The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen database schemas, also known as the cross-domain Text-to-SQL task. The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learn the mapping between words in the question and tables/columns in the database schema. Focusing on the above two key issues, we propose a Structure-Aware Dual Graph Aggregation Network (SADGA) for cross-domain Text-to-SQL. In SADGA, we adopt the graph structure to provide a unified encoding model for both the natural language question and database schema. Based on the proposed unified modeling, we further devise a structure-aware aggregation method to learn the mapping between the question-graph and schema-graph. The structure-aware aggregation method is featured with Global Graph Linking, Local Graph Linking, and Dual-Graph Aggregation Mechanism. We not only study the performance of our proposal empirically but also achieved 3rd place on the challenging Text-to-SQL benchmark Spider at the time of writing.
Coherence is one of the critical factors that determine the quality of writing. We propose writing relevance (WR) training method for neural encoder-decoder natural language generation (NLG) models which improves coherence of the continuation by leveraging negative examples. WR loss regresses the vector representation of the context and generated sentence toward positive continuation by contrasting it with the negatives. We compare our approach with Unlikelihood (UL) training in a text continuation task on commonsense natural language inference (NLI) corpora to show which method better models the coherence by avoiding unlikely continuations. The preference of our approach in human evaluation shows the efficacy of our method in improving coherence.
Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art models on low or zero resource tasks. Many works in the past have attempted at learning a single massively-multilingual machine translation model for zero-shot translation. Although those translation models are producing correct translations, the main challenge is those models are producing the wrong languages for zero-shot translation. This work and its results indicate that prompt conditioned large models do not suffer from off-target language errors i.e. errors arising due to translation to wrong languages. We empirically demonstrate the effectiveness of self-supervised pre-training and data augmentation for zero-shot multi-lingual machine translation.
The text clustering technique is an unsupervised text mining method which are used to partition a huge amount of text documents into groups. It has been reported that text clustering algorithms are hard to achieve better performance than supervised methods and their clustering performance is highly dependent on the picked text features. Currently, there are many different types of text feature generation algorithms, each of which extracts text features from some specific aspects, such as VSM and distributed word embedding, thus seeking a new way of obtaining features as complete as possible from the corpus is the key to enhance the clustering effects. In this paper, we present a hybrid multisource feature fusion (HMFF) framework comprising three components, feature representation of multimodel, mutual similarity matrices and feature fusion, in which we construct mutual similarity matrices for each feature source and fuse discriminative features from mutual similarity matrices by reducing dimensionality to generate HMFF features, then k-means clustering algorithm could be configured to partition input samples into groups. The experimental tests show our HMFF framework outperforms other recently published algorithms on 7 of 11 public benchmark datasets and has the leading performance on the rest 4 benchmark datasets as well. At last, we compare HMFF framework with those competitors on a COVID-19 dataset from the wild with the unknown cluster count, which shows the clusters generated by HMFF framework partition those similar samples much closer.
This paper describes the experimental framework and results of the IJCB 2022 Mobile Behavioral Biometrics Competition (MobileB2C). The aim of MobileB2C is benchmarking mobile user authentication systems based on behavioral biometric traits transparently acquired by mobile devices during ordinary Human-Computer Interaction (HCI), using a novel public database, BehavePassDB, and a standard experimental protocol. The competition is divided into four tasks corresponding to typical user activities: keystroke, text reading, gallery swiping, and tapping. The data are composed of touchscreen data and several background sensor data simultaneously acquired. "Random" (different users with different devices) and "skilled" (different user on the same device attempting to imitate the legitimate one) impostor scenarios are considered. The results achieved by the participants show the feasibility of user authentication through behavioral biometrics, although this proves to be a non-trivial challenge. MobileB2C will be established as an on-going competition.
Entity relationship extraction envisions the automatic generation of semantic data models from collections of text, by automatic recognition of entities, by association of entities to form relationships, and by classifying these instances to assign them to entity sets (or classes) and relationship sets (or associations). As a first step in this direction, the Lokahi prototype can extract entities based on the TF*IDF measure, and generate semantic relationships based on document-level co-occurrence statistics, for example with likelihood ratios and pointwise mutual information. This paper presents results of an explorative, prototypical, qualitative and synthetic research, summarizes insights from two research projects and, based on this, indicates an outline for further research in the field of entity relationship extraction from text.
Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by augmenting reactive reviews with proactive forecasting. Specifically, we propose a new concept {\it text toxicity propensity} to characterize the extent to which a text tends to attract toxic comments. Beta regression is then introduced to do the probabilistic modeling, which is demonstrated to function well in comprehensive experiments. We also propose an explanation method to communicate the model decision clearly. Both propensity scoring and interpretation benefit text moderation in a novel manner. Finally, the proposed scaling mechanism for the linear model offers useful insights beyond this work.
Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse characteristics, zero-shot adaptive TTS requires strong generalization ability on speaker characteristics, which brings modeling challenges. In this paper, we develop AdaSpeech 4, a zero-shot adaptive TTS system for high-quality speech synthesis. We model the speaker characteristics systematically to improve the generalization on new speakers. Generally, the modeling of speaker characteristics can be categorized into three steps: extracting speaker representation, taking this speaker representation as condition, and synthesizing speech/mel-spectrogram given this speaker representation. Accordingly, we improve the modeling in three steps: 1) To extract speaker representation with better generalization, we factorize the speaker characteristics into basis vectors and extract speaker representation by weighted combining of these basis vectors through attention. 2) We leverage conditional layer normalization to integrate the extracted speaker representation to TTS model. 3) We propose a novel supervision loss based on the distribution of basis vectors to maintain the corresponding speaker characteristics in generated mel-spectrograms. Without any fine-tuning, AdaSpeech 4 achieves better voice quality and similarity than baselines in multiple datasets.
Monitoring progress on the United Nations Sustainable Development Goals (SDGs) is important for both academic and non-academic organizations. Existing approaches to monitoring SDGs have focused on specific data types, namely, publications listed in proprietary research databases. We present the text2sdg R package, a user-friendly, open-source package that detects SDGs in any kind of text data using several different query systems from any text source. The text2sdg package thereby facilitates the monitoring of SDGs for a wide array of text sources and provides a much-needed basis for validating and improving extant methods to detect SDGs from text.
If a picture is worth thousand words, a moving 3d shape must be worth a million. We build upon the success of recent generative methods that create images fitting the semantics of a text prompt, and extend it to the controlled generation of 3d objects. We present a novel algorithm for the creation of textured 3d meshes, controlled by text prompts. Our method creates aesthetically pleasing high resolution articulated 3d meshes, and opens new possibilities for automation and AI control of 3d assets. We call it "ClipMatrix" because it leverages CLIP text embeddings to breed new digital 3d creatures, a nod to the Latin meaning of the word "matrix" - "mother". See the online gallery for a full impression of our method's capability.