Journalists obtain "leads", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are interesting documents. We propose a model of "newsworthiness" aimed at surfacing interesting documents. We train models on automatically labeled corpora -- published newspaper articles -- to predict whether each article was a front-page article (i.e., \textbf{newsworthy}) or not (i.e., \textbf{less newsworthy}). We transfer these models to unlabeled corpora -- court cases, bills, city-council meeting minutes -- to rank documents in these corpora on "newsworthiness". A fine-tuned RoBERTa model achieves .93 AUC performance on heldout labeled documents, and .88 AUC on expert-validated unlabeled corpora. We provide interpretation and visualization for our models.
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；Reuters News（路透新闻）；University of California, Los Angeles（加州大学洛杉矶分校）；Stanford University（斯坦福大学）
The availability of parallel sentence simplification (SS) is scarce for neural SS modelings. We propose an unsupervised method to build SS corpora from large-scale bilingual translation corpora, alleviating the need for SS supervised corpora. Our method is motivated by the following two findings: neural machine translation model usually tends to generate more high-frequency tokens and the difference of text complexity levels exists between the source and target language of a translation corpus. By taking the pair of the source sentences of translation corpus and the translations of their refer…
In terminology work, natural language processing, and digital humanities, several studies address the analysis of variations in context and meaning of terms in order to detect semantic change and the evolution of terms. We distinguish three different approaches to describe contextual variations: methods based on the analysis of patterns and linguistic clues, methods exploring the latent semantic space of single words, and methods for the analysis of topic membership. The paper presents the notion of context volatility as a new measure for detecting semantic change and applies it to key term ex…
Institute of Formal and Applied Linguistics, Charles University（查理大学形式与应用语言学研究所）
Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora. Metadata of research articles are usually easy to find online and can be used to perform research on various tasks. In this paper, we introduce two huge datasets for text summarization (OAGSX) and keyword generation (OAGKX) research, containing 34 million and 23 million records, respectively. The data were retrieved from the Open Academic Graph which is a network o…
Institute for Computer Science and Control Hungarian Academy of Sciences（匈牙利科学院计算机科学与控制研究所）
This paper aims to make up for the lack of documented baselines for Hungarian language modeling. Various approaches are evaluated on three publicly available Hungarian corpora. Perplexity values comparable to models of similar-sized English corpora are reported. A new, freely downloadable Hungar- ian benchmark corpus is introduced.
University of Oxford（牛津大学）；Rural Senses Ltd.（Rural Senses有限公司）；University of Cambridge（剑桥大学）
Most well-established data collection methods currently adopted in NLP depend on the assumption of speaker literacy. Consequently, the collected corpora largely fail to represent swathes of the global population, which tend to be some of the most vulnerable and marginalised people in society, and often live in rural developing areas. Such underrepresented groups are thus not only ignored when making modeling and system design decisions, but also prevented from benefiting from development outcomes achieved through data-driven NLP. This paper aims to address the under-representation of illiterat…
The University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Microsoft Research（微软研究院）；Army Research Laboratory（陆军研究实验室）
While most topic modeling algorithms model text corpora with unigrams, human interpretation often relies on inherent grouping of terms into phrases. As such, we consider the problem of discovering topical phrases of mixed lengths. Existing work either performs post processing to the inference results of unigram-based topic models, or utilizes complex n-gram-discovery topic models. These methods generally produce low-quality topical phrases or suffer from poor scalability on even moderately-sized datasets. We propose a different approach that is both computationally efficient and effective. Our…
Earnings conference calls are significant information events for volatility forecasting, which is essential for financial risk management and asset pricing. Although some recent volatility forecasting models have utilized the textual content of conference calls, the dialogue structures of conference calls and company relationships are almost ignored in extant literature. To bridge this gap, we propose a new model called Temporal Virtual Graph Neural Network (TVGNN) for volatility forecasting by jointly modeling conference call dialogues and company networks. Our model differs from existing mod…
HistLens: Mapping Idea Change across Concepts and Corpora
Department of Computer Science and Technology, Tsinghua University, China（清华大学计算机科学与技术系）；School of History, Nanjing University, China（南京大学历史学院）；Department of Chinese Language and Literature, Tsinghua University, China（清华大学中国语言文学系）；State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, China（北京大学计算机学院多媒体信息处理国家重点实验室）
Microsoft Corporation（微软公司）；Coleridge Initiative（科尔里奇倡议组织）
