A key principle in assessing textual similarity is measuring the degree of semantic overlap between two texts by considering the word alignment. Such alignment-based approaches are intuitive and interpretable; however, they are empirically inferior to the simple cosine similarity between general-purpose sentence vectors. To address this issue, we focus on and demonstrate the fact that the norm of word vectors is a good proxy for word importance, and their angle is a good proxy for word similarity. Alignment-based approaches do not distinguish them, whereas sentence-vector approaches automatically use the norm as the word importance. Accordingly, we propose a method that first decouples word vectors into their norm and direction, and then computes alignment-based similarity using earth mover's distance (i.e., optimal transport cost), which we refer to as word rotator's distance. Besides, we find how to grow the norm and direction of word vectors (vector converter), which is a new systematic approach derived from sentence-vector estimation methods. On several textual similarity datasets, the combination of these simple proposed methods outperformed not only alignment-based approaches but also strong baselines. The source code is available at https://github.com/eumesy/wrd
Instituto Politécnico Nacional（国家理工学院）；Instituto Caro y Cuervo（卡罗-奎尔沃研究所）
We present our systems and findings on unsupervised lexical semantic change for the Italian language in the DIACR-Ita shared-task at EVALITA 2020. The task is to determine whether a target word has evolved its meaning with time, only relying on raw-text from two time-specific datasets. We propose two models representing the target words across the periods to predict the changing words using threshold and voting schemes. Our first model solely relies on part-of-speech usage and an ensemble of distance measures. The second model uses word embedding representation to extract the neighbor's relati…
Learning word representations has garnered greater attention in the recent past due to its diverse text applications. Word embeddings encapsulate the syntactic and semantic regularities of sentences. Modelling word embedding as multi-sense gaussian mixture distributions, will additionally capture uncertainty and polysemy of words. We propose to learn the Gaussian mixture representation of words using a Kullback-Leibler (KL) divergence based objective function. The KL divergence based energy function provides a better distance metric which can effectively capture entailment and distribution sim…
Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein distance provides a natural notion of dissimilarity with probability measures and has a closed-form solution when measuring the distance between two Gaussian distributions. Therefore, with the aim of representing words in a highly efficient way, we propose to operate a Gaussian word embedding model with a loss function based on the Wasserstein distance. Also, exter…
University of Connecticut（康涅狄格大学）；University of Hawai‘i at Mānoa（夏威夷大学马诺阿分校）
Cilibrasi and Vitanyi have demonstrated that it is possible to extract the meaning of words from the world-wide web. To achieve this, they rely on the number of webpages that are found through a Google search containing a given word and they associate the page count to the probability that the word appears on a webpage. Thus, conditional probabilities allow them to correlate one word with another word's meaning. Furthermore, they have developed a similarity distance function that gauges how closely related a pair of words is. We present a specific counterexample to the triangle inequality for …
University of Southern California（南加州大学）；National University of Singapore（新加坡国立大学）
Word Mover's Distance (WMD) computes the distance between words and models text similarity with the moving cost between words in two text sequences. Yet, it does not offer good performance in sentence similarity evaluation since it does not incorporate word importance and fails to take inherent contextual and structural information in a sentence into account. An improved WMD method using the syntactic parse tree, called Syntax-aware Word Mover's Distance (SynWMD), is proposed to address these two shortcomings in this work. First, a weighted graph is built upon the word co-occurrence statistics…
University of Washington（华盛顿大学）；Nanjing University（南京大学）
It is well-understood that different algorithms, training processes, and corpora produce different word embeddings. However, less is known about the relation between different embedding spaces, i.e. how far different sets of embeddings deviate from each other. In this paper, we propose a novel metric called Relative pairwise inner Product Distance (RPD) to quantify the distance between different sets of word embeddings. This metric has a unified scale for comparing different sets of word embeddings. Based on the properties of RPD, we study the relations of word embeddings of different algorith…
Yandex（俄罗斯搜索引擎公司雅虎（注：Yandex是俄罗斯的搜索引擎公司，常见中文名是“俄罗斯搜索引擎公司雅虎”））；Higher School of Economics（高等经济学院）
The word mover's distance (WMD) is a popular semantic similarity metric for two texts. This position paper studies several possible extensions of WMD. We experiment with the frequency of words in the corpus as a weighting factor and the geometry of the word vector space. We validate possible extensions of WMD on six document classification datasets. Some proposed extensions show better results in terms of the k-nearest neighbor classification error than WMD.
