This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we create an artificial dataset for data deduplication using English Wikipedia articles. Area-Under-Curve (AUC) over 0.9 were observed for most models, with the best model reaching 0.96. Deduplication enables more effective model training by preventing the model from learning a distribution that differs from the real one as a result of the repeated data.
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes. Existing generators suffer from poor visual grounding, causing them to rely on language priors and hallucinate objects. Our MARKY-MT5 system addresses this by focusing on visual landmarks; it comprises a first stage landmark detector and a second stage generator -- a multimodal, multilingual, multitask encoder-decoder. To train it, we bootstrap grounded landmark annotations on top of the Room-across-Room (RxR) dataset. Using text parsers, weak supervision from RxR's pose traces, and a multilingual image-text encoder trained on 1.8b images, we identify 1.1m English, Hindi and Telugu landmark descriptions and ground them to specific regions in panoramas. On Room-to-Room, human wayfinders obtain success rates (SR) of 71% following MARKY-MT5's instructions, just shy of their 75% SR following human instructions -- and well above SRs with other generators. Evaluations on RxR's longer, diverse paths obtain 61-64% SRs on three languages. Generating such high-quality navigation instructions in novel environments is a step towards conversational navigation tools and could facilitate larger-scale training of instruction-following agents.
This paper presents the VRAIN-UPV MLLP's speech synthesis system for the SH1 task of the Blizzard Challenge 2021. The SH1 task consisted in building a Spanish text-to-speech system trained on (but not limited to) the corpus released by the Blizzard Challenge 2021 organization. It included 5 hours of studio-quality recordings from a native Spanish female speaker. In our case, this dataset was solely used to build a two-stage neural text-to-speech pipeline composed of a non-autoregressive acoustic model with explicit duration modeling and a HiFi-GAN neural vocoder. Our team is identified as J in the evaluation results. Our system obtained very good results in the subjective evaluation tests. Only one system among other 11 participants achieved better naturalness than ours. Concretely, it achieved a naturalness MOS of 3.61 compared to 4.21 for real samples.
Text detection enables us to extract rich information from images. In this paper, we focus on how to generate bounding boxes that are appropriate to grasp text areas on books to help implement automatic text detection. We attempt not to improve a learning-based model by training it with an enough amount of data in the target domain but to leverage it, which has been already trained with another domain data. We develop algorithms that construct the bounding boxes by improving and leveraging the results of a learning-based method. Our algorithms can utilize different learning-based approaches to detect scene texts. Experimental evaluations demonstrate that our algorithms work well in various situations where books are roughly placed.
People vary in their ability to make accurate predictions about the future. Prior studies have shown that some individuals can predict the outcome of future events with consistently better accuracy. This leads to a natural question: what makes some forecasters better than others? In this paper we explore connections between the language people use to describe their predictions and their forecasting skill. Datasets from two different forecasting domains are explored: (1) geopolitical forecasts from Good Judgment Open, an online prediction forum and (2) a corpus of company earnings forecasts made by financial analysts. We present a number of linguistic metrics which are computed over text associated with people's predictions about the future including: uncertainty, readability, and emotion. By studying linguistic factors associated with predictions, we are able to shed some light on the approach taken by skilled forecasters. Furthermore, we demonstrate that it is possible to accurately predict forecasting skill using a model that is based solely on language. This could potentially be useful for identifying accurate predictions or potentially skilled forecasters earlier.
Many thousands of patent applications arrive at patent offices around the world every day. One important subtask when a patent application is submitted is to assign one or more classification codes from the complex and hierarchical patent classification schemes that will enable routing of the patent application to a patent examiner who is knowledgeable about the specific technical field. This task is typically undertaken by patent professionals, however due to the large number of applications and the potential complexity of an invention, they are usually overwhelmed. Therefore, there is a need for this code assignment manual task to be supported or even fully automated by classification systems that will classify patent applications, hopefully with an accuracy close to patent professionals. Like in many other text analysis problems, in the last years, this intellectually demanding task has been studied using word embeddings and deep learning techniques. In this paper we shortly review these research efforts and experiment with similar deep learning techniques using different feature representations on automatic patent classification in the level of sub-classes. On top of that, we present an innovative method of ensemble classifiers trained with different parts of the patent document. To the best of our knowledge, this is the first time that an ensemble method was proposed for the patent classification problem. Our first results are quite promising showing that an ensemble architecture of classifiers significantly outperforms current state-of-the-art techniques using the same classifiers as standalone solutions.
In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perfectly aligns with the original tasks BERT/RoBERTa is trained on, and hence we avoid any ad-hoc pooling or additional encoding layers which are necessary in prior approaches. Experiments on the WikiSQL dataset show that the proposed approach is very effective, achieving the top place on the leaderboard.
The increasing accessibility of the internet facilitated social media usage and encouraged individuals to express their opinions liberally. Nevertheless, it also creates a place for content polluters to disseminate offensive posts or contents. Most of such offensive posts are written in a cross-lingual manner and can easily evade the online surveillance systems. This paper presents an automated system that can identify offensive text from multilingual code-mixed data. In the task, datasets provided in three languages including Tamil, Malayalam and Kannada code-mixed with English where participants are asked to implement separate models for each language. To accomplish the tasks, we employed two machine learning techniques (LR, SVM), three deep learning (LSTM, LSTM+Attention) techniques and three transformers (m-BERT, Indic-BERT, XLM-R) based methods. Results show that XLM-R outperforms other techniques in Tamil and Malayalam languages while m-BERT achieves the highest score in the Kannada language. The proposed models gained weighted $f_1$ score of $0.76$ (for Tamil), $0.93$ (for Malayalam), and $0.71$ (for Kannada) with a rank of $3^{rd}$, $5^{th}$ and $4^{th}$ respectively.
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph topology as all nodes are connected. In contrast, local node encoding considers the relations between directly connected nodes capturing the graph structure, but it can fail to capture long-range relations. In this work, we gather the best of both encoding strategies, proposing novel models that encode an input graph combining both global and local node contexts. Our approaches are able to learn better contextualized node embeddings for text generation. In our experiments, we demonstrate that our models lead to significant improvements in KG-to-text generation, achieving BLEU scores of 17.81 on AGENDA dataset, and 63.10 on the WebNLG dataset for seen categories, outperforming the state of the art by 3.51 and 2.51 points, respectively.
This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing realistic videos conditioned on given texts. Existing video generation methods cannot be easily adapted to handle this task well, due to the frame discontinuity issue and their text-free generation schemes. To address these problems, we propose a recurrent deconvolutional generative adversarial network (RD-GAN), which includes a recurrent deconvolutional network (RDN) as the generator and a 3D convolutional neural network (3D-CNN) as the discriminator. The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information. The proposed model can be jointly trained by pushing the RDN to generate realistic videos so that the 3D-CNN cannot distinguish them from real ones. We apply the proposed RD-GAN to a series of tasks including conventional video generation, conditional video generation, video prediction and video classification, and demonstrate its effectiveness by achieving well performance.