Many prior language modeling efforts have shown that pre-training on an in-domain corpus can significantly improve performance on downstream domain-specific NLP tasks. However, the difficulties associated with collecting enough in-domain data might discourage researchers from approaching this pre-training task. In this paper, we conducted a series of experiments by pre-training Bidirectional Encoder Representations from Transformers (BERT) with different sizes of biomedical corpora. The results demonstrate that pre-training on a relatively small amount of in-domain data (4GB) with limited trai…
Human conversations consist of reasonable and natural topic flows, which are observed as the shifts of the mentioned concepts across utterances. Previous chatbots that incorporate the external commonsense knowledge graph prove that modeling the concept shifts can effectively alleviate the dull and uninformative response dilemma. However, there still exists a gap between the concept relations in the natural conversation and those in the external commonsense knowledge graph, which is an issue to solve. Specifically, the concept relations in the external commonsense knowledge graph are not intuit…
We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw, unstructured text. We release the full corpus as a resource to aid on…
Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem using parallel corpus has been a major workaround. However, existing solutions use linguistic constraints which may not capture the real data distribution. In this work, we propose a novel method for learning how to generate code-switching sentences from parallel corpora. Our model uses a Seq2Seq model in combination with pointer networks to align and choose words from the monolingual sentences and form a grammatical code-switching sentence. In our experiment, …
In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language. We perform an exhaustive study on techniques such as character Convolutional Neural Networks or Long-Short Term Memory, on the One Billion Word Benchmark. Our best single model significantly improves state-of-the-art perplexity from 51.3 down to 30.0 (whilst reducing the number of parameters by a f…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Google Research（谷歌研究院）；Army Research Laboratory（陆军研究实验室）
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus. Phrase mining is important in various tasks such as information extraction/retrieval, taxonomy construction, and topic modeling. Most existing methods rely on complex, trained linguistic analyzers, and thus likely have unsatisfactory performance on text corpora of new domains and genres without extra but expensive adaption. Recently, a few data-driven methods have been developed successfully for extraction of phrases from massive domain-specific text. However, none of the stat…
Stanford University（斯坦福大学）；Harvard Business School（哈佛商学院）；Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加利福尼亚大学）
What kind of basic research ideas are more likely to get applied in practice? There is a long line of research investigating patterns of knowledge transfer, but it generally focuses on documents as the unit of analysis and follow their transfer into practice for a specific scientific domain. Here we study translational research at the level of scientific concepts for all scientific fields. We do this through text mining and predictive modeling using three corpora: 38.6 million paper abstracts, 4 million patent documents, and 0.28 million clinical trials. We extract scientific concepts (i.e., p…
Singapore University of Technology and Design（新加坡科技设计大学）；Forth AI（Forth人工智能公司）；University of Colorado Denver（科罗拉多大学丹佛分校）
Since the start of COVID-19, several relevant corpora from various sources are presented in the literature that contain millions of data points. While these corpora are valuable in supporting many analyses on this specific pandemic, researchers require additional benchmark corpora that contain other epidemics to facilitate cross-epidemic pattern recognition and trend analysis tasks. During our other efforts on COVID-19 related work, we discover very little disease related corpora in the literature that are sizable and rich enough to support such cross-epidemic analysis tasks. In this paper, we…
This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical borrowings -- words from one language that are introduced into another without orthographic adaptation -- and use it to evaluate how several sequence labeling models (CRF, BiLSTM-CRF, and Transformer-based models) perform. The corpus contains 370,000 tokens and is larger, more borrowing-dense, OOV-rich, and topic-varied than previous corpora available for this task. Our result…
National Research University Higher School of Economics（俄罗斯国家研究型高等经济大学）；Mail.ru Group（Mail.ru集团）
Distributed vector representations for natural language vocabulary get a lot of attention in contemporary computational linguistics. This paper summarizes the experience of applying neural network language models to the task of calculating semantic similarity for Russian. The experiments were performed in the course of Russian Semantic Similarity Evaluation track, where our models took from the 2nd to the 5th position, depending on the task. We introduce the tools and corpora used, comment on the nature of the shared task and describe the achieved results. It was found out that Continuous Skip…
