PyTorchKR Papers

최신 논문

총 110편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2208.03094공식 코드 · Papers with Code

Knowledge Authoring with Factual English

Knowledge representation and reasoning (KRR) systems represent knowledge as collections of facts and rules. Like databases, KRR systems contain information about domains of human activities like industrial enterprises, science, and business. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. One solution could be to extract knowledge from English text, and a number of works have attempted to do so (OpenSesame, Google's Sling, etc.). Unfortunately, at present, extraction of logical facts from unrestricted natural language is still too inaccurate to be used for reasoning, while restricting the grammar of the language (so-called controlled natural language, or CNL) is hard for the users to learn and use. Nevertheless, some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. In this paper, we address this issue by transplanting the KALM framework to a neural natural language parser, mStanza. Here we limit our attention to authoring facts and queries and therefore our focus is what we call factual English statements. Authoring other types of knowledge, such as rules, will be considered in our followup work. As it turns out, neural network based parsers have problems of their own and the mistakes they make range from part-of-speech tagging to lemmatization to dependency errors. We present a number of techniques for combating these problems and test the new system, KALMFL (i.e., KALM for factual language), on a number of benchmarks, which show KALMFL achieves correctness in excess of 95%.

arXiv:2207.11565

Context based lemmatizer for Polish language

Lemmatization is the process of grouping together the inflected forms of a word so they can be analysed as a single item, identified by the word's lemma, or dictionary form. In computational linguistics, lemmatisation is the algorithmic process of determining the lemma of a word based on its intended meaning. Unlike stemming, lemmatisation depends on correctly identifying the intended part of speech and meaning of a word in a sentence, as well as within the larger context surrounding that sentence. As a result, developing efficient lemmatisation algorithm is the complex task. In recent years it can be observed that deep learning models used for this task outperform other methods including machine learning algorithms. In this paper the polish lemmatizer based on Google T5 model is presented. The training was run with different context lengths. The model achieves the best results for polish language lemmatisation process.

arXiv:2207.04796

TArC: Tunisian Arabish Corpus First complete release

In this paper we present the final result of a project on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations. The project led to the creation of two integrated and independent resources: a corpus and a NLP tool created to annotate the former with various levels of linguistic information: word classification, transliteration, tokenization, POS-tagging, lemmatization. We discuss our choices in terms of computational and linguistic methodology and the strategies adopted to improve our results. We report on the experiments performed in order to outline our research path. Finally, we explain why we believe in the potential of these resources for both computational and linguistic researches. Keywords: Tunisian Arabizi, Annotated Corpus, Neural Network Architecture

arXiv:2206.02208공식 코드 · Papers with Code

Stylistic Fingerprints, POS-tags and Inflected Languages: A Case Study in Polish

In stylometric investigations, frequencies of the most frequent words (MFWs) and character n-grams outperform other style-markers, even if their performance varies significantly across languages. In inflected languages, word endings play a prominent role, and hence different word forms cannot be recognized using generic text tokenization. Countless inflected word forms make frequencies sparse, making most statistical procedures complicated. Presumably, applying one of the NLP techniques, such as lemmatization and/or parsing, might increase the performance of classification. The aim of this paper is to examine the usefulness of grammatical features (as assessed via POS-tag n-grams) and lemmatized forms in recognizing authorial profiles, in order to address the underlying issue of the degree of freedom of choice within lexis and grammar. Using a corpus of Polish novels, we performed a series of supervised authorship attribution benchmarks, in order to compare the classification accuracy for different types of lexical and syntactic style-markers. Even if the performance of POS-tags as well as lemmatized forms was notoriously worse than that of lexical markers, the difference was not substantial and never exceeded ca. 15%.

arXiv:2204.03064

The 2021 Urdu Fake News Detection Task using Supervised Machine Learning and Feature Combinations

