In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion. In addition, we present a novel and unique dataset for intrinsic evaluation of corpus-based term set expansion algorithms. We show that, over this dataset, our algorithm provides up to 5 mean average precision points over the best baseline.
Microsoft India（微软印度）；IIT Madras（马德拉斯印度理工学院）；AI4Bharat
We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2.7 billion words for 10 Indian languages from two language families. We share pre-trained word embeddings trained on these corpora. We create news article category classification datasets for 9 languages to evaluate the embeddings. We show that the IndicNLP embeddings significantly outperform publicly available pre-trained embedding on multiple evaluation tasks. We hope that the availability of the corpus will accelerate Indic NLP research. The resources are available at https://github.com/ai4bharat-indicnlp/indic…
Virginia Tech（弗吉尼亚理工大学）；IBM Research Almaden（IBM阿尔马登研究院）；eBay Inc（eBay公司）
Recent advances in text representation have shown that training on large amounts of text is crucial for natural language understanding. However, models trained without predefined notions of topical interest typically require careful fine-tuning when transferred to specialized domains. When a sufficient amount of within-domain text may not be available, expanding a seed corpus of relevant documents from large-scale web data poses several challenges. First, corpus expansion requires scoring and ranking each document in the collection, an operation that can quickly become computationally expensiv…
Research and Technology Center, Robert Bosch（罗伯特·博世研究与技术中心）
Word embeddings are a basic building block of modern NLP pipelines. Efforts have been made to learn rich, efficient, and interpretable embeddings for large generic datasets available in the public domain. However, these embeddings have limited applicability for small corpora from specific domains such as automotive, manufacturing, maintenance and support, etc. In this work, we present a comprehensive notion of interpretability for word embeddings and propose a novel method to generate highly interpretable and efficient embeddings for a domain-specific small corpus. We report the evaluation res…
University of Electronic Science and Technology of China（电子科技大学）
Representing words and phrases into dense vectors of real numbers which encode semantic and syntactic properties is a vital constituent in natural language processing (NLP). The success of neural network (NN) models in NLP largely rely on such dense word representations learned on the large unlabeled corpus. Sindhi is one of the rich morphological language, spoken by large population in Pakistan and India lacks corpora which plays an essential role of a test-bed for generating word embeddings and developing language independent NLP systems. In this paper, a large corpus of more than 61 million…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；The Hong Kong University of Science and Technology（香港科技大学）
Given a small set of seed entities (e.g., ``USA'', ``Russia''), corpus-based set expansion is to induce an extensive set of entities which share the same semantic class (Country in this example) from a given corpus. Set expansion benefits a wide range of downstream applications in knowledge discovery, such as web search, taxonomy construction, and query suggestion. Existing corpus-based set expansion algorithms typically bootstrap the given seeds by incorporating lexical patterns and distributional similarity. However, due to no negative sets provided explicitly, these methods suffer from sema…
AI Saturdays Lagos（拉各斯AI星期六）；Niger-Volta Language Technologies Institute（尼日尔-沃尔特语言技术研究所）
This paper describes foundational efforts with SautiDB-Naija, a novel corpus of non-native (L2) Nigerian English speech. We describe how the corpus was created and curated as well as preliminary experiments with accent classification and learning Nigerian accent embeddings. The initial version of the corpus includes over 900 recordings from L2 English speakers of Nigerian languages, such as Yoruba, Igbo, Edo, Efik-Ibibio, and Igala. We further demonstrate how fine-tuning on a pre-trained model like wav2vec can yield representations suitable for related speech tasks such as accent classificatio…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-…
We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective…
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder architecture trained on a parallel corpus to obtain multilingual sentence representations. We then use the representations directly to score and filter the noisy parallel sentences without additionally training a scoring function. We contrast our approach to other promising methods and show that LASER yields strong results. Finally, we produce an ensemble of differen…
University of Oslo（奥斯陆大学）；University of Tyumen（秋明大学）
In this paper, we present a distributional word embedding model trained on one of the largest available Russian corpora: Araneum Russicum Maximum (over 10 billion words crawled from the web). We compare this model to the model trained on the Russian National Corpus (RNC). The two corpora are much different in their size and compilation procedures. We test these differences by evaluating the trained models against the Russian part of the Multilingual SimLex999 semantic similarity dataset. We detect and describe numerous issues in this dataset and publish a new corrected version. Aside from the …
