Multilingual pretrained language models (MPLMs) exhibit multilinguality and are well suited for transfer across languages. Most MPLMs are trained in an unsupervised fashion and the relationship between their objective and multilinguality is unclear. More specifically, the question whether MPLM representations are language-agnostic or they simply interleave well with learned task prediction heads arises. In this work, we locate language-specific information in MPLMs and identify its dimensionality and the layers where this information occurs. We show that language-specific information is scattered across many dimensions, which can be projected into a linear subspace. Our study contributes to a better understanding of MPLM representations, going beyond treating them as unanalyzable blobs of information.
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and extralinguistic context. Based on a pretrained language model (PLM), dynamic contextualized word embeddings model time and social space jointly, which makes them attractive for a range of NLP tasks involving semantic variability. We highlight potential app…
Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Schütze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has been addressed by separately learning representations for rare words. In this work, we transfer this idea to pretrained language models: We introduce BERTRAM, a powerful architecture based on BERT that is capable of inferring high-quality embeddings for rare words that are suitable as input representations for deep language models. This is achieved by enabling…
Fudan University（复旦大学）；Amazon Shanghai AI Lab（亚马逊上海人工智能实验室）
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models. Few works explore the potential of deep contextualized knowledge representation when injecting knowledge. In this paper, we propose the Contextualized Language and Knowledge Embedding (CoLAKE), which jointly learns contextualized representation for both language and knowledge with the extended MLM objective. Instead of injecting only entity embed…
Dalhousie University（达尔豪斯大学）；Qatar Computing Research Institute（卡塔尔计算研究所）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Post-processing of static embedding has beenshown to improve their performance on both lexical and sequence-level tasks. However, post-processing for contextualized embeddings is an under-studied problem. In this work, we question the usefulness of post-processing for contextualized embeddings obtained from different layers of pre-trained language models. More specifically, we standardize individual neuron activations using z-score, min-max normalization, and by removing top principle components using the all-but-the-top method. Additionally, we apply unit length normalization to word represen…
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
A growing body of research in natural language processing (NLP) and natural language understanding (NLU) is investigating human-like knowledge learned or encoded in the word embeddings from large language models. This is a step towards understanding what knowledge language models capture that resembles human understanding of language and communication. Here, we investigated whether and how the affect meaning of a word (i.e., valence, arousal, dominance) is encoded in word embeddings pre-trained in large neural networks. We used the human-labeled dataset as the ground truth and performed variou…
University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）；Google, Inc.（谷歌公司）
Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance. In this paper, we conduct probing experiments to determine what additional information is carried intrinsically by the in-domain trained contextualized embeddings. For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers. We compare BERT, ELMo, BioBERT and BioELMo, …
Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings
Institute for Research in Technology, ICAI School of Engineering, Comillas Pontifical University（技术研究所，ICAI工程学院，科米利亚斯宗座大学）；DD-AIM, Senior Machine Learning Researcher（DD-AIM，高级机器学习研究员）
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Cloud & AI（华为云与AI）；School of Computer Science, University of Science and Technology of China（中国科学技术大学计算机科学学院）
Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information. However, traditional methods usually treat a triple as a training unit during the knowledge representation learning (KRL) procedure, neglecting contextualized information of the nodes in knowledge graphs (KGs). We generalize the modeling object to a very general form, which theoretically supports any subgraph extracted from the knowledge graph, and these subgraphs are fed into a novel transformer-based model to learn the knowledge embeddings. To broaden usage scenarios of k…
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We evaluate the proposed architecture using both contextualized and fixed word embedding models on three different benchmark datasets (Inspec, SemEval 2010, SemEval 2017) and compare with existing popular unsupervised and supervised techniques. Our results quantify the benefits of (a) using contextualized embeddings (e.g. BERT) over fixed word embeddings (e.g. Glove); (b) using a B…
Contextualized word embeddings in language models have given much advance to NLP. Intuitively, sentential information is integrated into the representation of words, which can help model polysemy. However, context sensitivity also leads to the variance of representations, which may break the semantic consistency for synonyms. We quantify how much the contextualized embeddings of each word sense vary across contexts in typical pre-trained models. Results show that contextualized embeddings can be highly consistent across contexts. In addition, part-of-speech, number of word senses, and sentence…
