What are the units of text that we want to model? From bytes to multi-word expressions, text can be analyzed and generated at many granularities. Until recently, most natural language processing (NLP) models operated over words, treating those as discrete and atomic tokens, but starting with byte-pair encoding (BPE), subword-based approaches have become dominant in many areas, enabling small vocabularies while still allowing for fast inference. Is the end of the road character-level model or byte-level processing? In this survey, we connect several lines of work from the pre-neural and neural era, by showing how hybrid approaches of words and characters as well as subword-based approaches based on learned segmentation have been proposed and evaluated. We conclude that there is and likely will never be a silver bullet singular solution for all applications and that thinking seriously about tokenization remains important for many applications.
Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often modeled separately. Here, we test how encoding and decoding of lexical semantic information can emerge automatically from raw speech in unsupervised generative deep convolutional networks that combine the production and perception principles of speech. We introduce, to our knowledge, the most challenging objective in unsupervised lexical learning: a network that must learn unique representations for lexical items with no direct access to training data. We train several models (ciwGAN and fiwGAN arXiv:2006.02951) and test how the networks classify acoustic lexical items in unobserved test data. Strong evidence in favor of lexical learning and a causal relationship between latent codes and meaningful sublexical units emerge. The architecture that combines the production and perception principles is thus able to learn to decode unique information from raw acoustic data without accessing real training data directly. We propose a technique to explore lexical (holistic) and sublexical (featural) learned representations in the classifier network. The results bear implications for unsupervised speech technology, as well as for unsupervised semantic modeling as language models increasingly bypass text and operate from raw acoustics.
We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA and NLVR2. The code and pretrained models are available at https://aka.ms/vlmo.
This paper presents an improved classification model for Igbo text using N-gram and K-Nearest Neighbour approaches. The N-gram model was used for text representation and the classification was carried out on the text using the K-Nearest Neighbour model. Object-Oriented design methodology is used for the work and is implemented with the Python programming language with tools from Natural Language Toolkit (NLTK). The performance of the Igbo text classification system is measured by computing the precision, recall and F1-measure of the result obtained on Unigram, Bigram and Trigram represented text. The Igbo text classification on bigram represented text has highest degree of exactness (precision); result obtained with three N-gram models has the same level of completeness (recall) while trigram has the lowest level of precision. This shows that the classification on bigram Igbo represented text outperforms unigram and trigram represented texts. Therefore, bigram text representation model is highly recommended for any intelligent text-based system in Igbo language.
The task of Human-Object Interaction~(HOI) detection could be divided into two core problems, i.e., human-object association and interaction understanding. In this paper, we reveal and address the disadvantages of the conventional query-driven HOI detectors from the two aspects. For the association, previous two-branch methods suffer from complex and costly post-matching, while single-branch methods ignore the features distinction in different tasks. We propose Guided-Embedding Network~(GEN) to attain a two-branch pipeline without post-matching. In GEN, we design an instance decoder to detect humans and objects with two independent query sets and a position Guided Embedding~(p-GE) to mark the human and object in the same position as a pair. Besides, we design an interaction decoder to classify interactions, where the interaction queries are made of instance Guided Embeddings (i-GE) generated from the outputs of each instance decoder layer. For the interaction understanding, previous methods suffer from long-tailed distribution and zero-shot discovery. This paper proposes a Visual-Linguistic Knowledge Transfer (VLKT) training strategy to enhance interaction understanding by transferring knowledge from a visual-linguistic pre-trained model CLIP. In specific, we extract text embeddings for all labels with CLIP to initialize the classifier and adopt a mimic loss to minimize the visual feature distance between GEN and CLIP. As a result, GEN-VLKT outperforms the state of the art by large margins on multiple datasets, e.g., +5.05 mAP on HICO-Det. The source codes are available at https://github.com/YueLiao/gen-vlkt.
Temporal and causal relations play an important role in determining the dependencies between events. Classifying the temporal and causal relations between events has many applications, such as generating event timelines, event summarization, textual entailment and question answering. Temporal and causal relations are closely related and influence each other. So we propose a joint model that incorporates both temporal and causal features to perform causal relation classification. We use the syntactic structure of the text for identifying temporal and causal relations between two events from the text. We extract parts-of-speech tag sequence, dependency tag sequence and word sequence from the text. We propose an LSTM based model for temporal and causal relation classification that captures the interrelations between the three encoded features. Evaluation of our model on four popular datasets yields promising results for temporal and causal relation classification.
Beam search is an effective and widely used decoding algorithm in many sequence-to-sequence (seq2seq) text generation tasks. However, in open-ended text generation, beam search is often found to produce repetitive and generic texts, sampling-based decoding algorithms like top-k sampling and nucleus sampling are more preferred. Standard seq2seq models suffer from label bias due to its locally normalized probability formulation. This paper provides a series of empirical evidence that label bias is a major reason for such degenerate behaviors of beam search. By combining locally normalized maximum likelihood estimation and globally normalized sequence-level training, label bias can be reduced with almost no sacrifice in perplexity. To quantitatively measure label bias, we test the model's ability to discriminate the groundtruth text and a set of context-agnostic distractors. We conduct experiments on large-scale response generation datasets. Results show that beam search can produce more diverse and meaningful texts with our approach, in terms of both automatic and human evaluation metrics. Our analysis also suggests several future working directions towards the grand challenge of open-ended text generation.
The article is focused on automatic development and ranking of a large corpus for Russian paraphrase generation which proves to be the first corpus of such type in Russian computational linguistics. Existing manually annotated paraphrase datasets for Russian are limited to small-sized ParaPhraser corpus and ParaPlag which are suitable for a set of NLP tasks, such as paraphrase and plagiarism detection, sentence similarity and relatedness estimation, etc. Due to size restrictions, these datasets can hardly be applied in end-to-end text generation solutions. Meanwhile, paraphrase generation requires a large amount of training data. In our study we propose a solution to the problem: we collect, rank and evaluate a new publicly available headline paraphrase corpus (ParaPhraser Plus), and then perform text generation experiments with manual evaluation on automatically ranked corpora using the Universal Transformer architecture.
Government-sponsored policy-making and scheme generations is one of the means of protecting and promoting the social, economic, and personal development of the citizens. The evaluation of effectiveness of these schemes done by government only provide the statistical information in terms of facts and figures which do not include the in-depth knowledge of public perceptions, experiences and views on the topic. In this research work, we propose an improved text classification framework that classifies the Twitter data of different health-based government schemes. The proposed framework leverages the language representation models (LR models) BERT, ELMO, and USE. However, these LR models have less real-time applicability due to the scarcity of the ample annotated data. To handle this, we propose a novel GloVe word embeddings and class-specific sentiments based text augmentation approach (named Mod-EDA) which boosts the performance of text classification task by increasing the size of labeled data. Furthermore, the trained model is leveraged to identify the level of engagement of citizens towards these policies in different communities such as middle-income and low-income groups.
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative ability of the shared encoder and the performance during the rescoring stage. (2) We introduce an n-gram based language model and a WFST-based decoder into WeNet 2.0, promoting the use of rich text data in production scenarios. (3) We design a unified contextual biasing framework, which leverages user-specific context (e.g., contact lists) to provide rapid adaptation ability for production and improves ASR accuracy in both with-LM and without-LM scenarios. (4) We design a unified IO to support large-scale data for effective model training. In summary, the brand-new WeNet 2.0 achieves up to 10\% relative recognition performance improvement over the original WeNet on various corpora and makes available several important production-oriented features.