This paper presents the system description submitted at the FIRE Shared Task: "The 2021 Fake News Detection in the Urdu Language". This challenge aims at automatically identifying Fake news written in Urdu. Our submitted results ranked fifth in the competition. However, after the result declaration of the competition, we managed to attain even better results than the submitted results. The best F1 Macro score achieved by one of our models is 0.6674, higher than the second-best score in the competition. The result is achieved on Support Vector Machines (polynomial kernel degree 1) with stopwords removed, lemmatization applied, and selecting the 20K best features out of 1.557 million features in total (which were produced by Word n-grams n=1,2,3,4 and Char n-grams n=2,3,4,5,6). The code is made available for reproducibility.

arXiv:2204.03062

Abusive and Threatening Language Detection in Urdu using Supervised Machine Learning and Feature Combinations

This paper presents the system descriptions submitted at the FIRE Shared Task 2021 on Urdu's Abusive and Threatening Language Detection Task. This challenge aims at automatically identifying abusive and threatening tweets written in Urdu. Our submitted results were selected for the third recognition at the competition. This paper reports a non-exhaustive list of experiments that allowed us to reach the submitted results. Moreover, after the result declaration of the competition, we managed to attain even better results than the submitted results. Our models achieved 0.8318 F1 score on Task A (Abusive Language Detection for Urdu Tweets) and 0.4931 F1 score on Task B (Threatening Language Detection for Urdu Tweets). Results show that Support Vector Machines with stopwords removed, lemmatization applied, and features vector created by the combinations of word n-grams for n=1,2,3 produced the best results for Task A. For Task B, Support Vector Machines with stopwords removed, lemmatization not applied, feature vector created from a pre-trained Urdu Word2Vec (on word unigrams and bigrams), and making the dataset balanced using oversampling technique produced the best results. The code is made available for reproducibility.

arXiv:2201.01956

HuSpaCy: an industrial-strength Hungarian natural language processing toolkit

Although there are a couple of open-source language processing pipelines available for Hungarian, none of them satisfies the requirements of today's NLP applications. A language processing pipeline should consist of close to state-of-the-art lemmatization, morphosyntactic analysis, entity recognition and word embeddings. Industrial text processing applications have to satisfy non-functional software quality requirements, what is more, frameworks supporting multiple languages are more and more favored. This paper introduces HuSpaCy, an industry-ready Hungarian language processing toolkit. The presented tool provides components for the most important basic linguistic analysis tasks. It is open-source and is available under a permissive license. Our system is built upon spaCy's NLP components resulting in an easily usable, fast yet accurate application. Experiments confirm that HuSpaCy has high accuracy while maintaining resource-efficient prediction capabilities.

arXiv:2109.03903공식 코드 · Papers with Code

ELIT: Emory Language and Information Toolkit

We introduce ELIT, the Emory Language and Information Toolkit, which is a comprehensive NLP framework providing transformer-based end-to-end models for core tasks with a special focus on memory efficiency while maintaining state-of-the-art accuracy and speed. Compared to existing toolkits, ELIT features an efficient Multi-Task Learning (MTL) model with many downstream tasks that include lemmatization, part-of-speech tagging, named entity recognition, dependency parsing, constituency parsing, semantic role labeling, and AMR parsing. The backbone of ELIT's MTL framework is a pre-trained transformer encoder that is shared across tasks to speed up their inference. ELIT provides pre-trained models developed on a remix of eight datasets. To scale up its service, ELIT also integrates a RESTful Client/Server combination. On the server side, ELIT extends its functionality to cover other tasks such as tokenization and coreference resolution, providing an end user with agile research experience. All resources including the source codes, documentation, and pre-trained models are publicly available at https://github.com/emorynlp/elit.

arXiv:2107.07974

POS tagging, lemmatization and dependency parsing of West Frisian

We present a lemmatizer/POS-tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependency version 2. POS tags were assigned to words by using a Dutch POS tagger that was applied to a literal word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using literal translations that were created by using the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a literal Dutch translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. A significant improvement was found for `lemma'. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.

arXiv:2107.03266공식 코드 · Papers with Code

Lemmatization of Historical Old Literary Finnish Texts in Modern Orthography

Texts written in Old Literary Finnish represent the first literary work ever written in Finnish starting from the 16th century. There have been several projects in Finland that have digitized old publications and made them available for research use. However, using modern NLP methods in such data poses great challenges. In this paper we propose an approach for simultaneously normalizing and lemmatizing Old Literary Finnish into modern spelling. Our best model reaches to 96.3\% accuracy in texts written by Agricola and 87.7\% accuracy in other contemporary out-of-domain text. Our method has been made freely available on Zenodo and Github.

