embeddings in Clinical Natural Language Processing. In this survey paper, we discuss various medical corpora and their characteristics, medical codes and present a brief overview as well as comparison of popular embeddings models. We classify clinical embeddings into nine types and discuss each embedding type in detail. We discuss various evaluation methods followed by possible solutions to various challenges in clinical embeddings. Finally, we conclude with some of the future directions which will advance the research in clinical embeddings. Keywords: embeddings, distributed representations, medical, natural language processing, survey 1. INTRODUCTION Distributed vector representation or embedding is one of the recent as well as prominent addition to modern natural language processing. Embedding has gained lot of attention and has become a part of NLP researcher’s toolkit.
    [Show full text]