scholarly journals Inducing Relational Knowledge from BERT

2020 ◽  
Vol 34 (05) ◽  
pp. 7456-7463 ◽  
Author(s):  
Zied Bouraoui ◽  
Jose Camacho-Collados ◽  
Steven Schockaert
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Language Models ◽  
Word Embeddings ◽  
Relational Knowledge ◽  
Wide Range ◽  
Fine Tune ◽  
Standard Word

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a wide range of Natural Language Processing tasks. However, it is unclear to what extent such models capture relational knowledge beyond what is already captured by standard word embeddings. To explore this question, we propose a methodology for distilling relational knowledge from a pre-trained language model. Starting from a few seed instances of a given relation, we first use a large text corpus to find sentences that are likely to express this relation. We then use a subset of these extracted sentences as templates. Finally, we fine-tune a language model to predict whether a given word pair is likely to be an instance of some relation, when given an instantiated template for that relation as input.

KM-BERT: A Pre-trained BERT for Korean Medical Natural Language Processing (Preprint)

2021 ◽  
Author(s):  
Yoojoong Kim ◽  
Jeong Moon Lee ◽  
Moon Joung Jang ◽  
Yun Jin Yum ◽  
Jong-Ho Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Pearson Correlation ◽  
Language Model ◽  
Language Models ◽  
Korean Language ◽  
Medical Texts ◽  
Proposed Model

BACKGROUND With advances in deep learning and natural language processing, analyzing medical texts is becoming increasingly important. Nonetheless, a study on medical-specific language models has not yet been conducted given the importance of medical texts. OBJECTIVE Korean medical text is highly difficult to analyze because of the agglutinative characteristics of the language as well as the complex terminologies in the medical domain. To solve this problem, we collected a Korean medical corpus and used it to train language models. METHODS In this paper, we present a Korean medical language model based on deep learning natural language processing. The proposed model was trained using the pre-training framework of BERT for the medical context based on a state-of-the-art Korean language model. RESULTS After pre-training, the proposed method showed increased accuracies of 0.147 and 0.148 for the masked language model with next sentence prediction. In the intrinsic evaluation, the next sentence prediction accuracy improved by 0.258, which is a remarkable enhancement. In addition, the extrinsic evaluation of Korean medical semantic textual similarity data showed a 0.046 increase in the Pearson correlation. CONCLUSIONS The results demonstrated the superiority of the proposed model for Korean medical natural language processing. We expect that our proposed model can be extended for application to various languages and domains.

scholarly journals Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models

2021 ◽  
Vol 11 (5) ◽  
pp. 1974 ◽  
Author(s):  
Chanhee Lee ◽  
Kisu Yang ◽  
Taesun Whang ◽  
Chanjun Park ◽  
Andrew Matteson ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Language Modeling ◽  
Language Models ◽  
Low Resource ◽  
High Resource ◽  
Cross Lingual ◽  
Data Efficiency

Language model pretraining is an effective method for improving the performance of downstream natural language processing tasks. Even though language modeling is unsupervised and thus collecting data for it is relatively less expensive, it is still a challenging process for languages with limited resources. This results in great technological disparity between high- and low-resource languages for numerous downstream natural language processing tasks. In this paper, we aim to make this technology more accessible by enabling data efficient training of pretrained language models. It is achieved by formulating language modeling of low-resource languages as a domain adaptation task using transformer-based language models pretrained on corpora of high-resource languages. Our novel cross-lingual post-training approach selectively reuses parameters of the language model trained on a high-resource language and post-trains them while learning language-specific parameters in the low-resource language. We also propose implicit translation layers that can learn linguistic differences between languages at a sequence level. To evaluate our method, we post-train a RoBERTa model pretrained in English and conduct a case study for the Korean language. Quantitative results from intrinsic and extrinsic evaluations show that our method outperforms several massively multilingual and monolingual pretrained language models in most settings and improves the data efficiency by a factor of up to 32 compared to monolingual training.

Dissecting word embeddings and language models in natural language processing

2021 ◽  
Vol 24 (5) ◽  
pp. 1509-1515
Author(s):  
Vivek Kumar Verma ◽  
Mrigank Pandey ◽  
Tarun Jain ◽  
Pradeep Kumar Tiwari
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Language Models ◽  
Word Embeddings

scholarly journals Distill BERT to Traditional Models in Chinese Machine Reading Comprehension (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13901-13902
Author(s):  
Xingkai Ren ◽  
Ronghua Shi ◽  
Fangfang Li
Keyword(s):  
Reading Comprehension ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Representation Learning ◽  
Original Model ◽  
Language Models ◽  
Machine Reading

Recently, unsupervised representation learning has been extremely successful in the field of natural language processing. More and more pre-trained language models are proposed and achieved the most advanced results especially in machine reading comprehension. However, these proposed pre-trained language models are huge with hundreds of millions of parameters that have to be trained. It is quite time consuming to use them in actual industry. Thus we propose a method that employ a distillation traditional reading comprehension model to simplify the pre-trained language model so that the distillation model has faster reasoning speed and higher inference accuracy in the field of machine reading comprehension. We evaluate our proposed method on the Chinese machine reading comprehension dataset CMRC2018 and greatly improve the accuracy of the original model. To the best of our knowledge, we are the first to propose a method that employ the distillation pre-trained language model in Chinese machine reading comprehension.