arXiv:2106.02009

A Case Study of Spanish Text Transformations for Twitter Sentiment Analysis

Sentiment analysis is a text mining task that determines the polarity of a given text, i.e., its positiveness or negativeness. Recently, it has received a lot of attention given the interest in opinion mining in micro-blogging platforms. These new forms of textual expressions present new challenges to analyze text given the use of slang, orthographic and grammatical errors, among others. Along with these challenges, a practical sentiment classifier should be able to handle efficiently large workloads. The aim of this research is to identify which text transformations (lemmatization, stemming, entity removal, among others), tokenizers (e.g., words $n$-grams), and tokens weighting schemes impact the most the accuracy of a classifier (Support Vector Machine) trained on two Spanish corpus. The methodology used is to exhaustively analyze all the combinations of the text transformations and their respective parameters to find out which characteristics the best performing classifiers have in common. Furthermore, among the different text transformations studied, we introduce a novel approach based on the combination of word based $n$-grams and character based $q$-grams. The results show that this novel combination of words and characters produces a classifier that outperforms the traditional word based combination by $11.17\%$ and $5.62\%$ on the INEGI and TASS'15 dataset, respectively.

arXiv:2105.12428공식 코드 · Papers with Code

Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered

We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.

arXiv:2104.13456

Named Entity Recognition and Linking Augmented with Large-Scale Structured Data

In this paper we describe our submissions to the 2nd and 3rd SlavNER Shared Tasks held at BSNLP 2019 and BSNLP 2021, respectively. The tasks focused on the analysis of Named Entities in multilingual Web documents in Slavic languages with rich inflection. Our solution takes advantage of large collections of both unstructured and structured documents. The former serve as data for unsupervised training of language models and embeddings of lexical units. The latter refers to Wikipedia and its structured counterpart - Wikidata, our source of lemmatization rules, and real-world entities. With the aid of those resources, our system could recognize, normalize and link entities, while being trained with only small amounts of labeled data.

arXiv:2103.01273

On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions

Recent complementary strands of research have shown that leveraging information on the data source through encoding their properties into embeddings can lead to performance increase when training a single model on heterogeneous data sources. However, it remains unclear in which situations these dataset embeddings are most effective, because they are used in a large variety of settings, languages and tasks. Furthermore, it is usually assumed that gold information on the data source is available, and that the test data is from a distribution seen during training. In this work, we compare the effect of dataset embeddings in mono-lingual settings, multi-lingual settings, and with predicted data source label in a zero-shot setting. We evaluate on three morphosyntactic tasks: morphological tagging, lemmatization, and dependency parsing, and use 104 datasets, 66 languages, and two different dataset grouping strategies. Performance increases are highest when the datasets are of the same language, and we know from which distribution the test-instance is drawn. In contrast, for setups where the data is from an unseen distribution, performance increase vanishes.

arXiv:2101.12056공식 코드 · Papers with Code

Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources

We propose a novel hybrid approach to lemmatization that enhances the seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system. During training, the enhanced lemmatizer learns both to generate lemmas via a sequential decoder and copy the lemma characters from the external candidates supplied during run-time. Our lemmatizer enhanced with candidates extracted from the Apertium morphological analyzer achieves statistically significant improvements compared to baseline models not utilizing additional lemma information, achieves an average accuracy of 97.25% on a set of 23 UD languages, which is 0.55% higher than obtained with the Stanford Stanza model on the same set of languages. We also compare with other methods of integrating external data into lemmatization and show that our enhanced system performs considerably better than a simple lexicon extension method based on the Stanza system, and it achieves complementary improvements w.r.t. the data augmentation method.

