Capturing the meaning of sentences has long been a challenging task. Current models tend to apply linear combinations of word features to conduct semantic composition for bigger-granularity units e.g. phrases, sentences, and documents. However, the semantic linearity does not always hold in human language. For instance, the meaning of the phrase `ivory tower' can not be deduced by linearly combining the meanings of `ivory' and `tower'. To address this issue, we propose a new framework that models different levels of semantic units (e.g. sememe, word, sentence, and semantic abstraction) on a single \textit{Semantic Hilbert Space}, which naturally admits a non-linear semantic composition by means of a complex-valued vector word representation. An end-to-end neural network~\footnote{https://github.com/wabyking/qnn} is proposed to implement the framework in the text classification task, and evaluation results on six benchmarking text classification datasets demonstrate the effectiveness, robustness and self-explanation power of the proposed model. Furthermore, intuitive case studies are conducted to help end users to understand how the framework works.
The University of Tokyo（东京大学）；Ochanomizu University（御茶水女子大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）
Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast, logical semantic representations capture deeper levels of sentence semantics, but their symbolic nature does not offer graded notions of textual similarity. We propose a method for determining semantic textual similarity by combining shallow features with features extracted from natural deduction proofs of bidirectional entailment relations between sentence …
This dissertation explores the linguistic and computational aspects of the meaning relations that can hold between two or more complex linguistic expressions (phrases, clauses, sentences, paragraphs). In particular, it focuses on Paraphrasing, Textual Entailment, Contradiction, and Semantic Similarity. In Part I: "Similarity at the Level of Words and Phrases", I study the Distributional Hypothesis (DH) and explore several different methodologies for quantifying semantic similarity at the levels of words and short phrases. In Part II: "Paraphrase Typology and Paraphrase Identification", I focus…
In this chapter, we introduce a new dialogical system for first order classical logic which is close to natural language argumentation, and we prove its completeness with respect to usual classical validity. We combine our dialogical system with the Grail syntactic and semantic parser developed by the second author in order to address automated textual entailment, that is, we use it for deciding whether or not a sentence is a consequence of a short text. This work-which connects natural language semantics and argumentation with dialogical logic-can be viewed as a step towards an inferentialist…
We present our submitted systems for Semantic Textual Similarity (STS) Track 4 at SemEval-2017. Given a pair of Spanish-English sentences, each system must estimate their semantic similarity by a score between 0 and 5. In our submission, we use syntax-based, dictionary-based, context-based, and MT-based methods. We also combine these methods in unsupervised and supervised way. Our best run ranked 1st on track 4a with a correlation of 83.02% with human annotations.
Current measures for evaluating text simplification systems focus on evaluating lexical text aspects, neglecting its structural aspects. In this paper we propose the first measure to address structural aspects of text simplification, called SAMSA. It leverages recent advances in semantic parsing to assess simplification quality by decomposing the input based on its semantic structure and comparing it to the output. SAMSA provides a reference-less automatic evaluation procedure, avoiding the problems that reference-based methods face due to the vast space of valid simplifications for a given se…
Johns Hopkins University（约翰斯·霍普金斯大学）；Amazon Web Services AI Labs（亚马逊云服务人工智能实验室）；University of Pennsylvania（宾夕法尼亚大学）
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semantics during pre-training has not been extensively explored. We therefore propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems. LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from…
Jožef Stefan International Postgraduate School（约热夫·斯特凡国际研究生院）
Semantic parsing methods are used for capturing and representing semantic meaning of text. Meaning representation capturing all the concepts in the text may not always be available or may not be sufficiently complete. Ontologies provide a structured and reasoning-capable way to model the content of a collection of texts. In this work, we present a novel approach to joint learning of ontology and semantic parser from text. The method is based on semi-automatic induction of a context-free grammar from semantically annotated text. The grammar parses the text into semantic trees. Both, the grammar…
In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being non-obvious cases for text classification by analysing them in the semantic embedding space; specifically - (i) semantically similar samples that belong to different classes and (ii) semantically dissimilar samples that belong to the same class. We propose a penalty function to measure the overall difficulty score of every sample in the dataset. We conduct exhaustive experiments on 13 standard datasets to show a cons…
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semant…
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（工业机器人与信息学研究所（CSIC-UPC））
Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural approaches. We present a scenario where semantic similarity is not enough, and we devise a neural approach to learn semantic relatedness. The scenario is text spotting in the wild, where a text in an image (e.g. street sign, advertisement or bus destination) must be identified and recognized. Our goal is to improve the performance of vision systems by leveraging sema…
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of the original text. The attacks cause significant number of flips in white-box setting and same rule based can be used in black-box setting. In a black-box setting, the attacks created are able to reverse decisions of transformer based architectures.
