The explosion of disinformation related to the COVID-19 pandemic has overloaded fact-checkers and media worldwide. To help tackle this, we developed computational methods to support COVID-19 disinformation debunking and social impacts research. This paper presents: 1) the currently largest available manually annotated COVID-19 disinformation category dataset; and 2) a classification-aware neural topic model (CANTM) that combines classification and topic modelling under a variational autoencoder framework. We demonstrate that CANTM efficiently improves classification performance with low resources, and is scalable. In addition, the classification-aware topics help researchers and end-users to better understand the classification results.
We describe Bioformer team's participation in the multi-label topic classification task for COVID-19 literature (track 5 of BioCreative VII). Topic classification is performed using different BERT models (BioBERT, PubMedBERT, and Bioformer). We formulate the topic classification task as a sentence pair classification problem, where the title is the first sentence, and the abstract is the second sentence. Our results show that Bioformer outperforms BioBERT and PubMedBERT in this task. Compared to the baseline results, our best model increased micro, macro, and instance-based F1 score by 8.8%, 15.5%, 7.4%, respectively. Bioformer achieved the highest micro F1 and macro F1 scores in this challenge. In post-challenge experiments, we found that pretraining of Bioformer on COVID-19 articles further improves the performance.
Automatic classification of scientific articles based on common characteristics is an interesting problem with many applications in digital library and information retrieval systems. Properly organized articles can be useful for automatic generation of taxonomies in scientific writings, textual summarization, efficient information retrieval etc. Generating article bundles from a large number of input articles, based on the associated features of the articles is tedious and computationally expensive task. In this report we propose an automatic two-step approach for topic extraction and bundling of related articles from a set of scientific articles in real-time. For topic extraction, we make use of Latent Dirichlet Allocation (LDA) topic modeling techniques and for bundling, we make use of hierarchical agglomerative clustering techniques. We run experiments to validate our bundling semantics and compare it with existing models in use. We make use of an online crowdsourcing marketplace provided by Amazon called Amazon Mechanical Turk to carry out experiments. We explain our experimental setup and empirical results in detail and show that our method is advantageous over existing ones.
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. To develop an effective CRS, the support of high-quality datasets is essential. Existing CRS datasets mainly focus on immediate requests from users, while lack proactive guidance to the recommendation scenario. In this paper, we contribute a new CRS dataset named \textbf{TG-ReDial} (\textbf{Re}commendation through \textbf{T}opic-\textbf{G}uided \textbf{Dial}og). Our dataset has two major features. First, it incorporates topic threads to enforce natural semantic transitions towards the recommendation scenario. Second, it is created in a semi-automatic way, hence human annotation is more reasonable and controllable. Based on TG-ReDial, we present the task of topic-guided conversational recommendation, and propose an effective approach to this task. Extensive experiments have demonstrated the effectiveness of our approach on three sub-tasks, namely topic prediction, item recommendation and response generation. TG-ReDial is available at https://github.com/RUCAIBox/TG-ReDial.
Automatic text summarization aims at condensing a document to a shorter version while preserving the key information. Different from extractive summarization which simply selects text fragments from the document, abstractive summarization generates the summary in a word-by-word manner. Most current state-of-the-art (SOTA) abstractive summarization methods are based on the Transformer-based encoder-decoder architecture and focus on novel self-supervised objectives in pre-training. While these models well capture the contextual information among words in documents, little attention has been paid to incorporating global semantics to better fine-tune for the downstream abstractive summarization task. In this study, we propose a topic-aware abstractive summarization (TAAS) framework by leveraging the underlying semantic structure of documents represented by their latent topics. Specifically, TAAS seamlessly incorporates a neural topic modeling into an encoder-decoder based sequence generation procedure via attention for summarization. This design is able to learn and preserve global semantics of documents and thus makes summarization effective, which has been proved by our experiments on real-world datasets. As compared to several cutting-edge baseline methods, we show that TAAS outperforms BART, a well-recognized SOTA model, by 2%, 8%, and 12% regarding the F measure of ROUGE-1, ROUGE-2, and ROUGE-L, respectively. TAAS also achieves comparable performance to PEGASUS and ProphetNet, which is difficult to accomplish given that training PEGASUS and ProphetNet requires enormous computing capacity beyond what we used in this study.
