Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Improving N-gram Language Models with Pre-trained Deep Transformer

Nov 22, 2019
Yiren Wang, Hongzhao Huang, Zhe Liu, Yutong Pang, Yongqiang Wang, ChengXiang Zhai, Fuchun Peng

Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be improved by neural LMs through a text generation based data augmentation method. In contrast to previous approaches, we employ a large-scale general domain pre-training followed by in-domain fine-tuning strategy to construct deep Transformer based neural LMs. Large amount of in-domain text data is generated with the well trained deep Transformer to construct new n-gram LMs, which are then interpolated with baseline n-gram systems. Empirical studies on different speech recognition tasks show that the proposed approach can effectively improve recognition accuracy. In particular, our proposed approach brings significant relative word error rate reduction up to 6.0% for domains with limited in-domain data.

  Access Paper or Ask Questions

Predicting the Leading Political Ideology of YouTube Channels Using Acoustic, Textual, and Metadata Information

Oct 20, 2019
Yoan Dinkov, Ahmed Ali, Ivan Koychev, Preslav Nakov

We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.

* media bias, political ideology, Youtube channels, propaganda, disinformation, fake news 

  Access Paper or Ask Questions

Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling

Jun 20, 2019
Robert L. Logan IV, Nelson F. Liu, Matthew E. Peters, Matt Gardner, Sameer Singh

Modeling human language requires the ability to not only generate fluent text but also encode factual knowledge. However, traditional language models are only capable of remembering facts seen at training time, and often have difficulty recalling them. To address this, we introduce the knowledge graph language model (KGLM), a neural language model with mechanisms for selecting and copying facts from a knowledge graph that are relevant to the context. These mechanisms enable the model to render information it has never seen before, as well as generate out-of-vocabulary tokens. We also introduce the Linked WikiText-2 dataset, a corpus of annotated text aligned to the Wikidata knowledge graph whose contents (roughly) match the popular WikiText-2 benchmark. In experiments, we demonstrate that the KGLM achieves significantly better performance than a strong baseline language model. We additionally compare different language model's ability to complete sentences requiring factual knowledge, showing that the KGLM outperforms even very large language models in generating facts.

  Access Paper or Ask Questions

Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading

Jun 07, 2019
Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, Bill Dolan, Yejin Choi, Jianfeng Gao

Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading. The key idea is to provide the conversation model with relevant long-form text on the fly as a source of external knowledge. The model performs QA-style reading comprehension on this text in response to each conversational turn, thereby allowing for more focused integration of external knowledge than has been possible in prior approaches. To support further research on knowledge-grounded conversation, we introduce a new large-scale conversation dataset grounded in external web pages (2.8M turns, 7.4M sentences of grounding). Both human evaluation and automated metrics show that our approach results in more contentful responses compared to a variety of previous methods, improving both the informativeness and diversity of generated output.

* ACL 2019 long paper 

  Access Paper or Ask Questions

Open Information Extraction from Question-Answer Pairs

Apr 06, 2019
Nikita Bhutani, Yoshihiko Suhara, Wang-Chiew Tan, Alon Halevy, H. V. Jagadish

Open Information Extraction (OpenIE) extracts meaningful structured tuples from free-form text. Most previous work on OpenIE considers extracting data from one sentence at a time. We describe NeurON, a system for extracting tuples from question-answer pairs. Since real questions and answers often contain precisely the information that users care about, such information is particularly desirable to extend a knowledge base with. NeurON addresses several challenges. First, an answer text is often hard to understand without knowing the question, and second, relevant information can span multiple sentences. To address these, NeurON formulates extraction as a multi-source sequence-to-sequence learning task, wherein it combines distributed representations of a question and an answer to generate knowledge facts. We describe experiments on two real-world datasets that demonstrate that NeurON can find a significant number of new and interesting facts to extend a knowledge base compared to state-of-the-art OpenIE methods.

* NAACL 2019 

  Access Paper or Ask Questions

Topic Diffusion Discovery based on Sparseness-constrained Non-negative Matrix Factorization

Jul 12, 2018
Yihuang Kang, Keng-Pei Lin, I-Ling Cheng

Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities. Various scholarly search websites, citation recommendation engines, and research databases have been created to simplify the text search tasks. However, it is still difficult for researchers to be able to identify potential research topics without doing intensive reviews on a tremendous number of articles published by journals, conferences, meetings, and workshops. In this paper, we consider a novel topic diffusion discovery technique that incorporates sparseness-constrained Non-negative Matrix Factorization with generalized Jensen-Shannon divergence to help understand term-topic evolutions and identify topic diffusions. Our experimental result shows that this approach can extract more prominent topics from large article databases, visualize relationships between terms of interest and abstract topics, and further help researchers understand whether given terms/topics have been widely explored or whether new topics are emerging from literature.

  Access Paper or Ask Questions

LV-ROVER: Lexicon Verified Recognizer Output Voting Error Reduction

Jul 24, 2017
Bruno Stuner, Clément Chatelain, Thierry Paquet

Offline handwritten text line recognition is a hard task that requires both an efficient optical character recognizer and language model. Handwriting recognition state of the art methods are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN) coupled with the use of linguistic knowledge. Most of the proposed approaches in the literature focus on improving one of the two components and use constraint, dedicated to a database lexicon. However, state of the art performance is achieved by combining multiple optical models, and possibly multiple language models with the Recognizer Output Voting Error Reduction (ROVER) framework. Though handwritten line recognition with ROVER has been implemented by combining only few recognizers because training multiple complete recognizers is hard. In this paper we propose a Lexicon Verified ROVER: LV-ROVER, that has a reduce complexity compare to the original one and that can combine hundreds of recognizers without language models. We achieve state of the art for handwritten line text on the RIMES dataset.

* Submitted to Pattern Recognition Letters 

  Access Paper or Ask Questions

Deep Memory Networks for Attitude Identification

Jan 16, 2017
Cheng Li, Xiaoxiao Guo, Qiaozhu Mei

We consider the task of identifying attitudes towards a given set of entities from text. Conventionally, this task is decomposed into two separate subtasks: target detection that identifies whether each entity is mentioned in the text, either explicitly or implicitly, and polarity classification that classifies the exact sentiment towards an identified entity (the target) into positive, negative, or neutral. Instead, we show that attitude identification can be solved with an end-to-end machine learning architecture, in which the two subtasks are interleaved by a deep memory network. In this way, signals produced in target detection provide clues for polarity classification, and reversely, the predicted polarity provides feedback to the identification of targets. Moreover, the treatments for the set of targets also influence each other -- the learned representations may share the same semantics for some targets but vary for others. The proposed deep memory network, the AttNet, outperforms methods that do not consider the interactions between the subtasks or those among the targets, including conventional machine learning methods and the state-of-the-art deep learning models.

* Accepted to WSDM'17 

  Access Paper or Ask Questions