The semantics of determiner phrases, be they definite de- scriptions, indefinite descriptions or quantified noun phrases, is often as- sumed to be a fully solved question: common nouns are properties, and determiners are generalised quantifiers that apply to two predicates: the property corresponding to the common noun and the one corresponding to the verb phrase. We first present a criticism of this standard view. Firstly, the semantics of determiners does not follow the syntactical structure of the sentence. Secondly the standard interpretation of the indefinite article cannot ac- count for …
Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text summarization is to produce a brief summary of the main ideas of the text, while text simplification aims to reduce the linguistic complexity of the text and retain the original meaning. Recently, most approaches for text summarization and text simplification are based on the sequence-to-sequence model, which achieves much success in many text generation tasks. However, although the generated simplified texts are sim…
Peking University（北京大学）；The Hong Kong Polytechnic University（香港理工大学）
Current Chinese social media text summarization models are based on an encoder-decoder framework. Although its generated summaries are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization. We introduce a Semantic Relevance Based neural model to encourage high semantic similarity between texts and summaries. In our model, the source text is represented by a gated attention encoder, while the summary representation is produced by a decoder. Besides, th…
Ivan Franko Lviv National University（伊万·弗兰科利沃夫国立大学）
The use of naive Bayesian classifier (NB) and the classifier by the k nearest neighbors (kNN) in classification semantic analysis of authors' texts of English fiction has been analysed. The authors' works are considered in the vector space the basis of which is formed by the frequency characteristics of semantic fields of nouns and verbs. Highly precise classification of authors' texts in the vector space of semantic fields indicates about the presence of particular spheres of author's idiolect in this space which characterizes the individual author's style.
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Mined Semantic Analysis (MSA) is a novel concept space model which employs unsupervised learning to generate semantic representations of text. MSA represents textual structures (terms, phrases, documents) as a Bag of Concepts (BoC) where concepts are derived from concept rich encyclopedic corpora. Traditional concept space models exploit only target corpus content to construct the concept space. MSA, alternatively, uncovers implicit relations between concepts by mining for their associations (e.g., mining Wikipedia's "See also" link graph). We evaluate MSA's performance on benchmark datasets f…
End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges in generalizing to new domains and generating semantically consistent text. In this work, we present DataTuner, a neural, end-to-end data-to-text generation system that makes minimal assumptions about the data representation and the target domain. We take a two-stage generation-reranking approach, combining a fine-tuned language model with a semantic fidelity classifier. Each of our components is learnt end-to-end without the need for dataset-…
Semantic measures are widely used today to estimate the strength of the semantic relationship between elements of various types: units of language (e.g., words, sentences, documents), concepts or even instances semantically characterized (e.g., diseases, genes, geographical locations). Semantic measures play an important role to compare such elements according to semantic proxies: texts and knowledge representations, which support their meaning or describe their nature. Semantic measures are therefore essential for designing intelligent agents which will for example take advantage of semantic …
Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation scheme by clustering words according to their latent semantics and composing them together to get a set of cluster vectors, which are then concatenated as the final text representation. Evaluation on five classification benchmarks proves the effectiveness of our method. We further conduct visualization analysis showing statistical clustering results and veri…
Charles University, Faculty of Mathematics and Physics（查理大学数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text contains all and only facts supported by the input data. We propose a new metric for evaluating the semantic accuracy of D2T generation based on a neural model pretrained for natural language inference (NLI). We use the NLI model to check textual entailment between the input data and the output text in both directions, allowing us to reveal omissions or hallucinations. Input data are converted to text for NLI using trivial templates. Our exper…