Importance of document clustering is now widely acknowledged by researchers for better management, smart navigation, efficient filtering, and concise summarization of large collection of documents like World Wide Web (WWW). The next challenge lies in semantically performing clustering based on the semantic contents of the document. The problem of document clustering has two main components: (1) to represent the document in such a form that inherently captures semantics of the text. This may also help to reduce dimensionality of the document, and (2) to define a similarity measure based on the semantic representation such that it assigns higher numerical values to document pairs which have higher semantic relationship. Feature space of the documents can be very challenging for document clustering. A document may contain multiple topics, it may contain a large set of class-independent general-words, and a handful class-specific core-words. With these features in mind, traditional agglomerative clustering algorithms, which are based on either Document Vector model (DVM) or Suffix Tree model (STC), are less efficient in producing results with high cluster quality. This paper introduces a new approach for document clustering based on the Topic Map representation of the documents. The document is being transformed into a compact form. A similarity measure is proposed based upon the inferred information through topic maps data and structures. The suggested method is implemented using agglomerative hierarchal clustering and tested on standard Information retrieval (IR) datasets. The comparative experiment reveals that the proposed approach is effective in improving the cluster quality.
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependences. For inference, we develop a hybrid of stochastic-gradient MCMC and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms state-of-the-art larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.
With the advent of semantic web, various tools and techniques have been introduced for presenting and organizing knowledge. Concept hierarchies are one such technique which gained significant attention due to its usefulness in creating domain ontologies that are considered as an integral part of semantic web. Automated concept hierarchy learning algorithms focus on extracting relevant concepts from unstructured text corpus and connect them together by identifying some potential relations exist between them. In this paper, we propose a novel approach for identifying relevant concepts from plain text and then learns hierarchy of concepts by exploiting subsumption relation between them. To start with, we model topics using a probabilistic topic model and then make use of some lightweight linguistic process to extract semantically rich concepts. Then we connect concepts by identifying an "is-a" relationship between pair of concepts. The proposed method is completely unsupervised and there is no need for a domain specific training corpus for concept extraction and learning. Experiments on large and real-world text corpora such as BBC News dataset and Reuters News corpus shows that the proposed method outperforms some of the existing methods for concept extraction and efficient concept hierarchy learning is possible if the overall task is guided by a probabilistic topic modeling algorithm.
Topic models, and more specifically the class of Latent Dirichlet Allocation (LDA), are widely used for probabilistic modeling of text. MCMC sampling from the posterior distribution is typically performed using a collapsed Gibbs sampler. We propose a parallel sparse partially collapsed Gibbs sampler and compare its speed and efficiency to state-of-the-art samplers for topic models on five well-known text corpora of differing sizes and properties. In particular, we propose and compare two different strategies for sampling the parameter block with latent topic indicators. The experiments show that the increase in statistical inefficiency from only partial collapsing is smaller than commonly assumed, and can be more than compensated by the speedup from parallelization and sparsity on larger corpora. We also prove that the partially collapsed samplers scale well with the size of the corpus. The proposed algorithm is fast, efficient, exact, and can be used in more modeling situations than the ordinary collapsed sampler.
We propose a general method for automated word puzzle generation. Contrary to previous approaches in this novel field, the presented method does not rely on highly structured datasets obtained with serious human annotation effort: it only needs an unstructured and unannotated corpus (i.e., document collection) as input. The method builds upon two additional pillars: (i) a topic model, which induces a topic dictionary from the input corpus (examples include e.g., latent semantic analysis, group-structured dictionaries or latent Dirichlet allocation), and (ii) a semantic similarity measure of word pairs. Our method can (i) generate automatically a large number of proper word puzzles of different types, including the odd one out, choose the related word and separate the topics puzzle. (ii) It can easily create domain-specific puzzles by replacing the corpus component. (iii) It is also capable of automatically generating puzzles with parameterizable levels of difficulty suitable for, e.g., beginners or intermediate learners.
Add to Chrome
Add to Firefox