scholarly journals Towards Improving Open Student Answer Assessment using Pretrained Transformers

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Nisrine Ait Khayi ◽  
Vasile Rus ◽  
Lasang Tamang
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Transfer Learning ◽  
Language Processing ◽  
Text Classification ◽  
Question Answering ◽  
State Of The Art ◽  
Language Models ◽  
Assessment Task ◽  
Fine Tune

The transfer learning pretraining-finetuning  paradigm has revolutionized the natural language processing field yielding state-of the art results in  several subfields such as text classification and question answering. However, little work has been done investigating pretrained language models for the  open student answer assessment task. In this paper, we fine tune pretrained T5, BERT, RoBERTa, DistilBERT, ALBERT and XLNet models on the DT-Grade dataset which contains freely generated (or open) student answers together with judgment of their correctness. The experimental results demonstrated the effectiveness of these models based on the transfer learning pretraining-finetuning paradigm for open student answer assessment. An improvement of 8%-15% in accuracy was obtained over previous methods. Particularly, a T5 based method led to state-of-the-art results with an accuracy and F1 score of 0.88.

scholarly journals EMOSIS Sentiment Analysis on Tweets with Emotion and Intensity Level Recognition Considering Ending Punctuation Marks

2019 ◽  
Vol 8 (4) ◽  
pp. 10289-10293
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Emotion Recognition ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Significant Role ◽  
Language Model ◽  
Intensity Level ◽  
Processing Stage ◽  
Overall Performance

Sentiment Analysis is a tool used for determining the Polarity or Emotion of a Sentence. It is a field of Natural Language Processing which focuses on the study of opinions. In this study, the researchers solved one key challenge in Sentiment Analysis, which is to consider the Ending Punctuation Marks present in a sentence. Ending punctuation marks plays a significant role in Emotion Recognition and Intensity Level Recognition. The research made used of tweets expressing opinions about Philippine President Rodrigo Duterte. These downloaded tweets served as the inputs. It was initially subjected to pre-processing stage to be able to prepare the sentences for processing. A Language Model was created to serve as the classifier for determining the scores of the tweets. The scores give the polarity of the sentence. Accuracy is very important in sentiment analysis. To increase the chance of correctly identifying the polarity of the tweets, the input undergone Intensity Level Recognition which determines the intensifiers and negations within the sentences. The system was evaluated with overall performance of 80.27%.

scholarly journals Application of natural language processing methods to extract coded data from administrative data held in the Scottish Prescribing Information System

2017 ◽  
Vol 1 (1) ◽  
Author(s):  
Clifford Nangle ◽  
Stuart McTaggart ◽  
Margaret MacLeod ◽  
Jackie Caldwell ◽  
Marion Bennie
Keyword(s):  
Information System ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Drug Exposure ◽  
Drug Dose ◽  
Free Text ◽  
Wide Range ◽  
The Impact ◽  
Prescribing Information

ABSTRACT ObjectivesThe Prescribing Information System (PIS) datamart, hosted by NHS National Services Scotland receives around 90 million electronic prescription messages per year from GP practices across Scotland. Prescription messages contain information including drug name, quantity and strength stored as coded, machine readable, data while prescription dose instructions are unstructured free text and difficult to interpret and analyse in volume. The aim, using Natural Language Processing (NLP), was to extract drug dose amount, unit and frequency metadata from freely typed text in dose instructions to support calculating the intended number of days’ treatment. This then allows comparison with actual prescription frequency, treatment adherence and the impact upon prescribing safety and effectiveness. ApproachAn NLP algorithm was developed using the Ciao implementation of Prolog to extract dose amount, unit and frequency metadata from dose instructions held in the PIS datamart for drugs used in the treatment of gastrointestinal, cardiovascular and respiratory disease. Accuracy estimates were obtained by randomly sampling 0.1% of the distinct dose instructions from source records, comparing these with metadata extracted by the algorithm and an iterative approach was used to modify the algorithm to increase accuracy and coverage. ResultsThe NLP algorithm was applied to 39,943,465 prescription instructions issued in 2014, consisting of 575,340 distinct dose instructions. For drugs used in the gastrointestinal, cardiovascular and respiratory systems (i.e. chapters 1, 2 and 3 of the British National Formulary (BNF)) the NLP algorithm successfully extracted drug dose amount, unit and frequency metadata from 95.1%, 98.5% and 97.4% of prescriptions respectively. However, instructions containing terms such as ‘as directed’ or ‘as required’ reduce the usability of the metadata by making it difficult to calculate the total dose intended for a specific time period as 7.9%, 0.9% and 27.9% of dose instructions contained terms meaning ‘as required’ while 3.2%, 3.7% and 4.0% contained terms meaning ‘as directed’, for drugs used in BNF chapters 1, 2 and 3 respectively. ConclusionThe NLP algorithm developed can extract dose, unit and frequency metadata from text found in prescriptions issued to treat a wide range of conditions and this information may be used to support calculating treatment durations, medicines adherence and cumulative drug exposure. The presence of terms such as ‘as required’ and ‘as directed’ has a negative impact on the usability of the metadata and further work is required to determine the level of impact this has on calculating treatment durations and cumulative drug exposure.