Pre-training Large Language Models (LLMs) require massive amounts of text data, and the performance of the LLMs typically correlates with the scale and quality of the datasets. This means that it may be challenging to build LLMs for smaller languages such as Nordic ones, where the availability of text corpora is limited. In order to facilitate the development of the LLMS in the Nordic languages, we curate a high-quality dataset consisting of 1.2TB of text, in all of the major North Germanic languages (Danish, Icelandic, Norwegian, and Swedish), as well as some high-quality English data. This p…
Preconditions provide a form of logical connection between events that explains why some events occur together and information that is complementary to the more widely studied relations such as causation, temporal ordering, entailment, and discourse relations. Modeling preconditions in text has been hampered in part due to the lack of large scale labeled data grounded in text. This paper introduces PeKo, a crowd-sourced annotation of preconditions between event pairs in newswire, an order of magnitude larger than prior text annotations. To complement this new corpus, we also introduce two chal…
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
MemTensor (Shanghai) Technology（MemTensor（上海）科技）；KU Leuven（鲁汶大学）；Zhejiang University（浙江大学）；University of Chinese Academy of Sciences（中国科学院大学）；Sinar Mas Paper (China) Investment Co., Ltd（金光纸业（中国）投资有限公司）；The Hong Kong Polytechnic University（香港理工大学）
Center for Language and Speech Processing（语言与语音处理中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited. Current approaches to dealing with this problem mainly focus on filtering using heuristics or single features such as language model scores or bi-lingual similarity. This work presents an alternative approach which learns weights for multiple sentence-level features. These feature weights which are optimized directly for the task of improving tra…
Indian Institute of Technology Goa（印度理工学院果阿分校）；Informatics Institute, University of Florida（佛罗里达大学信息学研究所）；University of Florida（佛罗里达大学）
As electronically stored data grow in daily life, obtaining novel and relevant information becomes challenging in text mining. Thus people have sought statistical methods based on term frequency, matrix algebra, or topic modeling for text mining. Popular topic models have centered on one single text collection, which is deficient for comparative text analyses. We consider a setting where one can partition the corpus into subcollections. Each subcollection shares a common set of topics, but there exists relative variation in topic proportions among collections. Including any prior knowledge abo…
Topic Modeling refers to the problem of discovering the main topics that have occurred in corpora of textual data, with solutions finding crucial applications in numerous fields. In this work, inspired by the recent advancements in the Natural Language Processing domain, we introduce FAME, an open-source framework enabling an efficient mechanism of extracting and incorporating textual features and utilizing them in discovering topics and clustering text documents that are semantically similar in a corpus. These features range from traditional approaches (e.g., frequency-based) to the most rece…
Topic models are in widespread use in natural language processing and beyond. Here, we propose a new framework for the evaluation of probabilistic topic modeling algorithms based on synthetic corpora containing an unambiguously defined ground truth topic structure. The major innovation of our approach is the ability to quantify the agreement between the planted and inferred topic structures by comparing the assigned topic labels at the level of the tokens. In experiments, our approach yields novel insights about the relative strengths of topic models as corpus characteristics vary, and the fir…
University of South Carolina（南卡罗来纳大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
The majority of medical documents and electronic health records (EHRs) are in text format that poses a challenge for data processing and finding relevant documents. Looking for ways to automatically retrieve the enormous amount of health and medical knowledge has always been an intriguing topic. Powerful methods have been developed in recent years to make the text processing automatic. One of the popular approaches to retrieve information based on discovering the themes in health & medical corpora is topic modeling, however, this approach still needs new perspectives. In this research we descr…
Saarland University（萨尔大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Macquarie University（麦考瑞大学）
This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their publication date taking into account lexical variation represented as word n-grams, and morphosyntactic variation represented by part-of-speech (POS) distribution. We report results of 99.8% accuracy using word unigram features with a Support Vector Machines classifier to predict the publication date of documents in time intervals of both one century and half a c…
Peking University（北京大学）；Renmin University of China（中国人民大学）
Topic evolution modeling has received significant attentions in recent decades. Although various topic evolution models have been proposed, most studies focus on the single document corpus. However in practice, we can easily access data from multiple sources and also observe relationships between them. Then it is of great interest to recognize the relationship between multiple text corpora and further utilize this relationship to improve topic modeling. In this work, we focus on a special type of relationship between two text corpora, which we define as the "lead-lag relationship". This relati…
