Statistical patterns of word frequency suggesting the probabilistic nature of human languages
Beijing Language and Culture University（北京语言大学）；Anhui Jianzhu University（安徽建筑大学）；Zhejiang University（浙江大学）；Guangdong University of Foreign Studies（广东外语外贸大学）
Traditional linguistic theories have largely regard language as a formal system composed of rigid rules. However, their failures in processing real language, the recent successes in statistical natural language processing, and the findings of many psychological experiments have suggested that language may be more a probabilistic system than a formal system, and thus cannot be faithfully modeled with the either/or rules of formal linguistic theory. The present study, based on authentic language data, confirmed that those important linguistic issues, such as linguistic universal, diachronic drift, and language variations can be translated into probability and frequency patterns in parole. These findings suggest that human language may well be probabilistic systems by nature, and that statistical may well make inherent properties of human languages.
Yik Yak, Inc.（Yik Yak公司）；Georgia Institute of Technology（佐治亚理工学院）
Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen words. We propose to improve word embeddings by incorporating morphological information, capturing shared sub-word features. Unlike previous work that constructs word embeddings directly from morphemes, we combine morphological and distributional information in a unified probabilistic framework, in which the word embedding is a latent variable. The morpholo…
We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share statistical strength across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms b…
The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn domain-specific word embeddings, from text organized into hierarchical domains, such as reviews in an e-commerce website, where products follow a taxonomy. Our structured probabilistic model allows vector representations for the same word to drift away from each other for distant domains in the taxonomy, to accommodate its domain-specific meanings. By learnin…
Indian Institute of Information Technology, Kalyani（印度信息技术学院卡利亚尼分校）
Social media has seen a worrying rise in hate speech in recent times. Branching to several distinct categories of cyberbullying, gender discrimination, or racism, the combined label for such derogatory content can be classified as toxic content in general. This paper presents experimentation with a Keras wrapped lightweight BERT model to successfully identify hate speech and predict probabilistic impact score for the same to extract the hateful words within sentences. The dataset used for this task is the Hate Speech and Offensive Content Detection (HASOC 2021) data from FIRE 2021 in English. …
We look into the task of \emph{generalizing} word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, \emph{without} extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections…
University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）
Humans can flexibly extend word usages across different grammatical classes, a phenomenon known as word class conversion. Noun-to-verb conversion, or denominal verb (e.g., to Google a cheap flight), is one of the most prevalent forms of word class conversion. However, existing natural language processing systems are impoverished in interpreting and generating novel denominal verb usages. Previous work has suggested that novel denominal verb usages are comprehensible if the listener can compute the intended meaning based on shared knowledge with the speaker. Here we explore a computational form…
National Research University Higher School of Economics（国立研究大学高等经济学院）；Lomonosov Moscow State University（莫斯科国立大学）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic embeddings with online EM-algorithm on word co-occurrence data. The resulting embeddings perform on par with Skip-Gram Negative Sampling (SGNS) on word similarity tasks and benefit in the interpretability of the components. Next, we learn probabilistic document embeddings that outperform paragraph2vec on a document similarity task and require less memory and…
This research offers a new interdisciplinary approach to the field of Linguistics by using Computational Linguistics, NLP, Bayesian Statistics and Sociolinguistics methods. This thesis investigates word order change in infinitival clauses from Object-Verb (OV) to Verb-Object (VO) in the history of Latin and Old French. By applying a variationist approach, I examine a synchronic word order variation in each stage of language change, from which I infer the character, periodization and constraints of diachronic variation. I also show that in discourse-configurational languages, such as Latin and …
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）
Probabilistic word embeddings have shown effectiveness in capturing notions of generality and entailment, but there is very little work on doing the analogous type of investigation for sentences. In this paper we define probabilistic models that produce distributions for sentences. Our best-performing model treats each word as a linear transformation operator applied to a multivariate Gaussian distribution. We train our models on paraphrases and demonstrate that they naturally capture sentence specificity. While our proposed model achieves the best performance overall, we also show that specif…
Iran University of Science & Technology（伊朗科技大学）；Ferdowsi University of Mashhad（马什哈德菲尔多西大学）；University of Girona（赫罗纳大学）；Institute of Cognitive Sciences and Technologies (ISTC), Italian National Research Council (CNR)（意大利国家研究委员会认知科学与技术研究所）；Université Paris 13 - Sorbonne Paris Cité - CNRS（巴黎第十三大学 - 索邦巴黎西岱大学 - 法国国家科学研究中心）；University of Southern California（南加州大学）
WordNet lexical-database groups English words into sets of synonyms called "synsets." Synsets are utilized for several applications in the field of text-mining. However, they were also open to criticism because although, in reality, not all the members of a synset represent the meaning of that synset with the same degree, in practice, they are considered as members of the synset, identically. Thus, the fuzzy version of synsets, called fuzzy-synsets (or fuzzy word-sense classes) were proposed and studied. In this study, we discuss why (type-1) fuzzy synsets (T1 F-synsets) do not properly model …
