Most of the internet today is composed of digital media that includes videos and images. With pixels becoming the currency in which most transactions happen on the internet, it is becoming increasingly important to have a way of browsing through this ocean of information with relative ease. YouTube has 400 hours of video uploaded every minute and many million images are browsed on Instagram, Facebook, etc. Inspired by recent advances in the field of deep learning and success that it has gained on various problems like image captioning and, machine translation , word2vec , skip thoughts, etc, we present DeepSeek a natural language processing based deep learning model that allows users to enter a description of the kind of images that they want to search, and in response the system retrieves all the images that semantically and contextually relate to the query. Two approaches are described in the following sections.
Building Machine Translation (MT) systems for low-resource languages remains challenging. For many language pairs, parallel data are not widely available, and in such cases MT models do not achieve results comparable to those seen with high-resource languages. When data are scarce, it is of paramount importance to make optimal use of the limited material available. To that end, in this paper we propose employing the same parallel sentences multiple times, only changing the way the words are split each time. For this purpose we use several Byte Pair Encoding models, with various merge operations used in their configuration. In our experiments, we use this technique to expand the available data and improve an MT system involving a low-resource language pair, namely English-Esperanto. As an additional contribution, we made available a set of English-Esperanto parallel data in the literary domain.
Video description involves the generation of the natural language description of actions, events, and objects in the video. There are various applications of video description by filling the gap between languages and vision for visually impaired people, generating automatic title suggestion based on content, browsing of the video based on the content and video-guided machine translation [86] etc.In the past decade, several works had been done in this field in terms of approaches/methods for video description, evaluation metrics,and datasets. For analyzing the progress in the video description task, a comprehensive survey is needed that covers all the phases of video description approaches with a special focus on recent deep learning approaches. In this work, we report a comprehensive survey on the phases of video description approaches, the dataset for video description, evaluation metrics, open competitions for motivating the research on the video description, open challenges in this field, and future research directions. In this survey, we cover the state-of-the-art approaches proposed for each and every dataset with their pros and cons. For the growth of this research domain,the availability of numerous benchmark dataset is a basic need. Further, we categorize all the dataset into two classes: open domain dataset and domain-specific dataset. From our survey, we observe that the work in this field is in fast-paced development since the task of video description falls in the intersection of computer vision and natural language processing. But still, the work in the video description is far from saturation stage due to various challenges like the redundancy due to similar frames which affect the quality of visual features, the availability of dataset containing more diverse content and availability of an effective evaluation metric.
Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT' 16 En-De.
In this chapter we build a machine translation (MT) system tailored to the literary domain, specifically to novels, based on the state-of-the-art architecture in neural MT (NMT), the Transformer (Vaswani et al., 2017), for the translation direction English-to-Catalan. Subsequently, we assess to what extent such a system can be useful by evaluating its translations, by comparing this MT system against three other systems (two domain-specific systems under the recurrent and phrase-based paradigms and a popular generic on-line system) on three evaluations. The first evaluation is automatic and uses the most-widely used automatic evaluation metric, BLEU. The two remaining evaluations are manual and they assess, respectively, preference and amount of post-editing required to make the translation error-free. As expected, the domain-specific Transformer-based system outperformed the three other systems in all the three evaluations conducted, in all cases by a large margin.
Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages, for improving machine translation and other multi-lingual applications. Current unsupervised approaches rely on similarities in geometric structure of word embedding spaces across languages, to learn structure-preserving linear transformations using adversarial networks and refinement strategies. However, such techniques, in practice, tend to suffer from instability and convergence issues, requiring tedious fine-tuning for precise parameter setting. This paper proposes BioSpere, a novel framework for unsupervised mapping of bi-lingual word embeddings onto a shared vector space, by combining adversarial initialization and refinement procedure with point set registration algorithm used in image processing. We show that our framework alleviates the shortcomings of existing methodologies, and is relatively invariant to variable adversarial learning performance, depicting robustness in terms of parameter choices and training losses. Experimental evaluation on parallel dictionary induction task demonstrates state-of-the-art results for our framework on diverse language pairs.
Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers employ a variety of heuristic techniques, including searching for the conditional mode (vs. sampling) and incorporating various training heuristics (e.g., label smoothing). While search strategies significantly improve BLEU score, they yield deterministic outputs that lack the diversity of human translations. Moreover, search tends to bias the distribution of translated gender pronouns. This makes human-level BLEU a misleading benchmark in that modern MT systems cannot approach human-level BLEU while simultaneously maintaining human-level translation diversity. In this paper, we characterize distributional differences between generated and real translations, examining the cost in diversity paid for the BLEU scores enjoyed by NMT. Moreover, our study implicates search as a salient source of known bias when translating gender pronouns.
Automated generate-and-validate (GV) program repair techniques (APR) typically rely on hard-coded rules, thus only fixing bugs following specific fix patterns. These rules require a significant amount of manual effort to discover and it is hard to adapt these rules to different programming languages. To address these challenges, we propose a new G&V technique—CoCoNuT, which uses ensemble learning on the combination of convolutional neural networks (CNNs) and a new context-aware neural machine translation (NMT) architecture to automatically fix bugs in multiple programming languages. To better represent the context of a bug, we introduce a new context-aware NMT architecture that represents the buggy source code and its surrounding context separately. CoCoNuT uses CNNs instead of recurrent neural networks (RNNs), since CNN layers can be stacked to extract hierarchical features and better model source code at different granularity levels (e.g., statements and functions). In addition, CoCoNuT takes advantage of the randomness in hyperparameter tuning to build multiple models that fix different bugs and combines these models using ensemble learning to fix more bugs. Our evaluation on six popular benchmarks for four programming languages (Java, C, Python, and JavaScript) shows that CoCoNuT correctly fixes (i.e., the first generated patch is semantically equivalent to the developer’s patch) 509 bugs, including 309 bugs that are fixed by none of the 27 techniques with which we compare.
The term natural language refers to any system of symbolic communication (spoken, signed or written) without intentional human planning and design. This distinguishes natural languages such as Arabic and Japanese from artificially constructed languages such as Esperanto or Python. Natural language processing (NLP) is the sub-field of artificial intelligence (AI) focused on modeling natural languages to build applications such as speech recognition and synthesis, machine translation, optical character recognition (OCR), sentiment analysis (SA), question answering, dialogue systems, etc. NLP is a highly interdisciplinary field with connections to computer science, linguistics, cognitive science, psychology, mathematics and others. Some of the earliest AI applications were in NLP (e.g., machine translation); and the last decade (2010-2020) in particular has witnessed an incredible increase in quality, matched with a rise in public awareness, use, and expectations of what may have seemed like science fiction in the past. NLP researchers pride themselves on developing language independent models and tools that can be applied to all human languages, e.g. machine translation systems can be built for a variety of languages using the same basic mechanisms and models. However, the reality is that some languages do get more attention (e.g., English and Chinese) than others (e.g., Hindi and Swahili). Arabic, the primary language of the Arab world and the religious language of millions of non-Arab Muslims is somewhere in the middle of this continuum. Though Arabic NLP has many challenges, it has seen many successes and developments. Next we discuss Arabic's main challenges as a necessary background, and we present a brief history of Arabic NLP. We then survey a number of its research areas, and close with a critical discussion of the future of Arabic NLP.
Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation, i.e., both source-to-target and target-to-source translation using a single model. If we exclude some pioneering attempts, such as multilingual systems, all other bidirectional translation approaches are required to train two individual models. This paper proposes to build a single end-to-end bidirectional translation model using a two-dimensional grid, where the left-to-right decoding generates source-to-target, and the bottom-to-up decoding creates target-to-source output. Instead of training two models independently, our approach encourages a single network to jointly learn to translate in both directions. Experiments on the WMT 2018 German$\leftrightarrow$English and Turkish$\leftrightarrow$English translation tasks show that the proposed model is capable of generating a good translation quality and has sufficient potential to direct the research.