This paper evaluates global-scale dialect identification for 14 national varieties of English as a means for studying syntactic variation. The paper makes three main contributions: (i) introducing data-driven language mapping as a method for selecting the inventory of national varieties to include in the task; (ii) producing a large and dynamic set of syntactic features using grammar induction rather than focusing on a few hand-selected features such as function words; and (iii) comparing models across both web corpora and social media corpora in order to measure the robustness of syntactic va…
KAIST（韩国科学技术院）；Australian National University（澳大利亚国立大学）
Much of scientific progress stems from previously published findings, but searching through the vast sea of scientific publications is difficult. We often rely on metrics of scholarly authority to find the prominent authors but these authority indices do not differentiate authority based on research topics. We present Latent Topical-Authority Indexing (LTAI) for jointly modeling the topics, citations, and topical authority in a corpus of academic papers. Compared to previous models, LTAI differs in two main aspects. First, it explicitly models the generative process of the citations, rather th…
American University（美利坚大学）；University of Maryland（马里兰大学）；Energetics Technology Center（含能材料技术中心）
As the amount and variety of energetics research increases, machine aware topic identification is necessary to streamline future research pipelines. The makeup of an automatic topic identification process consists of creating document representations and performing classification. However, the implementation of these processes on energetics research imposes new challenges. Energetics datasets contain many scientific terms that are necessary to understand the context of a document but may require more complex document representations. Secondly, the predictions from classification must be unders…
iCoSys Institute, University of Applied Sciences and Arts Western Switzerland（瑞士西部应用科学与艺术大学iCoSys研究所）；University of Fribourg（弗里堡大学）；Swisscom AG（瑞士电信公司）
This paper presents SwissCrawl, the largest Swiss German text corpus to date. Composed of more than half a million sentences, it was generated using a customized web scraping tool that could be applied to other low-resource languages as well. The approach demonstrates how freely available web pages can be used to construct comprehensive text corpora, which are of fundamental importance for natural language processing. In an experimental evaluation, we show that using the new corpus leads to significant improvements for the task of language modeling. To capture new content, our approach will ru…
Salesforce（赛富时）；University of Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；University of Lorraine（洛林大学）
Probabilistic topic models like Latent Dirichlet Allocation (LDA) have been previously extended to the bilingual setting. A fundamental modeling assumption in several of these extensions is that the input corpora are in the form of document pairs whose constituent documents share a single topic distribution. However, this assumption is strong for comparable corpora that consist of documents thematically similar to an extent only, which are, in turn, the most commonly available or easy to obtain. In this paper we relax this assumption by proposing for the paired documents to have separate, yet …
GHTM: A graph-based hybrid topic modeling approach for Bengali language
Institute of Information Technology (IIT), University of Dhaka（达卡大学信息技术研究所）；Centre for Advanced Research in Sciences (CARS), University of Dhaka（达卡大学高级科学研究中心）
Northwestern Polytechnical University（西北工业大学）；Tencent AI Lab（腾讯人工智能实验室）
Deep learning models (DLMs) are state-of-the-art techniques in speech recognition. However, training good DLMs can be time consuming especially for production-size models and corpora. Although several parallel training algorithms have been proposed to improve training efficiency, there is no clear guidance on which one to choose for the task in hand due to lack of systematic and fair comparison among them. In this paper we aim at filling this gap by comparing four popular parallel training algorithms in speech recognition, namely asynchronous stochastic gradient descent (ASGD), blockwise model…
There are multiple sides to every story, and while statistical topic models have been highly successful at topically summarizing the stories in corpora of text documents, they do not explicitly address the issue of learning the different sides, the viewpoints, expressed in the documents. In this paper, we show how these viewpoints can be learned completely unsupervised and represented in a human interpretable form. We use a novel approach of applying CorrLDA2 for this purpose, which learns topic-viewpoint relations that can be used to form groups of topics, where each group represents a viewpo…
Siemens AG（西门子股份公司）；University of Munich (LMU)（慕尼黑大学（LMU））
Though word embeddings and topics are complementary representations, several past works have only used pre-trained word embeddings in (neural) topic modeling to address data sparsity problem in short text or small collection of documents. However, no prior work has employed (pre-trained latent) topics in transfer learning paradigm. In this paper, we propose an approach to (1) perform knowledge transfer using latent topics obtained from a large source corpus, and (2) jointly transfer knowledge via the two representations (or views) in neural topic modeling to improve topic quality, better deal …
