Artificial neural networks are a state-of-the-art solution for many problems in natural language processing. What can we learn about language and meaning from the way artificial neural networks represent it? Word representations obtained from the Skip-gram variant of the word2vec model exhibit interesting semantic properties. This is usually explained by referring to the general distributional hypothesis, which states that the meaning of the word is given by the contexts where it occurs. We propose a more specific approach based on Frege's holistic and functional approach to meaning. Taking Tugendhat's formal reinterpretation of Frege's work as a starting point, we demonstrate that it is analogical to the process of training the Skip-gram model and offers a possible explanation of its semantic properties.
Center for Security and Emerging Technology（安全与新兴技术中心）；Georgetown University（乔治城大学）
This work presents a large-scale analysis of artificial intelligence (AI) and machine learning (ML) references within news articles and scientific publications between 2011 and 2019. We implement word association measurements that automatically identify shifts in language co-occurring with AI/ML and quantify the strength of these word associations. Our results highlight the evolution of perceptions and definitions around AI/ML and detect emerging application areas, models, and systems (e.g., blockchain and cybersecurity). Recent small-scale, manual studies have explored AI/ML discourse within …
Kohli Center On Intelligent Systems (KCIS)（科利智能系统中心）；International Institute of Information Technology Hyderabad (IIIT-H)（海得拉巴国际信息技术学院）
We present a language independent, unsupervised method for building word embeddings using morphological expansion of text. Our model handles the problem of data sparsity and yields improved word embeddings by relying on training word embeddings on artificially generated sentences. We evaluate our method using small sized training sets on eleven test sets for the word similarity task across seven languages. Further, for English, we evaluated the impacts of our approach using a large training set on three standard test sets. Our method improved results across all languages.
The ambition of a character recognition system is to transform a text document typed on paper into a digital format that can be manipulated by word processor software Unlike other languages, Arabic has unique features, while other language doesn't have, from this language these are seven or eight language such as ordo, jewie and Persian writing, Arabic has twenty eight letters, each of which can be linked in three different ways or separated depending on the case. The difficulty of the Arabic handwriting recognition is that, the accuracy of the character recognition which affects on the accura…
Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-person actors in partially-observable worlds. To achieve this so-called grounded language learning, models must overcome challenges that infants face when learning their first words. While it is notable that models with no meaningful prior knowledge overcome these obstacles, researchers currently lack a clear understanding of how they do so, a problem that we attempt to address in this paper. For maximum control and …
Natural languages are complexly structured entities. They exhibit characterising regularities that can be exploited to link them one another. In this work, I compare two morphological aspects of languages: Written Patterns and Sentence Structure. I show how languages spontaneously group by similarity in both analyses and derive an average language distance. Finally, exploiting Sentence Structure I developed an Artificial Neural Network capable of distinguishing languages suggesting that not only word roots but also grammatical sentence structure is a characterising trait which alone suffice to…
Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to the same meaning, namely pseudo multi-sense. In this paper, we introduce the concept of pseudo multi-sense, and then propose an algorithm to detect such cases. With the consideration of the detected pseudo multi-sense cases, we try to refine the existing word embeddings to eliminate the influence of pseudo multi-sense. Moreover, we apply our algorithm on pr…
We demonstrate that large texts, representing human (English, Russian, Ukrainian) and artificial (C++, Java) languages, display quantitative patterns characterized by the Benford-like and Zipf laws. The frequency of a word following the Zipf law is inversely proportional to its rank, whereas the total numbers of a certain word appearing in the text generate the uneven Benford-like distribution of leading numbers. Excluding the most popular words essentially improves the correlation of actual textual data with the Zipfian distribution, whereas the Benford distribution of leading numbers (arisin…
The University of Liverpool（利物浦大学）；National Institute of Informatics（国立信息学研究所）；Preferred Infrastructure, Inc.（Preferred Infrastructure公司）
Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes in common, they are connected by some semantic relations. On the other hand, if there are numerous semantic relations between two words, we can expect some of the attributes of one of the words to be inherited by the other. Motivated by this close connection between attributes and relations, given a relational graph in which words are inter- connected via nu…
Lab Dynamics of Language UMR 5596（语言动力学实验室 UMR 5596）；University Lyon 2（里昂第二大学）；Uppsala University（乌普萨拉大学）
We analyze the information provided by the word embeddings about the grammatical gender in Swedish. We wish that this paper may serve as one of the bridges to connect the methods of computational linguistics and general linguistics. Taking nominal classification in Swedish as a case study, we first show how the information about grammatical gender in language can be captured by word embedding models and artificial neural networks. Then, we match our results with previous linguistic hypotheses on assignment and usage of grammatical gender in Swedish and analyze the errors made by the computatio…
Neural networks trained on natural language processing tasks capture syntax even though it is not provided as a supervision signal. This indicates that syntactic analysis is essential to the understating of language in artificial intelligence systems. This overview paper covers approaches of evaluating the amount of syntactic information included in the representations of words for different neural network architectures. We mainly summarize re-search on English monolingual data on language modeling tasks and multilingual data for neural machine translation systems and multilingual language mod…
We present a comparison of two english texts, written by Lewis Carroll, one (Alice in wonderland) and the other (Through a looking glass), the former translated into esperanto, in order to observe whether natural and artificial languages significantly differ from each other. We construct one dimensional time series like signals using either word lengths or word frequencies. We use the multifractal ideas for sorting out correlations in the writings. In order to check the robustness of the methods we also write the corresponding shuffled texts. We compare characteristic functions and e.g. observ…
University of Cambridge（剑桥大学）；ETH Zürich（苏黎世联邦理工学院）
Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases has proved complicated due to the many variables that appear in the experimental setup. Languages vary in many typological dimensions, and it is difficult to single out one or two to investigate without the others acting as confounders. We propose a novel method for investigating the inductive biases of language models using artificial languages. These lang…
Université de Montréal（蒙特利尔大学）；Université d’Ottawa（渥太华大学）
We analysed a dataset of scientific manuscripts that were submitted to various conferences in artificial intelligence. We performed a combination of semantic, lexical and psycholinguistic analyses of the full text of the manuscripts and compared them with the outcome of the peer review process. We found that accepted manuscripts scored lower than rejected manuscripts on two indicators of readability, and that they also used more scientific and artificial intelligence jargon. We also found that accepted manuscripts were written with words that are less frequent, that are acquired at an older ag…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
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…
Sogou Inc（搜狗公司）；Key Lab of Intelligent Information Processing of CAS（中国科学院智能信息处理重点实验室）；ICT（中国科学院计算技术研究所）
Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some attendant problems, such as corpus selection for embedding learning, dictionary transformation for different learning tasks, etc. In this paper, we propose to straightforwardly model sentences by means of character sequences, and then utilize convolutional neural networks to integrate character embedding learning together with point-wise answer selection training. C…
Mapping ChatGPT in Mainstream Media to Unravel Jobs and Diversity Challenges: Early Quantitative Insights through Sentiment Analysis and Word Frequency Analysis
To transcribe spoken language to written medium, most alphabets enable an unambiguous sound-to-letter rule. However, some writing systems have distanced themselves from this simple concept and little work exists in Natural Language Processing (NLP) on measuring such distance. In this study, we use an Artificial Neural Network (ANN) model to evaluate the transparency between written words and their pronunciation, hence its name Orthographic Transparency Estimation with an ANN (OTEANN). Based on datasets derived from Wikimedia dictionaries, we trained and tested this model to score the percentag…
Universidad Nacional Autónoma de México (UNAM)（墨西哥国立自治大学）；Centro de ciencias genómicas (CCG–UNAM)（基因组科学中心（墨西哥国立自治大学））；Instituto de ingeniería (IIngen–UNAM)（工程研究所（墨西哥国立自治大学））；Laboratoire Informatique d’Avignon (LIA–UAPV)（阿维尼翁计算机科学实验室（阿维尼翁大学））；Centro de investigación en computación (CIC–IPN)（计算机研究中心（国立理工学院））
Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an open question due to complexities of semantic interactions among words. In this paper, we present an embedding method, which is aimed at learning unsupervised sentence representations from unlabeled text. We propose an unsupervised method that models a sentence as a weighted series of word embeddings. The weights of the word embeddings are fitted by using Shan…
University of Oxford（牛津大学）；Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；Radboud University（拉德堡德大学）
Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. As such, they could be interesting models of the integration of linguistic information in the human brain. We review works that compare these artificial language models with human brain activity and we assess the extent to which this approach has improved our understanding of the neural processes involved in natural language comprehension. Two main results emerge. First, the neural representation of word meaning aligns with the context-dependent, de…
We present a simple yet elegant solution to train a single joint model on multi-criteria corpora for Chinese Word Segmentation (CWS). Our novel design requires no private layers in model architecture, instead, introduces two artificial tokens at the beginning and ending of input sentence to specify the required target criteria. The rest of the model including Long Short-Term Memory (LSTM) layer and Conditional Random Fields (CRFs) layer remains unchanged and is shared across all datasets, keeping the size of parameter collection minimal and constant. On Bakeoff 2005 and Bakeoff 2008 datasets, …
The emergence of knowledge graphs in the scholarly communication domain and recent advances in artificial intelligence and natural language processing bring us closer to a scenario where intelligent systems can assist scientists over a range of knowledge-intensive tasks. In this paper we present experimental results about the generation of word embeddings from scholarly publications for the intelligent processing of scientific texts extracted from SciGraph. We compare the performance of domain-specific embeddings with existing pre-trained vectors generated from very large and general purpose c…
Zhejiang University（浙江大学）；University of Electronic Science and Technology of China（电子科技大学）；Singapore Management University（新加坡管理大学）
Solving mathematical word problems (MWPs) automatically is challenging, primarily due to the semantic gap between human-readable words and machine-understandable logics. Despite the long history dated back to the1960s, MWPs have regained intensive attention in the past few years with the advancement of Artificial Intelligence (AI). Solving MWPs successfully is considered as a milestone towards general AI. Many systems have claimed promising results in self-crafted and small-scale datasets. However, when applied on large and diverse datasets, none of the proposed methods in the literature achie…
Athens University of Economics and Business（雅典经济与商业大学）；Institute for Language and Speech Processing, Research Center ‘Athena’（“雅典娜”研究中心语言与语音处理研究所）；Institute of Informatics and Telecommunications, NCSR ‘Demokritos’（国家科学研究中心“德谟克利特”信息与电信研究所）
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult. We experiment with data from the BioASQ challenge, which we augment with training instances obtained from an artificial biomedical machine reading comprehension dataset, or via back-translation, information retrieval, word substitution based on word2vec embeddings, or masked language modeling, question generation, or extending the given passage with additional context. We show that da can lead to very signifi…
Institute for Anthropomatics and Robotics（人机与机器人研究所）；KIT - Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
In this work we look into adding a new language to a multilingual NMT system in an unsupervised fashion. Under the utilization of pre-trained cross-lingual word embeddings we seek to exploit a language independent multilingual sentence representation to easily generalize to a new language. While using cross-lingual embeddings for word lookup we decode from a yet entirely unseen source language in a process we call blind decoding. Blindly decoding from Portuguese using a basesystem containing several Romance languages we achieve scores of 36.4 BLEU for Portuguese-English and 12.8 BLEU for Russi…
North China University of Technology（北方工业大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Spelling error detection serves as a crucial preprocessing in many natural language processing applications. Due to the characteristics of Chinese Language, Chinese spelling error detection is more challenging than error detection in English. Existing methods are mainly under a pipeline framework, which artificially divides error detection process into two steps. Thus, these methods bring error propagation and cannot always work well due to the complexity of the language environment. Besides existing methods only adopt character or word information, and ignore the positive effect of fusing cha…
