PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1701.06549

Learning to Decode for Future Success

We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of as a simple version of the actor-critic model that uses an interpolation of the actor (the MLE-based token generation policy) and the critic (a value function that estimates the future values of the desired property) for decision making. We demonstrate that the approach is able to incorporate a variety of properties that cannot be handled by standard neural sequence decoders, such as sequence length and backward probability (probability of sources given targets), in addition to yielding consistent improvements in abstractive summarization and machine translation when the property to be optimized is BLEU or ROUGE scores.

arXiv:1701.03214

An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation

In this paper, we propose a novel domain adaptation method named "mixed fine tuning" for neural machine translation (NMT). We combine two existing approaches namely fine tuning and multi domain NMT. We first train an NMT model on an out-of-domain parallel corpus, and then fine tune it on a parallel corpus which is a mix of the in-domain and out-of-domain corpora. All corpora are augmented with artificial tags to indicate specific domains. We empirically compare our proposed method against fine tuning and multi domain methods and discuss its benefits and shortcomings.

arXiv:1702.02429

Trainable Greedy Decoding for Neural Machine Translation

Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-to-end learning algorithms. The problem of decoding, however, has received relatively little attention from the research community. In this paper, we solely focus on the problem of decoding given a trained neural machine translation model. Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding objective. More specifically, we design an actor that observes and manipulates the hidden state of the neural machine translation decoder and propose to train it using a variant of deterministic policy gradient. We extensively evaluate the proposed algorithm using four language pairs and two decoding objectives and show that we can indeed train a trainable greedy decoder that generates a better translation (in terms of a target decoding objective) with minimal computational overhead.

arXiv:1702.01587

A Hybrid Approach For Hindi-English Machine Translation

In this paper, an extended combined approach of phrase based statistical machine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) is proposed to develop a novel hybrid data driven MT system capable of outperforming the baseline SMT, EBMT and RBMT systems from which it is derived. In short, the proposed hybrid MT process is guided by the rule based MT after getting a set of partial candidate translations provided by EBMT and SMT subsystems. Previous works have shown that EBMT systems are capable of outperforming the phrase-based SMT systems and RBMT approach has the strength of generating structurally and morphologically more accurate results. This hybrid approach increases the fluency, accuracy and grammatical precision which improve the quality of a machine translation system. A comparison of the proposed hybrid machine translation (HTM) model with renowned translators i.e. Google, BING and Babylonian is also presented which shows that the proposed model works better on sentences with ambiguity as well as comprised of idioms than others.

arXiv:1610.02209

Morphology Generation for Statistical Machine Translation using Deep Learning Techniques

Morphology in unbalanced languages remains a big challenge in the context of machine translation. In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem. We investigate the morphology simplification with a reasonable trade-off between expected gain and generation complexity. For the Chinese-Spanish task, optimum morphological simplification is in gender and number. For this purpose, we design a new classification architecture which, compared to other standard machine learning techniques, obtains the best results. This proposed neural-based architecture consists of several layers: an embedding, a convolutional followed by a recurrent neural network and, finally, ends with sigmoid and softmax layers. We obtain classification results over 98% accuracy in gender classification, over 93% in number classification, and an overall translation improvement of 0.7 METEOR.

arXiv:1702.03856

Towards speech-to-text translation without speech recognition

We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations. We present the first system for this problem applied to a realistic multi-speaker dataset, the CALLHOME Spanish-English speech translation corpus. Our approach uses unsupervised term discovery (UTD) to cluster repeated patterns in the audio, creating a pseudotext, which we pair with translations to create a parallel text and train a simple bag-of-words MT model. We identify the challenges faced by the system, finding that the difficulty of cross-speaker UTD results in low recall, but that our system is still able to correctly translate some content words in test data.

arXiv:1702.03033

Local System Voting Feature for Machine Translation System Combination

In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network. This work is motivated by the fact that the commonly used binary system voting models only assign each input system a global weight which is responsible for the global impact of each input system on all translations. This prevents individual systems with low system weights from having influence on the system combination output, although in some situations this could be helpful. Further, words which have only been seen by one or few systems rarely have a chance of being present in the combined output. We train a local system voting model by a neural network which is based on the words themselves and the combinatorial occurrences of the different system outputs. This gives system combination the option to prefer other systems at different word positions even for the same sentence.