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
We present an extensive evaluation of three recently proposed methods for contextualized embeddings on 89 corpora in 54 languages of the Universal Dependencies 2.3 in three tasks: POS tagging, lemmatization, and dependency parsing. Employing the BERT, Flair and ELMo as pretrained embedding inputs in a strong baseline of UDPipe 2.0, one of the best-performing systems of the CoNLL 2018 Shared Task and an overall winner of the EPE 2018, we present a one-to-one comparison of the three contextualized word embedding methods, as well as a comparison with word2vec-like pretrained embeddings and with e…
We present a novel online algorithm that learns the essence of each dimension in word embeddings by minimizing the within-group distance of contextualized embedding groups. Three state-of-the-art neural-based language models are used, Flair, ELMo, and BERT, to generate contextualized word embeddings such that different embeddings are generated for the same word type, which are grouped by their senses manually annotated in the SemCor dataset. We hypothesize that not all dimensions are equally important for downstream tasks so that our algorithm can detect unessential dimensions and discard them…
Stanford University（斯坦福大学）；University of Toronto（多伦多大学）
Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT? Are there infinitely many context-specific representations for each word, or are words essentially assigned one of a finite number of word-sense representations? For one, we find that the contextualized representations of all words are not isotropic in any layer of the contextualizing model. While representations of the same word in different contexts still …
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；University of Edinburgh（爱丁堡大学）
In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations. Instead of seeking alignments to existing well-defined annotations, we infer this latent network in a fully unsupervised way using a structured variational autoencoder. The induced states not only serve as anchors that mark the topology (neighbors and connectivity) of the representation manifold but also reveal the internal mechanism…
How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore the geometric characteristics of contextualized word embeddings with two novel tools: (1) an identity probe that predicts the identity of a word using its embedding; (2) the minimal bounding sphere for a word's contextualized representations. Our results reveal that words of high and low frequency differ significantly with respect to their representational geo…
As the name implies, contextualized representations of language are typically motivated by their ability to encode context. Which aspects of context are captured by such representations? We introduce an approach to address this question using Representational Similarity Analysis (RSA). As case studies, we investigate the degree to which a verb embedding encodes the verb's subject, a pronoun embedding encodes the pronoun's antecedent, and a full-sentence representation encodes the sentence's head word (as determined by a dependency parse). In all cases, we show that BERT's contextualized embedd…
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument cluster…
Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in NMT. However, most approaches require parallel training data, and quality decreases as less training data is available. We propose word alignment methods that require no parallel data. The key idea is to leverage multilingual word embeddings, both static and contextualized, for word alignment. Our multilingual embeddings are created from monolingual data only…
Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in part to their structural and linguistic complexity. In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-level word representations and contextualized ELMo word representations for chemical patents. We compare word embeddings pre-trained on biomedical and chemical patent corpora. The effect of tokenizers optimized for the chemical domain on NER performance…
Humor is a natural and fundamental component of human interactions. When correctly applied, humor allows us to express thoughts and feelings conveniently and effectively, increasing interpersonal affection, likeability, and trust. However, understanding the use of humor is a computationally challenging task from the perspective of humor-aware language processing models. As language models become ubiquitous through virtual-assistants and IOT devices, the need to develop humor-aware models rises exponentially. To further improve the state-of-the-art capacity to perform this particular sentiment-…
We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCAR-based and Wikipedia-based ELMo embeddings for these languages on the part-of-speech tagging and parsing tasks. We show that, despite the noise in the Common-Crawl-based OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in taggin…
Bocconi University（博科尼大学）；University of Milan-Bicocca（米兰比可卡大学）
Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Virginia（弗吉尼亚大学）；University of Cambridge（剑桥大学）