Shenzhen Research Institute of Big Data（深圳大数据研究院）；University of Electronic Science and Technology of China（电子科技大学）；University of Washington（华盛顿大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts, especially user-generated social media content. Semantic augmentation is a potential way to alleviate this problem. Given that rich semantic information is implicitly preserved in pre-trained word embeddings, they are potential ideal resources for semantic augmentation. In this paper, we propose a neural-based approach to NER for social media texts where both local (from running text) and augmented semantics are taken into account. In particular, we obtain the augment…
Several recent works have suggested to represent semantic relations with questions and answers, decomposing textual information into separate interrogative natural language statements. In this paper, we consider three QA-based semantic tasks - namely, QA-SRL, QANom and QADiscourse, each targeting a certain type of predication - and propose to regard them as jointly providing a comprehensive representation of textual information. To promote this goal, we investigate how to best utilize the power of sequence-to-sequence (seq2seq) pre-trained language models, within the unique setup of semi-struc…
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a …
University of Maryland（马里兰大学）；Department of Computer Science（计算机科学系）；College Park, MD 20742, USA（美国马里兰州学院公园市）
Recognizing that even correct translations are not always semantically equivalent, we automatically detect meaning divergences in parallel sentence pairs with a deep neural model of bilingual semantic similarity which can be trained for any parallel corpus without any manual annotation. We show that our semantic model detects divergences more accurately than models based on surface features derived from word alignments, and that these divergences matter for neural machine translation.
The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds the LM in an auto-encoder by feeding its output to a semantic parser whose output is in the same representation domain as the input message. Compared to a baseline that generates text using greedy search, we demonstrate two techniques that improve the fluency and semantic accuracy of the generated text: The first technique samples multiple candidate text sequ…
Norwegian University of Science and Technology（挪威科技大学）；Harokopio University（哈罗科皮奥大学）；Athens University of Economics and Business（雅典经济与商业大学）
The computation of relatedness between two fragments of text in an automated manner requires taking into account a wide range of factors pertaining to the meaning the two fragments convey, and the pairwise relations between their words. Without doubt, a measure of relatedness between text segments must take into account both the lexical and the semantic relatedness between words. Such a measure that captures well both aspects of text relatedness may help in many tasks, such as text retrieval, classification and clustering. In this paper we present a new approach for measuring the semantic rela…
Modern approaches to semanic analysis if reformulated as Hilbert-space problems reveal formal structures known from quantum mechanics. Similar situation is found in distributed representations of cognitive structures developed for the purposes of neural networks. We take a closer look at similarites and differences between the above two fields and quantum information theory.
Measuring text complexity is an essential task in several fields and applications (such as NLP, semantic web, smart education, etc.). The semantic layer of text is more tacit than its syntactic structure and, as a result, calculation of semantic complexity is more difficult than syntactic complexity. While there are famous and powerful academic and commercial syntactic complexity measures, the problem of measuring semantic complexity is still a challenging one. In this paper, we introduce the DAST model, which stands for Deciding About Semantic Complexity of a Text. DAST proposes an intuitioni…
Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学 key laboratory，计算机科学学院，复旦大学）；School of Management, Fudan University（管理学院，复旦大学）；Tencent Weixin Group（腾讯微信集团）；IFM Lab, University of California, Davis（加州大学戴维斯分校IFM实验室）
Semantic Noise affects text analytics activities for the domain-specific industries significantly. It impedes the text understanding which holds prime importance in the critical decision making tasks. In this work, we formalize semantic noise as a sequence of terms that do not contribute to the narrative of the text. We look beyond the notion of standard statistically-based stop words and consider the semantics of terms to exclude the semantic noise. We present a novel Semantic Infusion technique to associate meta-data with the categorical corpus text and demonstrate its near-lossless nature. …
In this paper, we present a novel method for measurably adjusting the semantics of text while preserving its sentiment and fluency, a task we call semantic text exchange. This is useful for text data augmentation and the semantic correction of text generated by chatbots and virtual assistants. We introduce a pipeline called SMERTI that combines entity replacement, similarity masking, and text infilling. We measure our pipeline's success by its Semantic Text Exchange Score (STES): the ability to preserve the original text's sentiment and fluency while adjusting semantic content. We propose to u…