University of Cambridge（剑桥大学）；Mila/McGill University（米拉/麦吉尔大学）
Capturing word meaning in context and distinguishing between correspondences and variations across languages is key to building successful multilingual and cross-lingual text representation models. However, existing multilingual evaluation datasets that evaluate lexical semantics "in-context" have various limitations. In particular, 1) their language coverage is restricted to high-resource languages and skewed in favor of only a few language families and areas, 2) a design that makes the task solvable via superficial cues, which results in artificially inflated (and sometimes super-human) perf…
This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the proposed CSP randomly replaces some words in the source sentence with their translation words in the target language. Specifically, we firstly perform lexicon induction with unsupervised word embedding mapping between the source and target languages, and then randomly replace some words in the input sentence with their translation words according to the extrac…
The dialogue management is a task of conversational artificial intelligence. The goal of the dialogue manager is to select the appropriate response to the conversational partner conditioned by the input message and recent dialogue state. Hybrid Code Networks is one of the models of dialogue managers, which uses an average of word embeddings and bag-of-words as input features. We perform experiments on Dialogue bAbI Task 6 and Alquist Conversational Dataset. The experiments show that the convolutional neural network used as an input layer of the Hybrid Code Network improves the model's turn acc…
Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial word-similarity tasks, we don't know if they improve real natural language understanding tasks. In this paper we introduce a multi-sense embedding model based on Chinese Restaurant Processes that achieves state of the art performance on matching human word similarity judgments, and propose a pipelined architecture for incorporating multi-sense embeddings into langua…
When communicating, people behave consistently across conversational roles: People understand the words they say and are able to produce the words they hear. To date, artificial agents developed for language tasks have lacked such symmetry, meaning agents trained to produce language are unable to understand it and vice-versa. In this work, we exploit the symmetric nature of communication in order to improve both the efficiency and quality of language acquisition in learning agents. Specifically, we consider the setting in which an agent must learn to both understand and generate words in an ex…
Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Swisscom (Switzerland) AG（瑞士电信（瑞士）股份公司）；University of Southern California (USC)（南加利福尼亚大学）；Swisscom AG（瑞士电信股份公司）
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, …
A lack of code-switching data complicates the training of code-switching (CS) language models. We propose an approach to train such CS language models on monolingual data only. By constraining and normalizing the output projection matrix in RNN-based language models, we bring embeddings of different languages closer to each other. Numerical and visualization results show that the proposed approaches remarkably improve the performance of CS language models trained on monolingual data. The proposed approaches are comparable or even better than training CS language models with artificially genera…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心）；The Hong Kong University of Science and Technology（香港科技大学）
Training code-switched language models is difficult due to lack of data and complexity in the grammatical structure. Linguistic constraint theories have been used for decades to generate artificial code-switching sentences to cope with this issue. However, this require external word alignments or constituency parsers that create erroneous results on distant languages. We propose a sequence-to-sequence model using a copy mechanism to generate code-switching data by leveraging parallel monolingual translations from a limited source of code-switching data. The model learns how to combine words fr…
This paper presents machine learning solutions to a practical problem of Natural Language Generation (NLG), particularly the word formation in agglutinative languages like Tamil, in a supervised manner. The morphological generator is an important component of Natural Language Processing in Artificial Intelligence. It generates word forms given a root and affixes. The morphophonemic changes like addition, deletion, alternation etc., occur when two or more morphemes or words joined together. The Sandhi rules should be explicitly specified in the rule based morphological analyzers and generators.…
Polish-Japanese Academy of Information Technology（波日信息技术学院）；Jatar（Jatar公司）