Tsinghua University（清华大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Text similarity calculation is a fundamental problem in natural language processing and related fields. In recent years, deep neural networks have been developed to perform the task and high performances have been achieved. The neural networks are usually trained with labeled data in supervised learning, and creation of labeled data is usually very costly. In this short paper, we address unsupervised learning for text similarity calculation. We propose a new method called Word Embedding based Edit Distance (WED), which incorporates word embedding into edit distance. Experiments on three benchm…
Despite the increasing popularity of NLP in the humanities and social sciences, advances in model performance and complexity have been accompanied by concerns about interpretability and explanatory power for sociocultural analysis. One popular model that balances complexity and legibility is Word Mover's Distance (WMD). Ostensibly adapted for its interpretability, WMD has nonetheless been used and further developed in ways which frequently discard its most interpretable aspect: namely, the word-level distances required for translating a set of words into another set of words. To address this a…
National University（国立大学）；De La Salle University（德拉萨大学）
Assessing the proper difficulty levels of reading materials or texts in general is the first step towards effective comprehension and learning. In this study, we improve the conventional methodology of automatic readability assessment by incorporating the Word Mover's Distance (WMD) of ranked texts as an additional post-processing technique to further ground the difficulty level given by a model. Results of our experiments on three multilingual datasets in Filipino, German, and English show that the post-processing technique outperforms previous vanilla and ranking-based models using SVM.
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 focus on the task of unsupervised lemmatization, i.e. grouping together inflected forms of one word under one label (a lemma) without the use of annotated training data. We propose to perform agglomerative clustering of word forms with a novel distance measure. Our distance measure is based on the observation that inflections of the same word tend to be similar both string-wise and in meaning. We therefore combine word embedding cosine similarity, serving as a proxy to the meaning similarity, with Jaro-Winkler edit distance. Our experiments on 23 languages show our approach to be promising,…
The distances between words calculated in word units are studied and compared with the distributions of the Random Matrix Theory (RMT). It is found that the distribution of distance between the same words can be well described by the single-parameter Brody distribution. Using the Brody distribution fit, we found that the distance between given words in a set of texts can show mixed dynamics, coexisting regular and chaotic regimes. It is found that distributions correctly fitted by the Brody distribution with a certain goodness of the fit threshold can be identifid as stop words, usually consid…
University of Oslo（奥斯陆大学）；University of Hamburg（汉堡大学）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph em…
Mohammad Ali Jinnah University（穆罕默德·阿里·真纳大学）；FAST NUCES（巴基斯坦国家计算机与新兴科学大学）
Lexical Similarity (LS) between two languages uncovers many interesting linguistic insights such as genetic relationship, mutual intelligibility, and the usage of one's vocabulary into other. There are various methods through which LS is evaluated. In the same regard, this paper presents a method of Phonetic Edit Distance (PED) that uses a soft comparison of letters using the articulatory features associated with them. The system converts the words into the corresponding International Phonetic Alphabet (IPA), followed by the conversion of IPA into its set of articulatory features. Later, the l…
University of Southern California（南加州大学）；University of Utah（犹他大学）；University of Washington（华盛顿大学）
Linguistic coordination is a well-established phenomenon in spoken conversations and often associated with positive social behaviors and outcomes. While there have been many attempts to measure lexical coordination or entrainment in literature, only a few have explored coordination in syntactic or semantic space. In this work, we attempt to combine these different aspects of coordination into a single measure by leveraging distances in a neural word representation space. In particular, we adopt the recently proposed Word Mover's Distance with word2vec embeddings and extend it to measure the di…
We introduce a new measure of distance between languages based on word embedding, called word embedding language divergence (WELD). WELD is defined as divergence between unified similarity distribution of words between languages. Using such a measure, we perform language comparison for fifty natural languages and twelve genetic languages. Our natural language dataset is a collection of sentence-aligned parallel corpora from bible translations for fifty languages spanning a variety of language families. Although we use parallel corpora, which guarantees having the same content in all languages,…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；IBM Research（IBM研究院）