arXiv:1612.04629공식 코드 · Papers with Code

How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs

Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming. Neural machine translation has the attractive property that it can produce scores for arbitrary translations, and we propose a novel method to assess how well NMT systems model specific linguistic phenomena such as agreement over long distances, the production of novel words, and the faithful translation of polarity. The core idea is that we measure whether a reference translation is more probable under a NMT model than a contrastive translation which introduces a specific type of error. We present LingEval97, a large-scale data set of 97000 contrastive translation pairs based on the WMT English->German translation task, with errors automatically created with simple rules. We report results for a number of systems, and find that recently introduced character-level NMT systems perform better at transliteration than models with byte-pair encoding (BPE) segmentation, but perform more poorly at morphosyntactic agreement, and translating discontiguous units of meaning.

arXiv:1612.03791

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined with the Bayes-risk of the translation according the SMT lattice. This makes our approach much more flexible than $n$-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space. We show an efficient and simple way to integrate risk estimation into the NMT decoder which is suitable for word-level as well as subword-unit-level NMT. We test our method on English-German and Japanese-English and report significant gains over lattice rescoring on several data sets for both single and ensembled NMT. The MBR decoder produces entirely new hypotheses far beyond simply rescoring the SMT search space or fixing UNKs in the NMT output.

arXiv:1702.04510

A Dependency-Based Neural Reordering Model for Statistical Machine Translation

In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network and dependency-based embeddings to predict whether the translations of two source words linked by a dependency relation should remain in the same order or should be swapped in the translated sentence. Experiments on Chinese-to-English translation show that our approach yields a statistically significant improvement of 0.57 BLEU point on benchmark NIST test sets, compared to our prior state-of-the-art statistical MT system that uses sparse dependency-based reordering features.

arXiv:1702.00887

Structured Attention Networks

Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training. In this work, we experiment with incorporating richer structural distributions, encoded using graphical models, within deep networks. We show that these structured attention networks are simple extensions of the basic attention procedure, and that they allow for extending attention beyond the standard soft-selection approach, such as attending to partial segmentations or to subtrees. We experiment with two different classes of structured attention networks: a linear-chain conditional random field and a graph-based parsing model, and describe how these models can be practically implemented as neural network layers. Experiments show that this approach is effective for incorporating structural biases, and structured attention networks outperform baseline attention models on a variety of synthetic and real tasks: tree transduction, neural machine translation, question answering, and natural language inference. We further find that models trained in this way learn interesting unsupervised hidden representations that generalize simple attention.

arXiv:1702.05552

Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection

As humans we possess an intuitive ability for navigation which we master through years of practice; however existing approaches to model this trait for diverse tasks including monitoring pedestrian flow and detecting abnormal events have been limited by using a variety of hand-crafted features. Recent research in the area of deep-learning has demonstrated the power of learning features directly from the data; and related research in recurrent neural networks has shown exemplary results in sequence-to-sequence problems such as neural machine translation and neural image caption generation. Motivated by these approaches, we propose a novel method to predict the future motion of a pedestrian given a short history of their, and their neighbours, past behaviour. The novelty of the proposed method is the combined attention model which utilises both "soft attention" as well as "hard-wired" attention in order to map the trajectory information from the local neighbourhood to the future positions of the pedestrian of interest. We illustrate how a simple approximation of attention weights (i.e hard-wired) can be merged together with soft attention weights in order to make our model applicable for challenging real world scenarios with hundreds of neighbours. The navigational capability of the proposed method is tested on two challenging publicly available surveillance databases where our model outperforms the current-state-of-the-art methods. Additionally, we illustrate how the proposed architecture can be directly applied for the task of abnormal event detection without handcrafting the features.

arXiv:1611.04928

Neural Machine Translation with Pivot Languages

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.

arXiv:1702.08451

Approches d'analyse distributionnelle pour améliorer la désambiguïsation sémantique

Word sense disambiguation (WSD) improves many Natural Language Processing (NLP) applications such as Information Retrieval, Machine Translation or Lexical Simplification. WSD is the ability of determining a word sense among different ones within a polysemic lexical unit taking into account the context. The most straightforward approach uses a semantic proximity measure between the word sense candidates of the target word and those of its context. Such a method very easily entails a combinatorial explosion. In this paper, we propose two methods based on distributional analysis which enable to reduce the exponential complexity without losing the coherence. We present a comparison between the selection of distributional neighbors and the linearly nearest neighbors. The figures obtained show that selecting distributional neighbors leads to better results.

