This introduction aims to tell the story of how we put words into computers. It is part of the story of the field of natural language processing (NLP), a branch of artificial intelligence. It targets a wide audience with a basic understanding of computer programming, but avoids a detailed mathematical treatment, and it does not present any algorithms. It also does not focus on any particular application of NLP such as translation, question answering, or information extraction. The ideas presented here were developed by many researchers over many decades, so the citations are not exhaustive but rather direct the reader to a handful of papers that are, in the author's view, seminal. After reading this document, you should have a general understanding of word vectors (also known as word embeddings): why they exist, what problems they solve, where they come from, how they have changed over time, and what some of the open questions about them are. Readers already familiar with word vectors are advised to skip to Section 5 for the discussion of the most recent advance, contextual word vectors.
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…
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…
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…
Ohio State University（俄亥俄州立大学）；Alt Inc（Alt公司）；University of Liverpool（利物浦大学）；Nagoya University（名古屋大学）；Riken AIP（理化学研究所先进智能项目中心）
Fine-Grained Named Entity Recognition (FG-NER) is critical for many NLP applications. While classical named entity recognition (NER) has attracted a substantial amount of research, FG-NER is still an open research domain. The current state-of-the-art (SOTA) model for FG-NER relies heavily on manual efforts for building a dictionary and designing hand-crafted features. The end-to-end framework which achieved the SOTA result for NER did not get the competitive result compared to SOTA model for FG-NER. In this paper, we investigate how effective multi-task learning approaches are in an end-to-end…
BlackRock（贝莱德）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention detection (MD) and entity disambiguation (ED) easily possible. Our model is based on BERT and produces contextualized word embeddings which are trained against a joint MD and ED objective. We achieve state-of-the-art results on several standard entity linking (EL) datasets.
The clinical named entity recognition (CNER) task seeks to locate and classify clinical terminologies into predefined categories, such as diagnostic procedure, disease disorder, severity, medication, medication dosage, and sign symptom. CNER facilitates the study of side-effect on medications including identification of novel phenomena and human-focused information extraction. Existing approaches in extracting the entities of interests focus on using static word embeddings to represent each word. However, one word can have different interpretations that depend on the context of the sentences. …
In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far o…
University College London（伦敦大学学院）；Alan Turing Institute（艾伦·图灵研究所）
Linear chain conditional random fields (CRFs) combined with contextual word embeddings have achieved state of the art performance on sequence labeling tasks. In many of these tasks, the identity of the neighboring words is often the most useful contextual information when predicting the label of a given word. However, contextual embeddings are usually trained in a task-agnostic manner. This means that although they may encode information about the neighboring words, it is not guaranteed. It can therefore be beneficial to design the sequence labeling architecture to directly extract this inform…
Studio Ousia；RIKEN AIP（理化学研究所先进智能项目中心）；University of Washington（华盛顿大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；National Institute of Informatics（国立情报学研究所）
Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware…
Contextual word embedding models, such as BioBERT and Bio_ClinicalBERT, have achieved state-of-the-art results in biomedical natural language processing tasks by focusing their pre-training process on domain-specific corpora. However, such models do not take into consideration expert domain knowledge. In this work, we introduced UmlsBERT, a contextual embedding model that integrates domain knowledge during the pre-training process via a novel knowledge augmentation strategy. More specifically, the augmentation on UmlsBERT with the Unified Medical Language System (UMLS) Metathesaurus was perfor…
Recent progress in neural information retrieval has demonstrated large gains in effectiveness, while often sacrificing the efficiency and interpretability of the neural model compared to classical approaches. This paper proposes ColBERTer, a neural retrieval model using contextualized late interaction (ColBERT) with enhanced reduction. Along the effectiveness Pareto frontier, ColBERTer's reductions dramatically lower ColBERT's storage requirements while simultaneously improving the interpretability of its token-matching scores. To this end, ColBERTer fuses single-vector retrieval, multi-vector…
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 …
Recent work in cross-lingual contextual word embedding learning cannot handle multi-sense words well. In this work, we explore the characteristics of contextual word embeddings and show the link between contextual word embeddings and word senses. We propose two improving solutions by considering contextual multi-sense word embeddings as noise (removal) and by generating cluster level average anchor embeddings for contextual multi-sense word embeddings (replacement). Experiments show that our solutions can improve the supervised contextual word embeddings alignment for multi-sense words in a mi…
Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering, named entity recognition, and sentiment analysis. However, evaluation on word sense disambiguation (WSD) in prior work shows that using contextualized word representations does not outperform the state-of-the-art approach that makes use of non-contextualized word embeddings. In this paper, we explore different strategies of integrating pre-trained contextualiz…
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…
In recent years, after the neural-network-based method was proposed, the accuracy of the Chinese word segmentation task has made great progress. However, when dealing with out-of-vocabulary words, there is still a large error rate. We used a simple bidirectional LSTM architecture and a large-scale pretrained language model to generate high-quality contextualize character representations, which successfully reduced the weakness of the ambiguous meanings of each Chinese character that widely appears in Chinese characters, and hence effectively reduced OOV error rate. State-of-the-art performance…
Contextualized word representations have proven useful for various natural language processing tasks. However, it remains unclear to what extent these representations can cover hand-coded semantic information such as semantic frames, which specify the semantic role of the arguments associated with a predicate. In this paper, we focus on verbs that evoke different frames depending on the context, and we investigate how well contextualized word representations can recognize the difference of frames that the same verb evokes. We also explore which types of representation are suitable for semantic…
University of Liverpool（利物浦大学）；Department of Computer Science（计算机科学系）；University of Liverpool, UK（英国利物浦大学）
Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context. On the other hand, static word embeddings such as GloVe represent words by relatively low-dimensional, memory- and compute-efficient vectors but are not sensitive to the different senses of the word. We propose Context Derived Embeddings of Senses (CDES), a method that extracts sense related information from contextualised embeddings and injects it into static embeddings to create sense-specific static emb…
Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of contextualization, i.e., how well words are interpreted in context, by studying the extent to which semantic classes of a word can be inferred from its contextualized embeddings. Quantifying contextualization helps in understanding and utilizing pretrained language models. We show that top layer representations achieve high accuracy inferring semantic class…
When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment. Massively pretrained language models like BERT can encode not only just the words in a document but also the context around the words along with them. This begs the questions, "Does a pretrain language model also automatically encode sentiment information about each word?" and "Can it be used to infer polarity towards different aspects?". In this work we try to answer this question by showing that training a comparison of a contextual embedding from BERT and a …
Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment
Konan University（甲南大学）；National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）；Tokyo University of Foreign Studies（东京外国语大学）；University of Tokyo（东京大学）
Hebrew University of Jerusalem（希伯来大学）；University of Utah（犹他大学）；Georgetown University（乔治城大学）
We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses. By inducing a contextualized "pseudoword" as a stand-in for a static embedding in the input layer, and then performing masked prediction of a word in the sentence, we are able to investigate the geometry of the BERT-space in a controlled manner around individual instances. Using our method on a set of carefully constructed sentences targeting ambiguous English words, we find substantial regularity in…
This paper introduces the first dataset for evaluating English-Chinese Bilingual Contextual Word Similarity, namely BCWS (https://github.com/MiuLab/BCWS). The dataset consists of 2,091 English-Chinese word pairs with the corresponding sentential contexts and their similarity scores annotated by the human. Our annotated dataset has higher consistency compared to other similar datasets. We establish several baselines for the bilingual embedding task to benchmark the experiments. Modeling cross-lingual sense representations as provided in this dataset has the potential of moving artificial intell…
Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and is typically through learning linear projections to align monolingual word representation spaces. Two classes of word representations have been explored for BLI: static word embeddings and contextual representations, but there is no studies to combine both. In this paper, we propose a simple yet effective mechanism to combine the static word embeddings and the contextual representations to utilize the advantages of both paradigms. We test the combination mechanism on various language pairs…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Cornell University（康奈尔大学）
