Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neural language models to text retrieval and ranking problems have been very promising, but still involve a two-step process in which result candidates are first obtained through bag-of-words-based approaches, and then reranked by a neural transformer. In this paper, we introduce novel approaches for effectively applying neural transformer models to similar text retrieval and ranking without an initial bag-of-words-based step. By eliminating the bag-of-words-based step, our approach is able to accurately retrieve and rank results even when they have no non-stopwords in common with the query. We accomplish this by using bidirectional encoder representations from transformers (BERT) to create vectorized representations of sentence-length texts, along with a vector nearest neighbor search index. We demonstrate both supervised and unsupervised means of using BERT to accomplish this task.
Texts from scene images typically consist of several characters and exhibit a characteristic sequence structure. Existing methods capture the structure with the sequence-to-sequence models by an encoder to have the visual representations and then a decoder to translate the features into the label sequence. In this paper, we study text recognition framework by considering the long-term temporal dependencies in the encoder stage. We demonstrate that the proposed Temporal Convolutional Encoder with increased sequential extents improves the accuracy of text recognition. We also study the impact of different attention modules in convolutional blocks for learning accurate text representations. We conduct comparisons on seven datasets and the experiments demonstrate the effectiveness of our proposed approach.
Testing with quiz questions has proven to be an effective way to assess and improve the educational process. However, manually creating quizzes is tedious and time-consuming. To address this challenge, we present Leaf, a system for generating multiple-choice questions from factual text. In addition to being very well suited for the classroom, Leaf could also be used in an industrial setting, e.g., to facilitate onboarding and knowledge sharing, or as a component of chatbots, question answering systems, or Massive Open Online Courses (MOOCs). The code and the demo are available on https://github.com/KristiyanVachev/Leaf-Question-Generation.
The lack of publicly available text corpora is a major obstacle for progress in clinical natural language processing, for non-English speaking countries in particular. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely distributable German language corpus based on clinical practice guidelines in the field of oncology. The corpus is one of the largest corpora of German medical text to date. It does not contain any patient-related data and can therefore be used without data protection restrictions. Moreover, it is the first corpus for the German language covering diverse conditions in a large medical subfield. In addition to the textual sources, we provide a large variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other medical text corpora.
Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often perform sub-optimally for profane words as they are underrepresented in training corpora and not spoken clearly or completely. Exploration of this problem entirely in the audio domain has largely been limited by the lack of audio datasets. Building on these challenges, we propose ADIMA, a novel, linguistically diverse, ethically sourced, expert annotated and well-balanced multilingual profanity detection audio dataset comprising of 11,775 audio samples in 10 Indic languages spanning 65 hours and spoken by 6,446 unique users. Through quantitative experiments across monolingual and cross-lingual zero-shot settings, we take the first step in democratizing audio based content moderation in Indic languages and set forth our dataset to pave future work.
News recommender systems are used by online news providers to alleviate information overload and to provide personalized content to users. However, algorithmic news curation has been hypothesized to create filter bubbles and to intensify users' selective exposure, potentially increasing their vulnerability to polarized opinions and fake news. In this paper, we show how information on news items' stance and sentiment can be utilized to analyze and quantify the extent to which recommender systems suffer from biases. To that end, we have annotated a German news corpus on the topic of migration using stance detection and sentiment analysis. In an experimental evaluation with four different recommender systems, our results show a slight tendency of all four models for recommending articles with negative sentiments and stances against the topic of refugees and migration. Moreover, we observed a positive correlation between the sentiment and stance bias of the text-based recommenders and the preexisting user bias, which indicates that these systems amplify users' opinions and decrease the diversity of recommended news. The knowledge-aware model appears to be the least prone to such biases, at the cost of predictive accuracy.
In this paper, we introduce a new benchmark dataset for the challenging writing in the air (WiTA) task -- an elaborate task bridging vision and NLP. WiTA implements an intuitive and natural writing method with finger movement for human-computer interaction (HCI). Our WiTA dataset will facilitate the development of data-driven WiTA systems which thus far have displayed unsatisfactory performance -- due to lack of dataset as well as traditional statistical models they have adopted. Our dataset consists of five sub-datasets in two languages (Korean and English) and amounts to 209,926 video instances from 122 participants. We capture finger movement for WiTA with RGB cameras to ensure wide accessibility and cost-efficiency. Next, we propose spatio-temporal residual network architectures inspired by 3D ResNet. These models perform unconstrained text recognition from finger movement, guarantee a real-time operation by processing 435 and 697 decoding frames-per-second for Korean and English, respectively, and will serve as an evaluation standard. Our dataset and the source codes are available at https://github.com/Uehwan/WiTA.
On top of a neural network-based dependency parser and a graph-based natural language processing module we design a Prolog-based dialog engine that explores interactively a ranked fact database extracted from a text document. We reorganize dependency graphs to focus on the most relevant content elements of a sentence and integrate sentence identifiers as graph nodes. Additionally, after ranking the graph we take advantage of the implicit semantic information that dependency links and WordNet bring in the form of subject-verb-object, is-a and part-of relations. Working on the Prolog facts and their inferred consequences, the dialog engine specializes the text graph with respect to a query and reveals interactively the document's most relevant content elements. The open-source code of the integrated system is available at https://github.com/ptarau/DeepRank . Under consideration in Theory and Practice of Logic Programming (TPLP).
Guide dogs play a critical role in the lives of many, however training them is a time- and labor-intensive process. We are developing a method to allow an autonomous robot to physically guide humans using direct human-robot communication. The proposed algorithm will be deployed on a Unitree A1 quadrupedal robot and will autonomously navigate the person to their destination while communicating with the person using a speech interface compatible with the robot. This speech interface utilizes cloud based services such as Amazon Polly and Google Cloud to serve as the text-to-speech and speech-to-text engines.
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing user data), degrades utility (repeated easy-to-memorize text is often low quality), and hurts fairness (some texts are memorized over others). We describe three log-linear relationships that quantify the degree to which LMs emit memorized training data. Memorization significantly grows as we increase (1) the capacity of a model, (2) the number of times an example has been duplicated, and (3) the number of tokens of context used to prompt the model. Surprisingly, we find the situation becomes complicated when generalizing these results across model families. On the whole, we find that memorization in LMs is more prevalent than previously believed and will likely get worse as models continues to scale, at least without active mitigations.