This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical borrowings -- words from one language that are introduced into another without orthographic adaptation -- and use it to evaluate how several sequence labeling models (CRF, BiLSTM-CRF, and Transformer-based models) perform. The corpus contains 370,000 tokens and is larger, more borrowing-dense, OOV-rich, and topic-varied than previous corpora available for this task. Our result…
Production of news content is growing at an astonishing rate. To help manage and monitor the sheer amount of text, there is an increasing need to develop efficient methods that can provide insights into emerging content areas, and stratify unstructured corpora of text into `topics' that stem intrinsically from content similarity. Here we present an unsupervised framework that brings together powerful vector embeddings from natural language processing with tools from multiscale graph partitioning that can reveal natural partitions at different resolutions without making a priori assumptions abo…
Given a small corpus $\mathcal D_T$ pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of $\mathcal D_T$. These embeddings may be used in various tasks involving $\mathcal D_T$. A popular strategy in limited data settings is to adapt pre-trained embeddings $\mathcal E$ trained on a large corpus. To correct for sense drift, fine-tuning, regularization, projection, and pivoting have been proposed recently. Among these, regularization informed by a word's corpus frequency performed wel…
Generative adversarial nets (GANs) have been successfully applied to the artificial generation of image data. In terms of text data, much has been done on the artificial generation of natural language from a single corpus. We consider multiple text corpora as the input data, for which there can be two applications of GANs: (1) the creation of consistent cross-corpus word embeddings given different word embeddings per corpus; (2) the generation of robust bag-of-words document embeddings for each corpora. We demonstrate our GAN models on real-world text data sets from different corpora, and show…
Semantic code search is the task of retrieving relevant code snippet given a natural language query. Different from typical information retrieval tasks, code search requires to bridge the semantic gap between the programming language and natural language, for better describing intrinsic concepts and semantics. Recently, deep neural network for code search has been a hot research topic. Typical methods for neural code search first represent the code snippet and query text as separate embeddings, and then use vector distance (e.g. dot-product or cosine) to calculate the semantic similarity betwe…
Dartmouth College（达特茅斯学院）；Geisel School of Medicine at Dartmouth（达特茅斯盖泽尔医学院）
Objective: Currently, a major limitation for natural language processing (NLP) analyses in clinical applications is that a concept can be referenced in various forms across different texts. This paper introduces Multi-Ontology Refined Embeddings (MORE), a novel hybrid framework for incorporating domain knowledge from multiple ontologies into a distributional semantic model, learned from a corpus of clinical text. Materials and Methods: We use the RadCore and MIMIC-III free-text datasets for the corpus-based component of MORE. For the ontology-based part, we use the Medical Subject Headings (Me…
Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is the large number of out-of-vocabulary words. In this paper we proposed a method which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of …
Technische Universität Berlin（柏林工业大学）；Telekom Innovation Laboratories（德国电信创新实验室）
In the field of Natural Language Processing (NLP), we revisit the well-known word embedding algorithm word2vec. Word embeddings identify words by vectors such that the words' distributional similarity is captured. Unexpectedly, besides semantic similarity even relational similarity has been shown to be captured in word embeddings generated by word2vec, whence two questions arise. Firstly, which kind of relations are representable in continuous space and secondly, how are relations built. In order to tackle these questions we propose a bottom-up point of view. We call generating input text for …
TU Berlin（柏林工业大学）；University of Copenhagen（哥本哈根大学）；BIFOLD（柏林学习与数据基础研究所）；Le Mans Université（勒芒大学）；RIKEN Center for AIP（理化学研究所先进智能项目中心）
Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, e.g., across time or domain. Current methods do not offer a way to use or predict information on structure between sub-corpora, time or domain and dynamic embeddings can only be compared after post-alignment. We propose novel word embedding methods that provide general word representations for the whole corpus, domain-specific representations for each sub-corpus, sub-corpus structure, and embedding alignment simultaneously. We present an empirical evaluat…
In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size. Natural language processing (NLP) tasks usually perform better with embeddings from bigger corpora. However, broadness of covered domain and noise can play important roles. We evaluate embeddings based on two Swedish corpora: The Gigaword and Wikipedia, in analogy (intrinsic) tests and discover that the embeddings from the Wikipedia corpus generally outperform those from the Gigaword corpus, which is a bigger corpus. Downstream…
Fake news detection is a challenging task aiming to reduce human time and effort to check the truthfulness of news. Automated approaches to combat fake news, however, are limited by the lack of labeled benchmark datasets, especially in languages other than English. Moreover, many publicly available corpora have specific limitations that make them difficult to use. To address this problem, our contribution is threefold. First, we propose a new, publicly available German topic related corpus for fake news detection. To the best of our knowledge, this is the first corpus of its kind. In this rega…