Recent work has explored methods for learning continuous vector space word representations reflecting the underlying semantics of words. Simple vector space arithmetic using cosine distances has been shown to capture certain types of analogies, such as reasoning about plurals from singulars, past tense from present tense, etc. In this paper, we introduce a new approach to capture analogies in continuous word representations, based on modeling not just individual word vectors, but rather the subspaces spanned by groups of words. We exploit the property that the set of subspaces in n-dimensional…
Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical inconsistencies and spelling variations in addition to all the previous known challenges for social media scenarios. In this article, we present a novel architecture focusing on normalizing phonetic typing variations, which is commonly seen in code-mixed data. One of the main features of our architecture is that in addition to normalizing, it can also be utiliz…
The Word Mover's Distance (WMD) proposed by Kusner et al. is a distance between documents that takes advantage of semantic relations among words that are captured by their embeddings. This distance proved to be quite effective, obtaining state-of-art error rates for classification tasks, but is also impracticable for large collections/documents due to its computational complexity. For circumventing this problem, variants of WMD have been proposed. Among them, Relaxed Word Mover's Distance (RWMD) is one of the most successful due to its simplicity, effectiveness, and also because of its fast im…
Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the same time, it has been argued that contextualized word representations exhibit sub-optimal statistical properties for encoding the true similarity between words or sentences. In this paper, we present two techniques for improving encoding representations for similarity metrics: a batch-mean centering strategy that improves statistical properties; and a comp…
Idiap Research Institute（Idiap研究所）；Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Recent works on word representations mostly rely on predictive models. Distributed word representations (aka word embeddings) are trained to optimally predict the contexts in which the corresponding words tend to appear. Such models have succeeded in capturing word similarties as well as semantic and syntactic regularities. Instead, we aim at reviving interest in a model based on counts. We present a systematic study of the use of the Hellinger distance to extract semantic representations from the word co-occurence statistics of large text corpora. We show that this distance gives good perform…
Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；PolyAI（PolyAI公司）
We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation. By injecting external linguistic constraints (e.g., WordNet links) into the initial vector space, the LE specialisation procedure brings true hyponymy-hypernymy pairs closer together in the transformed Euclidean space. The proposed asymmetric distance measure adjusts the norms of word vectors to reflect the actual WordNet-style hierarchy of concepts. …
There is a great deal of work in cognitive psychology, linguistics, and computer science, about using word (or phrase) frequencies in context in text corpora to develop measures for word similarity or word association, going back to at least the 1960s. The goal of this chapter is to introduce the normalizedis a general way to tap the amorphous low-grade knowledge available for free on the Internet, typed in by local users aiming at personal gratification of diverse objectives, and yet globally achieving what is effectively the largest semantic electronic database in the world. Moreover, this d…
Requirements elicitation has recently been complemented with crowd-based techniques, which continuously involve large, heterogeneous groups of users who express their feedback through a variety of media. Crowd-based elicitation has great potential for engaging with (potential) users early on but also results in large sets of raw and unstructured feedback. Consolidating and analyzing this feedback is a key challenge for turning it into sensible user requirements. In this paper, we focus on topic modeling as a means to identify topics within a large set of crowd-generated user stories and compar…
The word mover's distance (WMD) is a fundamental technique for measuring the similarity of two documents. As the crux of WMD, it can take advantage of the underlying geometry of the word space by employing an optimal transport formulation. The original study on WMD reported that WMD outperforms classical baselines such as bag-of-words (BOW) and TF-IDF by significant margins in various datasets. In this paper, we point out that the evaluation in the original study could be misleading. We re-evaluate the performances of WMD and the classical baselines and find that the classical baselines are co…
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…