In this thesis, we propose a multitask learning based method to improve Neural Sign Language Translation (NSLT) consisting of two parts, a tokenization layer and Neural Machine Translation (NMT). The tokenization part focuses on how Sign Language (SL) videos should be represented to be fed into the other part. It has not been studied elaborately whereas NMT research has attracted several researchers contributing enormous advancements. Up to now, there are two main input tokenization levels, namely frame-level and gloss-level tokenization. Glosses are world-like intermediate presentation and unique to SLs. Therefore, we aim to develop a generic sign-level tokenization layer so that it is applicable to other domains without further effort. We begin with investigating current tokenization approaches and explain their weaknesses with several experiments. To provide a solution, we adapt Transfer Learning, Multitask Learning and Unsupervised Domain Adaptation into this research to leverage additional supervision. We succeed in enabling knowledge transfer between SLs and improve translation quality by 5 points in BLEU-4 and 8 points in ROUGE scores. Secondly, we show the effects of body parts by extensive experiments in all the tokenization approaches. Apart from these, we adopt 3D-CNNs to improve efficiency in terms of time and space. Lastly, we discuss the advantages of sign-level tokenization over gloss-level tokenization. To sum up, our proposed method eliminates the need for gloss level annotation to obtain higher scores by providing additional supervision by utilizing weak supervision sources.
Recent advances in natural language processing have enabled automation of a wide range of tasks, including machine translation, named entity recognition, and sentiment analysis. Automated summarization of documents, or groups of documents, however, has remained elusive, with many efforts limited to extraction of keywords, key phrases, or key sentences. Accurate abstractive summarization has yet to be achieved due to the inherent difficulty of the problem, and limited availability of training data. In this paper, we propose a topic-centric unsupervised multi-document summarization framework to generate extractive and abstractive summaries for groups of scientific articles across 20 Fields of Study (FoS) in Microsoft Academic Graph (MAG) and news articles from DUC-2004 Task 2. The proposed algorithm generates an abstractive summary by developing salient language unit selection and text generation techniques. Our approach matches the state-of-the-art when evaluated on automated extractive evaluation metrics and performs better for abstractive summarization on five human evaluation metrics (entailment, coherence, conciseness, readability, and grammar). We achieve a kappa score of 0.68 between two co-author linguists who evaluated our results. We plan to publicly share MAG-20, a human-validated gold standard dataset of topic-clustered research articles and their summaries to promote research in abstractive summarization.
Pre-training models on vast quantities of unlabeled data has emerged as an effective approach to improving accuracy on many NLP tasks. On the other hand, traditional machine translation has a long history of leveraging unlabeled data through noisy channel modeling. The same idea has recently been shown to achieve strong improvements for neural machine translation. Unfortunately, na\"{i}ve noisy channel modeling with modern sequence to sequence models is up to an order of magnitude slower than alternatives. We address this issue by introducing efficient approximations to make inference with the noisy channel approach as fast as strong ensembles while increasing accuracy. We also show that the noisy channel approach can outperform strong pre-training results by achieving a new state of the art on WMT Romanian-English translation.
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of access to the full sequence and the quadratically growing computational cost concerning the sequence length. These characteristics pose challenges, especially for low-latency scenarios, where the system is often required to be streaming. In this paper, we build a compact and streaming speech recognition system on top of the end-to-end neural transducer architecture with attention-based modules augmented with convolution. The proposed system equips the end-to-end models with the streaming capability and reduces the large footprint from the streaming attention-based model using augmented memory. On the LibriSpeech dataset, our proposed system achieves word error rates 2.7% on test-clean and 5.8% on test-other, to our best knowledge the lowest among streaming approaches reported so far.
Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have explored using the readily available monolingual data in either or both of the languages to improve the standard of translation models in low, and even high, resource languages. One of the most successful of such works is the back-translation that utilizes the translations of the target language monolingual data to increase the amount of the training data. The quality of the backward model which is trained on the available parallel data has been shown to determine the performance of the back-translation approach. Despite this, only the forward model is improved on the monolingual target data in standard back-translation. A previous study proposed an iterative back-translation approach for improving both models over several iterations. But unlike in the traditional back-translation, it relied on both the target and source monolingual data. This work, therefore, proposes a novel approach that enables both the backward and forward models to benefit from the monolingual target data through a hybrid of self-learning and back-translation respectively. Experimental results have shown the superiority of the proposed approach over the traditional back-translation method on English-German low resource neural machine translation. We also proposed an iterative self-learning approach that outperforms the iterative back-translation while also relying only on the monolingual target data and require the training of less models.
Most prior art in visual understanding relies solely on analyzing the "what" (e.g., event recognition) and "where" (e.g., event localization), which in some cases, fails to describe correct contextual relationships between events or leads to incorrect underlying visual attention. Part of what defines us as human and fundamentally different from machines is our instinct to seek causality behind any association, say an event Y that happened as a direct result of event X. To this end, we propose iPerceive, a framework capable of understanding the "why" between events in a video by building a common-sense knowledge base using contextual cues to infer causal relationships between objects in the video. We demonstrate the effectiveness of our technique using the dense video captioning (DVC) and video question answering (VideoQA) tasks. Furthermore, while most prior work in DVC and VideoQA relies solely on visual information, other modalities such as audio and speech are vital for a human observer's perception of an environment. We formulate DVC and VideoQA tasks as machine translation problems that utilize multiple modalities. By evaluating the performance of iPerceive DVC and iPerceive VideoQA on the ActivityNet Captions and TVQA datasets respectively, we show that our approach furthers the state-of-the-art. Code and samples are available at: iperceive.amanchadha.com.
We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive sequence generation (Gu et al., 2019), EDITOR generates new sequences by iteratively editing hypotheses. It relies on a novel reposition operation designed to disentangle lexical choice from word positioning decisions, while enabling efficient oracles for imitation learning and parallel edits at decoding time. Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer (Gu et al., 2019) while speeding up decoding dramatically compared to constrained beam search (Post and Vilar, 2018). EDITOR also achieves comparable or better translation quality with faster decoding speed than the Levenshtein Transformer on standard Romanian-English, English-German, and English-Japanese machine translation tasks.
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the out-put pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM; Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical results on five translation tasks show that compared with CMLM, our method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5xspeedup. Further analysis indicates that our method reduces repeated translations and performs better at longer sentences.
Neural Machine Translation (NMT) on logographic source languages struggles when translating `unseen' characters, which never appear in the training data. One possible approach to this problem uses sub-character decomposition for training and test sentences. However, this approach involves complete retraining, and its effectiveness for unseen character translation to non-logographic languages has not been fully explored. We investigate existing ideograph-based sub-character decomposition approaches for Chinese-to-English and Japanese-to-English NMT, for both high-resource and low-resource domains. For each language pair and domain we construct a test set where all source sentences contain at least one unseen logographic character. We find that complete sub-character decomposition often harms unseen character translation, and gives inconsistent results generally. We offer a simple alternative based on decomposition before inference for unseen characters only. Our approach allows flexible application, achieving translation adequacy improvements and requiring no additional models or training.
In this paper, as a case study, we present a systematic study of gender bias in machine translation with Google Translate. We translated sentences containing names of occupations from Hungarian, a language with gender-neutral pronouns, into English. Our aim was to present a fair measure for bias by comparing the translations to an optimal non-biased translator. When assessing bias, we used the following reference points: (1) the distribution of men and women among occupations in both the source and the target language countries, as well as (2) the results of a Hungarian survey that examined if certain jobs are generally perceived as feminine or masculine. We also studied how expanding sentences with adjectives referring to occupations effect the gender of the translated pronouns. As a result, we found bias against both genders, but biased results against women are much more frequent. Translations are closer to our perception of occupations than to objective occupational statistics. Finally, occupations have a greater effect on translation than adjectives.