scholarly journals Better Word Representation Vectors Using Syllabic Alphabet: A Case Study of Swahili

2019 ◽  
Vol 9 (18) ◽  
pp. 3648
Author(s):  
Casper S. Shikali ◽  
Zhou Sijie ◽  
Liu Qihe ◽  
Refuoe Mokhosi
Keyword(s):  
Language Processing ◽  
Critical Role ◽  
Language Model ◽  
Central Africa ◽  
Spoken Language ◽  
Language Models ◽  
Word Embeddings ◽  
Word Representation

Deep learning has extensively been used in natural language processing with sub-word representation vectors playing a critical role. However, this cannot be said of Swahili, which is a low resource and widely spoken language in East and Central Africa. This study proposed novel word embeddings from syllable embeddings (WEFSE) for Swahili to address the concern of word representation for agglutinative and syllabic-based languages. Inspired by the learning methodology of Swahili in beginner classes, we encoded respective syllables instead of characters, character n-grams or morphemes of words and generated quality word embeddings using a convolutional neural network. The quality of WEFSE was demonstrated by the state-of-art results in the syllable-aware language model on both the small dataset (31.229 perplexity value) and the medium dataset (45.859 perplexity value), outperforming character-aware language models. We further evaluated the word embeddings using word analogy task. To the best of our knowledge, syllabic alphabets have not been used to compose the word representation vectors. Therefore, the main contributions of the study are a syllabic alphabet, WEFSE, a syllabic-aware language model and a word analogy dataset for Swahili.

scholarly journals Reports of the Workshops Held at the Tenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment

AI Magazine ◽  
2015 ◽  
Vol 36 (1) ◽  
pp. 99-102
Author(s):  
Tiffany Barnes ◽  
Oliver Bown ◽  
Michael Buro ◽  
Michael Cook ◽  
Arne Eigenfeldt ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
North Carolina ◽  
Natural Language Processing ◽  
Natural Language ◽  
Real Time ◽  
Language Processing ◽  
State University ◽  
North Carolina State University ◽  
Wide Range ◽  
Digital Entertainment

The AIIDE-14 Workshop program was held Friday and Saturday, October 3–4, 2014 at North Carolina State University in Raleigh, North Carolina. The workshop program included five workshops covering a wide range of topics. The titles of the workshops held Friday were Games and Natural Language Processing, and Artificial Intelligence in Adversarial Real-Time Games. The titles of the workshops held Saturday were Diversity in Games Research, Experimental Artificial Intelligence in Games, and Musical Metacreation. This article presents short summaries of those events.

Mood and modality: out of theory and into the fray

2004 ◽  
Vol 10 (1) ◽  
pp. 57-89 ◽  
Author(s):  
MARJORIE MCSHANE ◽  
SERGEI NIRENBURG ◽  
RON ZACHARSKI
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Translation System ◽  
Free Standing ◽  
Indicative Conditional ◽  
Tense And Aspect ◽  
Language L ◽  
Wide Range ◽  
Value Sets

The topic of mood and modality (MOD) is a difficult aspect of language description because, among other reasons, the inventory of modal meanings is not stable across languages, moods do not map neatly from one language to another, modality may be realised morphologically or by free-standing words, and modality interacts in complex ways with other modules of the grammar, like tense and aspect. Describing MOD is especially difficult if one attempts to develop a unified approach that not only provides cross-linguistic coverage, but is also useful in practical natural language processing systems. This article discusses an approach to MOD that was developed for and implemented in the Boas Knowledge-Elicitation (KE) system. Boas elicits knowledge about any language, L, from an informant who need not be a trained linguist. That knowledge then serves as the static resources for an L-to-English translation system. The KE methodology used throughout Boas is driven by a resident inventory of parameters, value sets, and means of their realisation for a wide range of language phenomena. MOD is one of those parameters, whose values are the inventory of attested and not yet attested moods (e.g. indicative, conditional, imperative), and whose realisations include flective morphology, agglutinating morphology, isolating morphology, words, phrases and constructions. Developing the MOD elicitation procedures for Boas amounted to wedding the extensive theoretical and descriptive research on MOD with practical approaches to guiding an untrained informant through this non-trivial task. We believe that our experience in building the MOD module of Boas offers insights not only into cross-linguistic aspects of MOD that have not previously been detailed in the natural language processing literature, but also into KE methodologies that could be applied more broadly.

Sign in / Sign up

Export Citation Format

Share Document