Automatic poetry generation is novel and interesting application of natural language processing research. It became more popular during the last few years due to the rapid development of technology and neural computing power. This line of research can be applied to the study of linguistics and literature, for social science experiments, or simply for entertainment. The most effective known method of artificial poem generation uses recurrent neural networks (RNN). We also used RNNs to generate poems in the style of Adam Mickiewicz. Our network was trained on the Sir Thaddeus poem. For data pre-…
INRIA（法国国家信息与自动化研究所）；ENS Rennes（雷恩高等师范学院）；Université de Bordeaux（波尔多大学）；Microsoft Research Montreal（微软蒙特利尔研究院）
Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with visual processing. Similar to humans, recent artificial models jointly trained on texts and images, e.g., OpenAI CLIP, show language-biased image classification. Exploring whether the bias leads to interference similar to those observed in humans can contribute to understanding how much the model acquires hierarchical semantic representations from joint learnin…
The paper argues that Fodor and Lepore are misguided in their attack on Pustejovsky's Generative Lexicon, largely because their argument rests on a traditional, but implausible and discredited, view of the lexicon on which it is effectively empty of content, a view that stands in the long line of explaining word meaning (a) by ostension and then (b) explaining it by means of a vacuous symbol in a lexicon, often the word itself after typographic transmogrification. (a) and (b) both share the wrong belief that to a word must correspond a simple entity that is its meaning. I then turn to the sema…
A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?
Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚研究与高等教育机构（ICREA））；New York University（纽约大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
Institut für Maschinelle Sprachverarbeitung（机器语言处理研究所）；Universität Stuttgart（斯图加特大学）
We present a general-purpose tagger based on convolutional neural networks (CNN), used for both composing word vectors and encoding context information. The CNN tagger is robust across different tagging tasks: without task-specific tuning of hyper-parameters, it achieves state-of-the-art results in part-of-speech tagging, morphological tagging and supertagging. The CNN tagger is also robust against the out-of-vocabulary problem, it performs well on artificially unnormalized texts.
Tehran University（德黑兰大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Query expansion is a method for alleviating the vocabulary mismatch problem present in information retrieval tasks. Previous works have shown that terms selected for query expansion by traditional methods such as pseudo-relevance feedback are not always helpful to the retrieval process. In this paper, we show that this is also true for more recently proposed embedding-based query expansion methods. We then introduce an artificial neural network classifier to predict the usefulness of query expansion terms. This classifier uses term word embeddings as inputs. We perform experiments on four TREC…
There have been many advances in the artificial intelligence field due to the emergence of deep learning. In almost all sub-fields, artificial neural networks have reached or exceeded human-level performance. However, most of the models are not interpretable. As a result, it is hard to trust their decisions, especially in life and death scenarios. In recent years, there has been a movement toward creating explainable artificial intelligence, but most work to date has concentrated on image processing models, as it is easier for humans to perceive visual patterns. There has been little work in o…
Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress. The ongoing surge to solve math word problems (MWPs) and hence achieve better mathematical reasoning ability would continue to be a key line of research in the coming time. We inspect non-neural and neural methods to solve math word problems narrated in a natural language. We also highlight the ability of these methods to be generalizable, mathematically reasonable, interpretable, and explainable. Neural approaches dominate the current state of the art, and we survey them highlig…
Institute of Nuclear Physics, Polish Academy of Sciences（波兰科学院核物理研究所）；Cracow University of Technology（克拉科夫理工大学）
We investigate properties of evolving linguistic networks defined by the word-adjacency relation. Such networks belong to the category of networks with accelerated growth but their shortest path length appears to reveal the network size dependence of different functional form than the ones known so far. We thus compare the networks created from literary texts with their artificial substitutes based on different variants of the Dorogovtsev-Mendes model and observe that none of them is able to properly simulate the novel asymptotics of the shortest path length. Then, we identify the local chain-…