Clustering token-level contextualized word representations produces output that shares many similarities with topic models for English text collections. Unlike clusterings of vocabulary-level word embeddings, the resulting models more naturally capture polysemy and can be used as a way of organizing documents. We evaluate token clusterings trained from several different output layers of popular contextualized language models. We find that BERT and GPT-2 produce high quality clusterings, but RoBERTa does not. These cluster models are simple, reliable, and can perform as well as, if not better t…
Boston University（波士顿大学）；Philips Research North America（飞利浦北美研究院）
Automatic extraction of clinical concepts is an essential step for turning the unstructured data within a clinical note into structured and actionable information. In this work, we propose a clinical concept extraction model for automatic annotation of clinical problems, treatments, and tests in clinical notes utilizing domain-specific contextual word embedding. A contextual word embedding model is first trained on a corpus with a mixture of clinical reports and relevant Wikipedia pages in the clinical domain. Next, a bidirectional LSTM-CRF model is trained for clinical concept extraction usin…
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…
One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contex…
Reading a document and extracting an answer to a question about its content has attracted substantial attention recently. While most work has focused on the interaction between the question and the document, in this work we evaluate the importance of context when the question and document are processed independently. We take a standard neural architecture for this task, and show that by providing rich contextualized word representations from a large pre-trained language model as well as allowing the model to choose between context-dependent and context-independent word representations, we can …
We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide a unique lens for investigating properties of embeddings. Using the Paraphrase Database's alignments, we study words within paraphrases as well as phrase representations. We find that contextual embeddings effectively handle polysemous words, but give synonyms surprisingly different representations in many cases. We confirm previous findings that BERT is sensitive to word order, but find slig…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why these models are so effective. In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g. LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned. We show there is a tradeoff between speed and accuracy, but all architectures…
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…
Detecting lexical semantic change in smaller data sets, e.g. in historical linguistics and digital humanities, is challenging due to a lack of statistical power. This issue is exacerbated by non-contextual embedding models that produce one embedding per word and, therefore, mask the variability present in the data. In this article, we propose an approach to estimate semantic shift by combining contextual word embeddings with permutation-based statistical tests. We use the false discovery rate procedure to address the large number of hypothesis tests being conducted simultaneously. We demonstra…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Irvine（加州大学欧文分校）；University of Washington（华盛顿大学）
Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to embed multiple knowledge bases (KBs) into large scale models, and thereby enhance their representations with structured, human-curated knowledge. For each KB, we first use an integrated entity linker to retrieve relevant entity embeddings, then update contextual word representations via a form of word-to-entity attention. In contrast to previous approaches, the…
Bucharest University of Economic Studies（布加勒斯特经济研究大学）；Erasmus University Rotterdam（鹿特丹伊拉斯姆斯大学）
The Web has become the main platform where people express their opinions about entities of interest and their associated aspects. Aspect-Based Sentiment Analysis (ABSA) aims to automatically compute the sentiment towards these aspects from opinionated text. In this paper we extend the state-of-the-art Hybrid Approach for Aspect-Based Sentiment Analysis (HAABSA) method in two directions. First we replace the non-contextual word embeddings with deep contextual word embeddings in order to better cope with the word semantics in a given text. Second, we use hierarchical attention by adding an extra…
University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Sun Yat-sen University（中山大学）；Microsoft Research Asia（微软亚洲研究院）
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a langua…
Black-box probing models can reliably extract linguistic features like tense, number, and syntactic role from pretrained word representations. However, the manner in which these features are encoded in representations remains poorly understood. We present a systematic study of the linear geometry of contextualized word representations in ELMO and BERT. We show that a variety of linguistic features (including structured dependency relationships) are encoded in low-dimensional subspaces. We then refine this geometric picture, showing that there are hierarchical relations between the subspaces en…
While contextualized word representations have improved state-of-the-art benchmarks in many NLP tasks, their potential usefulness for social-oriented tasks remains largely unexplored. We show how contextualized word embeddings can be used to capture affect dimensions in portrayals of people. We evaluate our methodology quantitatively, on held-out affect lexicons, and qualitatively, through case examples. We find that contextualized word representations do encode meaningful affect information, but they are heavily biased towards their training data, which limits their usefulness to in-domain an…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and…