National and Kapodistrian University of Athens（雅典国立与卡波迪斯特里亚大学）
One of the major challenges that NLP faces is metaphor detection, especially by automatic means, a task that becomes even more difficult for languages lacking in linguistic resources and tools. Our purpose is the automatic differentiation between literal and metaphorical meaning in authentic non-annotated phrases from the Corpus of Greek Texts by means of computational methods of machine learning. For this purpose the theoretical background of distributional semantics is discussed and employed. Distributional Semantics Theory develops concepts and methods for the quantification and classificat…
Allen Institute for AI（艾伦人工智能研究所）；Bar Ilan University（巴伊兰大学）
We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora. The result is a corpus which is sense-tagged according to a corpus-derived sense inventory and where each sense is associated with indicative words. Evaluation on English Wikipedia that was sense-tagged using our method shows that both the induced senses, and the per-instance sense assignment, are of high quality even compared to WSD methods, such as Babelfy. Furthermore, by training a static word embeddings algorithm on the sense-tagged …
This paper introduces the hmBlogs corpus for Persian, as a low resource language. This corpus has been prepared based on a collection of nearly 20 million blog posts over a period of about 15 years from a space of Persian blogs and includes more than 6.8 billion tokens. It can be claimed that this corpus is currently the largest Persian corpus that has been prepared independently for the Persian language. This corpus is presented in both raw and preprocessed forms, and based on the preprocessed corpus some word embedding models are produced. By the provided models, the hmBlogs is compared with…
In this paper, we share the process of developing word embeddings for the Cyrillic variant of the Uzbek language. The result of our work is the first publicly available set of word vectors trained on the word2vec, GloVe, and fastText algorithms using a high-quality web crawl corpus developed in-house. The developed word embeddings can be used in many natural language processing downstream tasks.
Mongolian University of Science and Technology（蒙古科技大学）；Irkutsk National Research Technical University（伊尔库茨克国立研究技术大学）
A large amount of feedback was collected over the years. Many feedback analysis models have been developed focusing on the English language. Recognizing the concept of feedback is challenging and crucial in languages which do not have applicable corpus and tools employed in Natural Language Processing (i.e., vocabulary corpus, sentence structure rules, etc). However, in this paper, we study a feedback classification in Mongolian language using two different word embeddings for deep learning. We compare the results of proposed approaches. We use feedback data in Cyrillic collected from 2012-201…
The recognition of pharmacological substances, compounds and proteins is an essential preliminary work for the recognition of relations between chemicals and other biomedically relevant units. In this paper, we describe an approach to Task 1 of the PharmaCoNER Challenge, which involves the recognition of mentions of chemicals and drugs in Spanish medical texts. We train a state-of-the-art BiLSTM-CRF sequence tagger with stacked Pooled Contextualized Embeddings, word and sub-word embeddings using the open-source framework FLAIR. We present a new corpus composed of articles and papers from Spani…
George Washington University（乔治华盛顿大学）；AWS AI（AWS人工智能）
In this paper we present an emotion classifier model submitted to the SemEval-2019 Task 3: EmoContext. The task objective is to classify emotion (i.e. happy, sad, angry) in a 3-turn conversational data set. We formulate the task as a classification problem and introduce a Gated Recurrent Neural Network (GRU) model with attention layer, which is bootstrapped with contextual information and trained with a multigenre corpus. We utilize different word embeddings to empirically select the most suited one to represent our features. We train the model with a multigenre emotion corpus to leverage usin…
Instituto Tecnológico de Buenos Aires（布宜诺斯艾利斯理工学院）；Universidad de Buenos Aires（布宜诺斯艾利斯大学）；CONICET（国家科学技术研究委员会）
There is an increasing interest in the NLP community in capturing variations in the usage of language, either through time (i.e., semantic drift), across regions (as dialects or variants) or in different social contexts (i.e., professional or media technolects). Several successful dynamical embeddings have been proposed that can track semantic change through time. Here we show that a model with a central word representation and a slice-dependent contribution can learn word embeddings from different corpora simultaneously. This model is based on a star-like representation of the slices. We appl…
Rootroo Ltd（Rootroo有限公司）；University of Helsinki（赫尔辛基大学）；Mahidol University（玛希隆大学）
We present the first openly available corpus for detecting depression in Thai. Our corpus is compiled by expert verified cases of depression in several online blogs. We experiment with two different LSTM based models and two different BERT based models. We achieve a 77.53\% accuracy with a Thai BERT model in detecting depression. This establishes a good baseline for future researcher on the same corpus. Furthermore, we identify a need for Thai embeddings that have been trained on a more varied corpus than Wikipedia. Our corpus, code and trained models have been released openly on Zenodo.