arXiv:2101.04226공식 코드 · Papers with Code

DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks

Translating Natural Language Queries (NLQs) to Structured Query Language (SQL) in interfaces deployed in relational databases is a challenging task, which has been widely studied in database community recently. Conventional rule based systems utilize series of solutions as a pipeline to deal with each step of this task, namely stop word filtering, tokenization, stemming/lemmatization, parsing, tagging, and translation. Recent works have mostly focused on the translation step overlooking the earlier steps by using ad-hoc solutions. In the pipeline, one of the most critical and challenging problems is keyword mapping; constructing a mapping between tokens in the query and relational database elements (tables, attributes, values, etc.). We define the keyword mapping problem as a sequence tagging problem, and propose a novel deep learning based supervised approach that utilizes POS tags of NLQs. Our proposed approach, called \textit{DBTagger} (DataBase Tagger), is an end-to-end and schema independent solution, which makes it practical for various relational databases. We evaluate our approach on eight different datasets, and report new state-of-the-art accuracy results, $92.4\%$ on the average. Our results also indicate that DBTagger is faster than its counterparts up to $10000$ times and scalable for bigger databases.

arXiv:2101.03717

Constraint 2021: Machine Learning Models for COVID-19 Fake News Detection Shared Task

In this system paper we present our contribution to the Constraint 2021 COVID-19 Fake News Detection Shared Task, which poses the challenge of classifying COVID-19 related social media posts as either fake or real. In our system, we address this challenge by applying classical machine learning algorithms together with several linguistic features, such as n-grams, readability, emotional tone and punctuation. In terms of pre-processing, we experiment with various steps like stop word removal, stemming/lemmatization, link removal and more. We find our best performing system to be based on a linear SVM, which obtains a weighted average F1 score of 95.19% on test data, which lands a place in the middle of the leaderboard (place 80 of 167).

arXiv:2101.03289공식 코드 · Papers with Code

Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing

We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependencies treebanks. Despite the use of a large pretrained transformer, our toolkit is still efficient in memory usage and speed. This is achieved by our novel plug-and-play mechanism with Adapters where a multilingual pretrained transformer is shared across pipelines for different languages. Our toolkit along with pretrained models and code are publicly available at: https://github.com/nlp-uoregon/trankit. A demo website for our toolkit is also available at: http://nlp.uoregon.edu/trankit. Finally, we create a demo video for Trankit at: https://youtu.be/q0KGP3zGjGc.

arXiv:2012.04575공식 코드 · Papers with Code

The Role of Interpretable Patterns in Deep Learning for Morphology

We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, where the encoder is a pattern matching network. Each pattern scores all possible N character long subwords (substrings) on the source side, and the highest scoring subword's score is used to initialize the decoder as well as the input to the attention mechanism. This method allows learning which subwords of the input are important for generating the output. By training the models on the same source but different target, we can compare what subwords are important for different tasks and how they relate to each other. We define a similarity metric, a generalized form of the Jaccard similarity, and assign a similarity score to each pair of the three tasks that work on the same source but may differ in target. We examine how these three tasks are related to each other in 12 languages. Our code is publicly available.

arXiv:2011.00565

CURE: Collection for Urdu Information Retrieval Evaluation and Ranking

Urdu is a widely spoken language with 163 million speakers worldwide across the globe. Information Retrieval (IR) for Urdu entails special consideration of research community due to its rich morphological features and a large number of speakers. In general, IR evaluation task is not extensively explored for Urdu. The most important missing element is the availability of a standardized evaluation corpus specific to Urdu. In this research work, we propose and construct a standard test collection of Urdu documents for IR evaluation and named it Collection for Urdu Retrieval Evaluation (CURE). We select 1,096 unique documents against 50 diverse queries from a large collection of 0.5 million crawled documents using two IR models. The purpose of test collection is the evaluation of IR models, ranking algorithms, and different natural language processing techniques. Next, we perform binary relevance judgment on the selected documents. We also built two other language resources for lemmatization and query expansion specific to our test collection. Evaluation of test collection is carried out using four retrieval models as well using the stop-words list, lemmatization, and query expansion. Furthermore, error analysis was performed for each query with different NLP techniques. To the best of our knowledge, this work is the first attempt for preparing a standardized information retrieval evaluation test collection for the Urdu language.