Lacking standardized extrinsic evaluation methods for vector representations of words, the NLP community has relied heavily on word similarity tasks as a proxy for intrinsic evaluation of word vectors. Word similarity evaluation, which correlates the distance between vectors and human judgments of semantic similarity is attractive, because it is computationally inexpensive and fast. In this paper we present several problems associated with the evaluation of word vectors on word similarity datasets, and summarize existing solutions. Our study suggests that the use of word similarity tasks for e…
Word embeddings are high dimensional vector representations of words that capture their semantic similarity in the vector space. There exist several algorithms for learning such embeddings both for a single language as well as for several languages jointly. In this work we propose to evaluate collections of embeddings by adapting downstream natural language tasks to the optimal transport framework. We show how the family of Wasserstein distances can be used to solve cross-lingual document retrieval and the cross-lingual document classification problems. We argue on the advantages of this appro…
We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they vary across the word embedding space. This demonstrates that the underlying maps are non-linear. Importantly, we show that the locally linear maps vary by an amount that is tightly correlated with the distance between the neighborhoods on which they are trained. Our results can be used to test non-linear methods, and to drive the design of more accurate map…
Several variants of deep neural networks have been successfully employed for building parametric models that project variable-duration spoken word segments onto fixed-size vector representations, or acoustic word embeddings (AWEs). However, it remains unclear to what degree we can rely on the distance in the emerging AWE space as an estimate of word-form similarity. In this paper, we ask: does the distance in the acoustic embedding space correlate with phonological dissimilarity? To answer this question, we empirically investigate the performance of supervised approaches for AWEs with differen…
Department of Computer Science Brunel University London（伦敦布鲁内尔大学计算机科学系）
This research project aimed to overcome the challenge of analysing human language relationships, facilitate the grouping of languages and formation of genealogical relationship between them by developing automated comparison techniques. Techniques were based on the phonetic representation of certain key words and concept. Example word sets included numbers 1-10 (curated), large database of numbers 1-10 and sheep counting numbers 1-10 (other sources), colours (curated), basic words (curated). To enable comparison within the sets the measure of Edit distance was calculated based on Levenshtein d…
Beijing Institute of Technology（北京理工大学）；Singapore University of Technology and Design（新加坡科技设计大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Dependency parse trees are helpful for discovering the opinion words in aspect-based sentiment analysis (ABSA). However, the trees obtained from off-the-shelf dependency parsers are static, and could be sub-optimal in ABSA. This is because the syntactic trees are not designed for capturing the interactions between opinion words and aspect words. In this work, we aim to shorten the distance between aspects and corresponding opinion words by learning an aspect-centric tree structure. The aspect and opinion words are expected to be closer along such tree structure compared to the standard depende…
Swap distance minimization shapes the order of subject, object and verb in languages of the world
Quantitative, Mathematical and Computational Linguistics Research Group, Department of Computer Science, Universitat Politècnica de Catalunya（量化、数学与计算语言学研究组，计算机科学系，巴塞罗那理工大学）
Extracting Spooky-activation-at-a-distance from Considerations of Entanglement
Queensland University of Technology（昆士兰科技大学）；University of South Florida（南佛罗里达大学）
Nelson & McEhran \cite{Nelson:McEvoy:2007}早期的一项声明表明，单词联想可以显示出“幽灵般的超距作用行为”，目前正在对这种联想的潜在量子性质进行认真的调查。本文提出了一个词联想系统的简单量子模型。它表明，字纠缠的量子模型可以恢复方面的扩散激活方程和幽灵激活在一个距离方程，这两个都是用来模拟激活水平的话在人类记忆。
Università di Roma "La Sapienza"（罗马大学（罗马第一大学））；Università dell’Aquila（拉奎拉大学）
The idea of measuring distance between languages seems to have its roots in the work of the French explorer Dumont D'Urville \cite{Urv}. He collected comparative words lists of various languages during his voyages aboard the Astrolabe from 1826 to 1829 and, in his work about the geographical division of the Pacific, he proposed a method to measure the degree of relation among languages. The method used by modern glottochronology, developed by Morris Swadesh in the 1950s, measures distances from the percentage of shared cognates, which are words with a common historical origin. Recently, we pro…
Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into fixed-dimensional vectors in a shared latent space; such that the distance between two word vectors represents how closely the two words sound. Instead of directly learning the distances between word vectors, we employ weak supervision and model a binary classification task to predict whether two inputs, one of each modality, represent the same word given a distance…
Università la Sapienza（罗马智慧大学）；Università dell'Aquila（拉奎拉大学）