Masked language model and autoregressive language model are two types of language models. While pretrained masked language models such as BERT overwhelm the line of natural language understanding (NLU) tasks, autoregressive language models such as GPT are especially capable in natural language generation (NLG). In this paper, we propose a probabilistic masking scheme for the masked language model, which we call probabilistically masked language model (PMLM). We implement a specific PMLM with a uniform prior distribution on the masking ratio named u-PMLM. We prove that u-PMLM is equivalent to a…
Word embeddings have been found to capture a surprisingly rich amount of syntactic and semantic knowledge. However, it is not yet sufficiently well-understood how the relational knowledge that is implicitly encoded in word embeddings can be extracted in a reliable way. In this paper, we propose two probabilistic models to address this issue. The first model is based on the common relations-as-translations view, but is cast in a probabilistic setting. Our second model is based on the much weaker assumption that there is a linear relationship between the vector representations of related words. …
College of Information and Computer Sciences（信息与计算机科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Recent progress in language modeling has been driven not only by advances in neural architectures, but also through hardware and optimization improvements. In this paper, we revisit the neural probabilistic language model (NPLM) of~\citet{Bengio2003ANP}, which simply concatenates word embeddings within a fixed window and passes the result through a feed-forward network to predict the next word. When scaled up to modern hardware, this model (despite its many limitations) performs much better than expected on word-level language model benchmarks. Our analysis reveals that the NPLM achieves lower…
Jamia Millia Islamia（贾米亚·米利亚伊斯兰大学）；Aligarh Muslim University（阿里加尔穆斯林大学）
The conventional natural language processing approaches are not accustomed to the social media text due to colloquial discourse and non-homogeneous characteristics. Significantly, the language identification in a multilingual document is ascertained to be a preceding subtask in several information extraction applications such as information retrieval, named entity recognition, relation extraction, etc. The problem is often more challenging in code-mixed documents wherein foreign languages words are drawn into base language while framing the text. The word embeddings are powerful language model…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich semantic relations between words. Recent advances in natural language processing have shown that semantically meaningful representations of words can be efficiently acquired by distributed models, making it possible to build text representations based on a better foundation called the Bag-of-Word-Embedding (BoWE) representation. However, existing text representation methods using …
This article compares four probabilistic algorithms (global algorithms) for Word Sense Disambiguation (WSD) in terms of the number of scorer calls (local algo- rithm) and the F1 score as determined by a gold-standard scorer. Two algorithms come from the state of the art, a Simulated Annealing Algorithm (SAA) and a Genetic Algorithm (GA) as well as two algorithms that we first adapt from WSD that are state of the art probabilistic search algorithms, namely a Cuckoo search algorithm (CSA) and a Bat Search algorithm (BS). As WSD requires to evaluate exponentially many word sense combinations (wit…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Science（中国科学院大学）
Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under the reinforcement framework can mitigate the problems of the word-level loss, but its performance is unstable due to the high variance of the gradient estimation. On these grounds, we present a method with a differentiable sequence-level training objective based on probabilistic n-gram matching which can avoid the reinforcement framework. In addition, this …
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Trento（特伦托大学）
In this paper, we derive a notion of 'word meaning in context' that characterizes meaning as both intensional and conceptual. We introduce a framework for specifying local as well as global constraints on word meaning in context, together with their interactions, thus modelling the wide range of lexical shifts and ambiguities observed in utterance interpretation. We represent sentence meaning as a 'situation description system', a probabilistic model which takes utterance understanding to be the mental process of describing to oneself one or more situations that would account for an observed u…
University of California（加利福尼亚大学）；Microsoft Research（微软研究院）
Mobile devices use language models to suggest words and phrases for use in text entry. Traditional language models are based on contextual word frequency in a static corpus of text. However, certain types of phrases, when offered to writers as suggestions, may be systematically chosen more often than their frequency would predict. In this paper, we propose the task of generating suggestions that writers accept, a related but distinct task to making accurate predictions. Although this task is fundamentally interactive, we propose a counterfactual setting that permits offline training and evalua…
We introduce probabilistic embeddings using Laplacian priors (PELP). The proposed model enables incorporating graph side-information into static word embeddings. We theoretically show that the model unifies several previously proposed embedding methods under one umbrella. PELP generalises graph-enhanced, group, dynamic, and cross-lingual static word embeddings. PELP also enables any combination of these previous models in a straightforward fashion. Furthermore, we empirically show that our model matches the performance of previous models as special cases. In addition, we demonstrate its flexib…