In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo's contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female entities, (2) the trained ELMo embeddings systematically encode gender information and (3) ELMo unequally encodes gender information about male and female entities. Then, we show that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus. Finally, we explore two methods …
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin. We submitted a system based on UDPipe 2.0, one of the winners of the CoNLL 2018 Shared Task, The 2018 Shared Task on Extrinsic Parser Evaluation and SIGMORPHON 2019 Shared Task. Our system places first by a wide margin both in lemmatization and POS tagging in the open modality, where additional supervised data is allowed, in which case we utilize all Universal Dependency Latin treebanks. In the closed modality, where only the EvaLatin training data i…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）
Learning causal and temporal relationships between events is an important step towards deeper story and commonsense understanding. Though there are abundant datasets annotated with event relations for story comprehension, many have no empirical results associated with them. In this work, we establish strong baselines for event temporal relation extraction on two under-explored story narrative datasets: Richer Event Description (RED) and Causal and Temporal Relation Scheme (CaTeRS). To the best of our knowledge, these are the first results reported on these two datasets. We demonstrate that neu…
The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across languages to overcome data scarcity for low-resource languages. In this work we (i) perform a comprehensive comparison of state-ofthe-art multilingual word and sentence encoders on the tasks of named entity recognition (NER) and part of speech (POS) tagging; and (ii) propose a new method for creating multilingual contextualized word embeddings, compare it to multip…
Information Sciences Institute（信息科学研究所）；University of Southern California（南加州大学）；College of Natural Sciences（自然科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem. Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given context that share no common words with reference responses. A recent work proposed Referenced metric and Unreferenced metric Blended Evaluation Routine (RUBER) to combine a learning-based metric, which predicts relatedness between a generated response and a given query, with reference-based metric; it showed high correlation with human judgments. In this pa…
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems. However, proposed methods for incorporating pre-trained models are non-trivial and mainly focus on BERT, which lacks a comparison of the impact that other pre-trained models may have on translation performance. In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained la…
University of California Los Angeles（加州大学洛杉矶分校）；University of Southern California（南加利福尼亚大学）；University of Pennsylvania（宾夕法尼亚大学）
Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized embedding of a word changes drastically when the context is paraphrased. As a result, the downstream model is not robust to paraphrasing and other linguistic variations. To enhance the stability of contextualized word embedding models, we propose an approach to retrofitting contextualized embedding models with paraphrase contexts. Our method learns an orthogo…
University of Hamburg（汉堡大学）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；University of Mannheim（曼海姆大学）；Samsung R&D Institute Russia（三星俄罗斯研发中心）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）
We present our system for semantic frame induction that showed the best performance in Subtask B.1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (QasemiZadeh et al., 2019). Our approach separates this task into two independent steps: verb clustering using word and their context embeddings and role labeling by combining these embeddings with syntactical features. A simple combination of these steps shows very competitive results and can be extended to process other datasets and languages.
Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings have enhanced previous word embedding techniques by computing word vector representations dependent on the sentence they appear in. In this paper, we study the impact of this conceptual change in the word embedding computation in relation with gender bias. Our analysis includes different measures previously applied in the literature to standard word embeddings.…
Subjective bias detection is critical for applications like propaganda detection, content recommendation, sentiment analysis, and bias neutralization. This bias is introduced in natural language via inflammatory words and phrases, casting doubt over facts, and presupposing the truth. In this work, we perform comprehensive experiments for detecting subjective bias using BERT-based models on the Wiki Neutrality Corpus(WNC). The dataset consists of $360k$ labeled instances, from Wikipedia edits that remove various instances of the bias. We further propose BERT-based ensembles that outperform stat…
Research Center for Social Computing and Information Retrieval（社会计算与信息检索研究中心）；Harbin Institute of Technology（哈尔滨工业大学）
This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on Stanford's winning system for the CoNLL 2017 shared task and make two effective extensions: 1) incorporating deep contextualized word embeddings into both the part of speech tagger and parser; 2) ensembling parsers trained with different initialization. We also explore different ways of concatenating treebanks for further improvements. Experimental results on the development data show the effectiveness of our methods. In t…