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…
Unsupervised vector representations of sentences or documents are a major building block for many language tasks such as sentiment classification. However, current methods are uninterpretable and slow or require large training datasets. Recent word vector-based proposals implicitly assume that distances in a word embedding space are equally important, regardless of context. We introduce contextual salience (CoSal), a measure of word importance that uses the distribution of context vectors to normalize distances and weights. CoSal relies on the insight that unusual word vectors disproportionate…
Google AI Language；Johns Hopkins University（约翰斯·霍普金斯大学）；Swarthmore College（斯沃斯莫尔学院）；New York University（纽约大学）；Brown University（布朗大学）
Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that ex…
The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less relevant words could be in the context window, hindering the SG model from learning a better quality representation. In this paper, we propose an enhanced version of the SG that leverages context information to produce word representation. The proposed model, Contextual Skip-gram, is designed to predict contextual words with both the center words and the con…
A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural architecture to model syntactically and semantically adequate contextualized representations of varying length spoken words. The use of such representations can not only lead to great advances in the audio-based NLP tasks but can also curtail the loss of information like tone, expression, accent, etc while converting speech to text to perform these tasks. T…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Utrecht University（乌得勒支大学）
Defining words in a textual context is a useful task both for practical purposes and for gaining insight into distributed word representations. Building on the distributional hypothesis, we argue here that the most natural formalization of definition modeling is to treat it as a sequence-to-sequence task, rather than a word-to-sequence task: given an input sequence with a highlighted word, generate a contextually appropriate definition for it. We implement this approach in a Transformer-based sequence-to-sequence model. Our proposal allows to train contextualization and definition generation i…
In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the contextually relevant information is not trivial. We investigate how an LSTM language model deals with lexical ambiguity in English, designing a method to probe its hidden representations for lexical and contextual information about words. We find that both types of information are represented to a large extent, but also that there is room for improvement for contextua…
Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case …
University of Innsbruck（因斯布鲁克大学）；The University of Tokyo（东京大学）
Predicting context-dependent and non-literal utterances like sarcastic and ironic expressions still remains a challenging task in NLP, as it goes beyond linguistic patterns, encompassing common sense and shared knowledge as crucial components. To capture complex morpho-syntactic features that can usually serve as indicators for irony or sarcasm across dynamic contexts, we propose a model that uses character-level vector representations of words, based on ELMo. We test our model on 7 different datasets derived from 3 different data sources, providing state-of-the-art performance in 6 of them, a…
Inferring the probability distribution of sentences or word sequences is a key process in natural language processing. While word-level language models (LMs) have been widely adopted for computing the joint probabilities of word sequences, they have difficulty in capturing a context long enough for sentence probability estimation (SPE). To overcome this, recent studies introduced training methods using sentence-level noise-contrastive estimation (NCE) with recurrent neural networks (RNNs). In this work, we attempt to extend it for contextual SPE, which aims to estimate a conditional sentence p…
Graduate School of Engineering（工学研究生院）；The University of Tokyo（东京大学）
In this paper we describe our system designed for the WASSA 2018 Implicit Emotion Shared Task (IEST), which obtained 2$^{\text{nd}}$ place out of 26 teams with a test macro F1 score of $0.710$. The system is composed of a single pre-trained ELMo layer for encoding words, a Bidirectional Long-Short Memory Network BiLSTM for enriching word representations with context, a max-pooling operation for creating sentence representations from said word vectors, and a Dense Layer for projecting the sentence representations into label space. Our official submission was obtained by ensembling 6 of these mo…
Given a specific discourse, which discourse properties trigger the use of metaphorical language, rather than using literal alternatives? For example, what drives people to say "grasp the meaning" rather than "understand the meaning" within a specific context? Many NLP approaches to metaphorical language rely on cognitive and (psycho-)linguistic insights and have successfully defined models of discourse coherence, abstractness and affect. In this work, we build five simple models relying on established cognitive and linguistic properties -- frequency, abstractness, affect, discourse coherence a…
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…