The present paper explores a novel variant of Random Indexing (RI) based representations for encoding language data with a view to using them in a dynamic scenario where events are happening in a continuous fashion. As the size of the representations in the general method of onehot encoding grows linearly with the size of the vocabulary, they become non-scalable for online purposes with high volumes of dynamic data. On the other hand, existing pre-trained embedding models are not suitable for detecting happenings of new events due to the dynamic nature of the text data. The present work addres…
Institute of Computer Science, Polish Academy of Sciences（波兰科学院计算机科学研究所）
As we discuss, a stationary stochastic process is nonergodic when a random persistent topic can be detected in the infinite random text sampled from the process, whereas we call the process strongly nonergodic when an infinite sequence of independent random bits, called probabilistic facts, is needed to describe this topic completely. Replacing probabilistic facts with an algorithmically random sequence of bits, called algorithmic facts, we adapt this property back to ergodic processes. Subsequently, we call a process perigraphic if the number of algorithmic facts which can be inferred from a …
University of Essex（埃塞克斯大学）；University of Southampton（南安普顿大学）
Contextualised word vectors obtained via pre-trained language models encode a variety of knowledge that has already been exploited in applications. Complementary to these language models are probabilistic topic models that learn thematic patterns from the text. Recent work has demonstrated that conducting clustering on the word-level contextual representations from a language model emulates word clusters that are discovered in latent topics of words from Latent Dirichlet Allocation. The important question is how such topical word clusters are automatically formed, through clustering, in the la…
Georgia Institute of Technology（佐治亚理工学院）；Institute for the Study of Learning and Expertise（学习与专业知识研究所）
This paper presents a novel approach to the acquisition of language models from corpora. The framework builds on Cobweb, an early system for constructing taxonomic hierarchies of probabilistic concepts that used a tabular, attribute-value encoding of training cases and concepts, making it unsuitable for sequential input like language. In response, we explore three new extensions to Cobweb -- the Word, Leaf, and Path variants. These systems encode each training case as an anchor word and surrounding context words, and they store probabilistic descriptions of concepts as distributions over ancho…
Siemens AG（西门子股份公司）；University of Munich (LMU)（慕尼黑大学）
We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i.e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order by summarizing a given context as a "bag-of-word" and consequently the semantics of words in the context is lost. The LSTM-LM learns a vector-space representation of each word by accounting for word order in local collocation patterns and models complex characteristics of language (e.g., syntax and semantics), while the TM simultaneously learns a latent repre…
National and Kapodistrian University of Athens（雅典国立与卡波迪斯特里亚大学）
The term idiolect refers to the unique and distinctive use of language of an individual and it is the theoretical foundation of Authorship Attribution. In this paper we are focusing on learning distributed representations (embeddings) of social media users that reflect their writing style. These representations can be considered as stylistic fingerprints of the authors. We are exploring the performance of the two main flavours of distributed representations, namely embeddings produced by Neural Probabilistic Language models (such as word2vec) and matrix factorization (such as GloVe).
A popular approach to topic modeling involves extracting co-occurring n-grams of a corpus into semantic themes. The set of n-grams in a theme represents an underlying topic, but most topic modeling approaches are not able to label these sets of words with a single n-gram. Such labels are useful for topic identification in summarization systems. This paper introduces a novel approach to labeling a group of n-grams comprising an individual topic. The approach taken is to complement the existing topic distributions over words with a known distribution based on a predefined set of topics. This is …
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received linguistic input, robust spoken word recognition -- and language processing more generally -- relies heavily on listeners' prior knowledge to evaluate whether candidate interpretations of that input are more or less likely. Here we compare several broad-coverage probabilistic generative language models in their ability to capture human linguistic expectations. Serial reproductio…
Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dimensions for probabilistic word embeddings. Experimental results show that sensible priors can capture latent semantic concepts better than or on-par with the current state of the art, while retaining the simplicity and generalizability of using priors.
University College London（伦敦大学学院）；Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）
Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon without relying on supervision. However, current state-of-the art methods only focus on point vectors although distributional embeddings have proven to embed richer semantic information when representing words. In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings. Finally, we evaluate our method on the problem of unsupe…
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…
Semantic composition remains an open problem for vector space models of semantics. In this paper, we explain how the probabilistic graphical model used in the framework of Functional Distributional Semantics can be interpreted as a probabilistic version of model theory. Building on this, we explain how various semantic phenomena can be recast in terms of conditional probabilities in the graphical model. This connection between formal semantics and machine learning is helpful in both directions: it gives us an explicit mechanism for modelling context-dependent meanings (a challenge for formal s…