We introduced KaWAT (Kata Word Analogy Task), a new word analogy task dataset for Indonesian. We evaluated on it several existing pretrained Indonesian word embeddings and embeddings trained on Indonesian online news corpus. We also tested them on two downstream tasks and found that pretrained word embeddings helped either by reducing the training epochs or yielding significant performance gains.
Relation Extraction Datasets in the Digital Humanities Domain and their Evaluation with Word Embeddings
ITMO University（圣彼得堡国立信息技术机械与光学大学）；International Laboratory of Information Science and Semantic Technologies（国际信息科学与语义技术实验室）；National Research University, Higher School of Economics（国立研究型大学高等经济学院）
In this article we present the Frankfurt Latin Lexicon (FLL), a lexical resource for Medieval Latin that is used both for the lemmatization of Latin texts and for the post-editing of lemmatizations. We describe recent advances in the development of lemmatizers and test them against the Capitularies corpus (comprising Frankish royal edicts, mid-6th to mid-9th century), a corpus created as a reference for processing Medieval Latin. We also consider the post-correction of lemmatizations using a limited crowdsourcing process aimed at continuous review and updating of the FLL. Starting from the tex…
Universidad de Buenos Aires（布宜诺斯艾利斯大学）；Instituto de Investigación en Ciencias de la Computación, UBA-CONICET（布宜诺斯艾利斯大学-阿根廷国家科学技术研究委员会计算机科学研究所）；Universidad Torcuato Di Tella - CONICET（托尔夸托·迪特利亚大学-阿根廷国家科学技术研究委员会）
Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acquire new semantic relations between words remain unclear. In the present article we investigate whether LSA and Word2vec capacity to identify relevant semantic dimensions increases with size of corpus. One intuitive hypothesis is that the capacity to identify relevant dimensions should increase as the amount of data increases. However, if corpus size grow in topics which are not specific to the domain of interest, sign…
University of Canterbury（坎特伯雷大学）；New Zealand Institute for Language, Brain and Behaviour（新西兰语言、大脑与行为研究所）
This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible t…
Charles University（查理大学）；University of the Basque Country（巴斯克大学）
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data. We first produce a synthetic parallel corpus using unsupervised machine translation, and use it to fine-tune a pretrained cross-lingual masked language model (XLM) to derive the multilingual sentence representations. The quality of the representations is evaluated on two parallel corpus mining tasks with improvements of up to 22 F1 points o…
Google AI（谷歌人工智能）；Carnegie Mellon University（卡内基梅隆大学）
This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of each other. This is achieved using a novel training method that introduces hard negatives consisting of sentences that are not translations but that have some degree of semantic similarity. The quality of the resulting embeddings are evaluated on parallel corpus reconstruction and by assessing machine translation systems trained on gold vs. mined sentence pa…
Motivation: The proliferation of Biomedical research articles has made the task of information retrieval more important than ever. Scientists and Researchers are having difficulty in finding articles that contain information relevant to them. Proper extraction of biomedical entities like Disease, Drug/chem, Species, Gene/protein, can considerably improve the filtering of articles resulting in better extraction of relevant information. Performance on BioNer benchmarks has progressively improved because of progression in transformers-based models like BERT, XLNet, OpenAI, GPT2, etc. These models…
Learned vector representations of words are useful tools for many information retrieval and natural language processing tasks due to their ability to capture lexical semantics. However, while many such tasks involve or even rely on named entities as central components, popular word embedding models have so far failed to include entities as first-class citizens. While it seems intuitive that annotating named entities in the training corpus should result in more intelligent word features for downstream tasks, performance issues arise when popular embedding approaches are naively applied to entit…