Ivan Franko Lviv National University（伊万·弗兰科利沃夫国立大学）
The clustering of text documents in the vector space of semantic fields and in the semantic space with orthogonal basis has been analysed. It is shown that using the vector space model with the basis of semantic fields is effective in the cluster analysis algorithms of author's texts in English fiction. The analysis of the author's texts distribution in cluster structure showed the presence of the areas of semantic space that represent the author's ideolects of individual authors. SVD factorization of the semantic fields matrix makes it possible to reduce significantly the dimension of the sem…
The paper deals with the problem of text generation and planning approaches making only limited formally specifiable contact with accounts of grammar. We propose an enhancement of a systemically-based generation architecture for German (the KOMET system) by aspects of Kunze's theory of semantic emphasis. Doing this, we gain more control over both concept selection in generation and choice of fine-grained grammatical variation.
Linguistic steganography (LS) aims to embed secret information into a highly encoded text for covert communication. It can be roughly divided to two main categories, i.e., modification based LS (MLS) and generation based LS (GLS). Unlike MLS that hides secret data by slightly modifying a given text without impairing the meaning of the text, GLS uses a trained language model to directly generate a text carrying secret data. A common disadvantage for MLS methods is that the embedding payload is very low, whose return is well preserving the semantic quality of the text. In contrast, GLS allows th…
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is cap…
Ever since neural models were adopted in data-to-text language generation, they have invariably been reliant on extrinsic components to improve their semantic accuracy, because the models normally do not exhibit the ability to generate text that reliably mentions all of the information provided in the input. In this paper, we propose a novel decoding method that extracts interpretable information from encoder-decoder models' cross-attention, and uses it to infer which attributes are mentioned in the generated text, which is subsequently used to rescore beam hypotheses. Using this decoding meth…
Most of the existing text generative steganographic methods are based on coding the conditional probability distribution of each word during the generation process, and then selecting specific words according to the secret information, so as to achieve information hiding. Such methods have their limitations which may bring potential security risks. Firstly, with the increase of embedding rate, these models will choose words with lower conditional probability, which will reduce the quality of the generated steganographic texts; secondly, they can not control the semantic expression of the final…
Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing links between text spans from different content types. In this article we propose a model that approximates the human reading pattern of a document and outputs a unique semantic representation for every text span irrespective of the content type they are found in. We base our architecture on a graph representation of the structured text, and we demonstrate that…
Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to embody semantic information and employed to TTS recently. However, original or simply fine-tuned BERT embeddings still cannot provide sufficient semantic knowledge that expressive TTS models should take into account. In this paper, we propose a word-level semantic representation enhancing method based on dependency structure and pre-trained BERT embedding. The…
Zhejiang University（浙江大学）；University of Sydney（悉尼大学）；Hangzhou Dianzi University（杭州电子科技大学）
Generating an image from a given text description has two goals: visual realism and semantic consistency. Although significant progress has been made in generating high-quality and visually realistic images using generative adversarial networks, guaranteeing semantic consistency between the text description and visual content remains very challenging. In this paper, we address this problem by proposing a novel global-local attentive and semantic-preserving text-to-image-to-text framework called MirrorGAN. MirrorGAN exploits the idea of learning text-to-image generation by redescription and con…
Sun Yat-sen University（中山大学）；University of Technology Sydney（悉尼科技大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Oxford（牛津大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existing works focus on pixel grouping and cross-modal semantic alignment, while ignoring the correspondence among multiple augmented views of the same image. To overcome such limitation, we propose multi-\textbf{View} \textbf{Co}nsistent learning (ViewCo) for text-supervised semantic segmentation. Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input…