Technische Universität Darmstadt（达姆施塔特工业大学）；University of Central Florida（中佛罗里达大学）
A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality. We validate our new metric, namely MoverScore, on a number of text generation tasks including summarization, machine translation, image captioning, and data-to-text generation, where the outputs are produced by a variety of neur…
Indian Institute of Technology (BHU)（印度理工学院（瓦拉纳西））
Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words depending on their respective context. Their advantage over static word embeddings has been shown for a number of tasks, such as text classification, sequence tagging, or machine translation. Since vectors of the same word type can vary depending on the respective context, they implicitly provide a model for word sense disambiguation (WSD). We introduce a sim…
In this paper, we investigate a new approach to Population, Intervention and Outcome (PIO) element detection, a common task in Evidence Based Medicine (EBM). The purpose of this study is two-fold: to build a training dataset for PIO element detection with minimum redundancy and ambiguity and to investigate possible options in utilizing state of the art embedding methods for the task of PIO element detection. For the former purpose, we build a new and improved dataset by investigating the shortcomings of previously released datasets. For the latter purpose, we leverage the state of the art text…
Manipal Institute of Technology（马尼帕尔理工学院）；Elsevier Labs（爱思唯尔实验室）
Biomedical Named Entity Recognition (NER) is a challenging problem in biomedical information processing due to the widespread ambiguity of out of context terms and extensive lexical variations. Performance on bioNER benchmarks continues to improve due to advances like BERT, GPT, and XLNet. FLAIR (1) is an alternative embedding model which is less computationally intensive than the others mentioned. We test FLAIR and its pretrained PubMed embeddings (which we term BioFLAIR) on a variety of bio NER tasks and compare those with results from BERT-type networks. We also investigate the effects of a…
University of California, Berkeley（加州大学伯克利分校）；Massachusetts Institute of Technology（麻省理工学院）
Understanding context-dependent variation in word meanings is a key aspect of human language comprehension supported by the lexicon. Lexicographic resources (e.g., WordNet) capture only some of this context-dependent variation; for example, they often do not encode how closely senses, or discretized word meanings, are related to one another. Our work investigates whether recent advances in NLP, specifically contextualized word embeddings, capture human-like distinctions between English word senses, such as polysemy and homonymy. We collect data from a behavioral, web-based experiment, in which…
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
We present our contribution to the SIGMORPHON 2019 Shared Task: Crosslinguality and Context in Morphology, Task 2: contextual morphological analysis and lemmatization. We submitted a modification of the UDPipe 2.0, one of best-performing systems of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies and an overall winner of the The 2018 Shared Task on Extrinsic Parser Evaluation. As our first improvement, we use the pretrained contextualized embeddings (BERT) as additional inputs to the network; secondly, we use individual morphological features as regulari…
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope. In this paper, we show that, even though some details of the picture have changed after the switch to neural networks and continuous representations, the basic trade-off between rich features and global optimization remains essentially the same. Moreover, we show that deep contextualiz…
Georgetown University（乔治城大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking. Through experiments on TREC benchmarks, we find that several existing neural ranking architectures can benefit from the additional context provided by contextualized language models. Furthermore, we propose a joint approach that incorporates BERT's classification vector…
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；BNP Paribas（法国巴黎银行）；Criteo AI Lab（科睿唯安人工智能实验室）
Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context. This is intuitively useful for generalization, especially in Named-Entity Recognition where it is crucial to detect mentions never seen during training. However, standard English benchmarks overestimate the importance of lexical over contextual features because of an unrealistic lexical overlap between train and test mentions. In this paper, we perform an empirical analysis of the generalization capabilities of state-of-the-art contextualized embeddings by separatin…
Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two …
Pivot-based neural representation models have lead to significant progress in domain adaptation for NLP. However, previous works that follow this approach utilize only labeled data from the source domain and unlabeled data from the source and target domains, but neglect to incorporate massive unlabeled corpora that are not necessarily drawn from these domains. To alleviate this, we propose PERL: A representation learning model that extends contextualized word embedding models such as BERT with pivot-based fine-tuning. PERL outperforms strong baselines across 22 sentiment classification domain …