The idea of measuring distance between languages seems to have its roots in the work of the French explorer Dumont D'Urville (D'Urville 1832). He collected comparative words lists of various languages during his voyages aboard the Astrolabe from 1826 to1829 and, in his work about the geographical division of the Pacific, he proposed a method to measure the degree of relation among languages. The method used by modern glottochronology, developed by Morris Swadesh in the 1950s (Swadesh 1952), measures distances from the percentage of shared cognates, which are words with a common historical orig…
Infinia ML, Inc.（Infinia ML公司）；Duke University（杜克大学）；Tencent AI Lab（腾讯人工智能实验室）
We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the underlying distance in the Wasserstein topic model. The word distributions of topics, their optimal transports to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the co…
How to measure the optimality of word or gesture order with respect to the principle of swap distance minimization
Computational Linguistics Research Group (LQMC) Departament de Ci\`encies de la Computaci\'o Universitat Polit\`ecnica de Catalunya Campus Nord, Edifici Omega Jordi Girona Salgado 1-3 08034 Barcelona, Catalonia, Spain
Nearest neighbors in word embedding models are commonly observed to be semantically similar, but the relations between them can vary greatly. We investigate the extent to which word embedding models preserve syntactic interchangeability, as reflected by distances between word vectors, and the effect of hyper-parameters---context window size in particular. We use part of speech (POS) as a proxy for syntactic interchangeability, as generally speaking, words with the same POS are syntactically valid in the same contexts. We also investigate the relationship between interchangeability and similari…
University of Oslo（奥斯陆大学）；Universität Hamburg（汉堡大学）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
The computation of distance measures between nodes in graphs is inefficient and does not scale to large graphs. We explore dense vector representations as an effective way to approximate the same information: we introduce a simple yet efficient and effective approach for learning graph embeddings. Instead of directly operating on the graph structure, our method takes structural measures of pairwise node similarities into account and learns dense node representations reflecting user-defined graph distance measures, such as e.g.the shortest path distance or distance measures that take informatio…
The idea that the distance among pairs of languages can be evaluated from lexical differences seems to have its roots in the work of the French explorer Dumont D'Urville. He collected comparative words lists of various languages during his voyages aboard the Astrolabe from 1826 to 1829 and, in his work about the geographical division of the Pacific, he proposed a method to measure the degree of relation between languages. The method used by the modern lexicostatistics, developed by Morris Swadesh in the 1950s, measures distances from the percentage of shared cognates, which are words with a co…
Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools. Current state-of-the-art methods, however, involve multiple steps, including heuristic post-hoc refinement strategies. In this paper, we cast the correspondence problem directly as an optimal transport (OT) problem, building on the idea that word embeddings arise from metric recovery algorithms. Indeed, we exploit the Gromov-Wasserstein distance that measures …
In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances. Furthermore, we propose two new document distance measures, word vector-based Dynamic Time Warping (wDTW) and word vector-based Tree Edit Distance (wTED). Our revision detection system is designed for a large scale corpus and implemented in Apache Spark. We demonstrate that our system can more precisely detect revisions than state-of-the-art methods by utilizing the Wikipedia revision dumps https://snap.stanford.edu/data/wiki-meta.html and simulated d…
Yandex；National Research University Higher School of Economics（俄罗斯国立高等经济研究大学）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）
It has become a de-facto standard to represent words as elements of a vector space (word2vec, GloVe). While this approach is convenient, it is unnatural for language: words form a graph with a latent hierarchical structure, and this structure has to be revealed and encoded by word embeddings. We introduce GraphGlove: unsupervised graph word representations which are learned end-to-end. In our setting, each word is a node in a weighted graph and the distance between words is the shortest path distance between the corresponding nodes. We adopt a recent method learning a representation of data in…
Kapital Bank（卡皮塔尔银行）；Khazar University（哈扎尔大学）；Lumos Extension School of Data（Lumos数据扩展学校）
Spell correction is used to detect and correct orthographic mistakes in texts. Most of the time, traditional dictionary lookup with string similarity methods is suitable for the languages that have a less complex structure such as the English language. However, the Azerbaijani language has a more complex structure and due to its morphological structure, the derivation of words is plenty that several words are derived from adding suffices, affixes to the words. Therefore, in this paper sequence to sequence model with an attention mechanism is used to develop spelling correction for Azerbaijani.…