arXiv:1702.08450

A Knowledge-Based Approach to Word Sense Disambiguation by distributional selection and semantic features

Word sense disambiguation improves many Natural Language Processing (NLP) applications such as Information Retrieval, Information Extraction, Machine Translation, or Lexical Simplification. Roughly speaking, the aim is to choose for each word in a text its best sense. One of the most popular method estimates local semantic similarity relatedness between two word senses and then extends it to all words from text. The most direct method computes a rough score for every pair of word senses and chooses the lexical chain that has the best score (we can imagine the exponential complexity that returns this comprehensive approach). In this paper, we propose to use a combinatorial optimization metaheuristic for choosing the nearest neighbors obtained by distributional selection around the word to disambiguate. The test and the evaluation of our method concern a corpus written in French by means of the semantic network BabelNet. The obtained accuracy rate is 78 % on all names and verbs chosen for the evaluation.

arXiv:1702.08217

A case study on English-Malayalam Machine Translation

In this paper we present our work on a case study on Statistical Machine Translation (SMT) and Rule based machine translation (RBMT) for translation from English to Malayalam and Malayalam to English. One of the motivations of our study is to make a three way performance comparison, such as, a) SMT and RBMT b) English to Malayalam SMT and Malayalam to English SMT c) English to Malayalam RBMT and Malayalam to English RBMT. We describe the development of English to Malayalam and Malayalam to English baseline phrase based SMT system and the evaluation of its performance compared against the RBMT system. Based on our study the observations are: a) SMT systems outperform RBMT systems, b) In the case of SMT, English - Malayalam systems perform better than that of Malayalam - English systems, c) In the case RBMT, Malayalam to English systems are performing better than English to Malayalam systems. Based on our evaluations and detailed error analysis, we describe the requirements of incorporating morphological processing into the SMT to improve the accuracy of translation.

arXiv:1703.01485

Lexical Resources for Hindi Marathi MT

In this paper we describe some ways to utilize various lexical resources to improve the quality of statistical machine translation system. We have augmented the training corpus with various lexical resources such as IndoWordnet semantic relation set, function words, kridanta pairs and verb phrases etc. Our research on the usage of lexical resources mainly focused on two ways such as augmenting parallel corpus with more vocabulary and augmenting with various word forms. We have described case studies, evaluations and detailed error analysis for both Marathi to Hindi and Hindi to Marathi machine translation systems. From the evaluations we observed that, there is an incremental growth in the quality of machine translation as the usage of various lexical resources increases. Moreover usage of various lexical resources helps to improve the coverage and quality of machine translation where limited parallel corpus is available.

arXiv:1607.07086공식 코드 · Papers with Code

An Actor-Critic Algorithm for Sequence Prediction

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \textit{critic} network that is trained to predict the value of an output token, given the policy of an \textit{actor} network. This results in a training procedure that is much closer to the test phase, and allows us to directly optimize for a task-specific score such as BLEU. Crucially, since we leverage these techniques in the supervised learning setting rather than the traditional RL setting, we condition the critic network on the ground-truth output. We show that our method leads to improved performance on both a synthetic task, and for German-English machine translation. Our analysis paves the way for such methods to be applied in natural language generation tasks, such as machine translation, caption generation, and dialogue modelling.

arXiv:1703.02573

Data Noising as Smoothing in Neural Network Language Models

Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and speech, commonly used noising primitives have not been developed for discrete sequence-level settings such as language modeling. In this paper, we derive a connection between input noising in neural network language models and smoothing in $n$-gram models. Using this connection, we draw upon ideas from smoothing to develop effective noising schemes. We demonstrate performance gains when applying the proposed schemes to language modeling and machine translation. Finally, we provide empirical analysis validating the relationship between noising and smoothing.

arXiv:1703.01619

Neural Machine Translation and Sequence-to-sequence Models: A Tutorial

This tutorial introduces a new and powerful set of techniques variously called "neural machine translation" or "neural sequence-to-sequence models". These techniques have been used in a number of tasks regarding the handling of human language, and can be a powerful tool in the toolbox of anyone who wants to model sequential data of some sort. The tutorial assumes that the reader knows the basics of math and programming, but does not assume any particular experience with neural networks or natural language processing. It attempts to explain the intuition behind the various methods covered, then delves into them with enough mathematical detail to understand them concretely, and culiminates with a suggestion for an implementation exercise, where readers can test that they understood the content in practice.