PyTorchKR Papers

최신 논문

총 5,206편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1610.07420

Reordering rules for English-Hindi SMT

Reordering is a preprocessing stage for Statistical Machine Translation (SMT) system where the words of the source sentence are reordered as per the syntax of the target language. We are proposing a rich set of rules for better reordering. The idea is to facilitate the training process by better alignments and parallel phrase extraction for a phrase-based SMT system. Reordering also helps the decoding process and hence improving the machine translation quality. We have observed significant improvements in the translation quality by using our approach over the baseline SMT. We have used BLEU, NIST, multi-reference word error rate, multi-reference position independent error rate for judging the improvements. We have exploited open source SMT toolkit MOSES to develop the system.

arXiv:1610.07418

Statistical Machine Translation for Indian Languages: Mission Hindi

This paper discusses Centre for Development of Advanced Computing Mumbai's (CDACM) submission to the NLP Tools Contest on Statistical Machine Translation in Indian Languages (ILSMT) 2014 (collocated with ICON 2014). The objective of the contest was to explore the effectiveness of Statistical Machine Translation (SMT) for Indian language to Indian language and English-Hindi machine translation. In this paper, we have proposed that suffix separation and word splitting for SMT from agglutinative languages to Hindi significantly improves over the baseline (BL). We have also shown that the factored model with reordering outperforms the phrase-based SMT for English-Hindi (\enhi). We report our work on all five pairs of languages, namely Bengali-Hindi (\bnhi), Marathi-Hindi (\mrhi), Tamil-Hindi (\tahi), Telugu-Hindi (\tehi), and \enhi for Health, Tourism, and General domains.

arXiv:1610.07272

Bridging Neural Machine Translation and Bilingual Dictionaries

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in the bilingual training data. In this paper, we propose two methods to bridge NMT and the bilingual dictionaries. The core idea behind is to design novel models that transform the bilingual dictionaries into adequate sentence pairs, so that NMT can distil latent bilingual mappings from the ample and repetitive phenomena. One method leverages a mixed word/character model and the other attempts at synthesizing parallel sentences guaranteeing massive occurrence of the translation lexicon. Extensive experiments demonstrate that the proposed methods can remarkably improve the translation quality, and most of the rare words in the test sentences can obtain correct translations if they are covered by the dictionary.

arXiv:1610.06550공식 코드 · Papers with Code

Neural Machine Translation with Characters and Hierarchical Encoding

Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output. We first argue that this hierarchical representation of the character encoder reduces computational complexity, and show that it improves translation performance. Secondly, by qualitatively studying attention plots from the decoder we find that the model learns to compress common words into a single embedding whereas rare words, such as names and places, are represented character by character.

arXiv:1610.04841

Translation Quality Estimation using Recurrent Neural Network

This paper describes our submission to the shared task on word/phrase level Quality Estimation (QE) in the First Conference on Statistical Machine Translation (WMT16). The objective of the shared task was to predict if the given word/phrase is a correct/incorrect (OK/BAD) translation in the given sentence. In this paper, we propose a novel approach for word level Quality Estimation using Recurrent Neural Network Language Model (RNN-LM) architecture. RNN-LMs have been found very effective in different Natural Language Processing (NLP) applications. RNN-LM is mainly used for vector space language modeling for different NLP problems. For this task, we modify the architecture of RNN-LM. The modified system predicts a label (OK/BAD) in the slot rather than predicting the word. The input to the system is a word sequence, similar to the standard RNN-LM. The approach is language independent and requires only the translated text for QE. To estimate the phrase level quality, we use the output of the word level QE system.

arXiv:1604.06045

Dialog-based Language Learning

A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of (Weston et al., 2015) and large-scale question answering from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.

arXiv:1610.08000

Statistical Machine Translation for Indian Languages: Mission Hindi 2

This paper presents Centre for Development of Advanced Computing Mumbai's (CDACM) submission to NLP Tools Contest on Statistical Machine Translation in Indian Languages (ILSMT) 2015 (collocated with ICON 2015). The aim of the contest was to collectively explore the effectiveness of Statistical Machine Translation (SMT) while translating within Indian languages and between English and Indian languages. In this paper, we report our work on all five language pairs, namely Bengali-Hindi (\bnhi), Marathi-Hindi (\mrhi), Tamil-Hindi (\tahi), Telugu-Hindi (\tehi), and English-Hindi (\enhi) for Health, Tourism, and General domains. We have used suffix separation, compound splitting and preordering prior to SMT training and testing.

arXiv:1610.09565공식 코드 · Papers with Code

Sequence-to-sequence neural network models for transliteration

Transliteration is a key component of machine translation systems and software internationalization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing datasets. In an effort to make machine transliteration accessible, we open source a new Arabic to English transliteration dataset and our trained models.

arXiv:1610.09027

Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in both space and time as the amount of memory grows --- limiting their applicability to real-world domains. Here, we present an end-to-end differentiable memory access scheme, which we call Sparse Access Memory (SAM), that retains the representational power of the original approaches whilst training efficiently with very large memories. We show that SAM achieves asymptotic lower bounds in space and time complexity, and find that an implementation runs $1,\!000\times$ faster and with $3,\!000\times$ less physical memory than non-sparse models. SAM learns with comparable data efficiency to existing models on a range of synthetic tasks and one-shot Omniglot character recognition, and can scale to tasks requiring $100,\!000$s of time steps and memories. As well, we show how our approach can be adapted for models that maintain temporal associations between memories, as with the recently introduced Differentiable Neural Computer.

arXiv:1611.00179

Dual Learning for Machine Translation

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck, we develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual-learning game. This mechanism is inspired by the following observation: any machine translation task has a dual task, e.g., English-to-French translation (primal) versus French-to-English translation (dual); the primal and dual tasks can form a closed loop, and generate informative feedback signals to train the translation models, even if without the involvement of a human labeler. In the dual-learning mechanism, we use one agent to represent the model for the primal task and the other agent to represent the model for the dual task, then ask them to teach each other through a reinforcement learning process. Based on the feedback signals generated during this process (e.g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e.g., using the policy gradient methods). We call the corresponding approach to neural machine translation \emph{dual-NMT}. Experiments show that dual-NMT works very well on English$\leftrightarrow$French translation; especially, by learning from monolingual data (with 10% bilingual data for warm start), it achieves a comparable accuracy to NMT trained from the full bilingual data for the French-to-English translation task.

arXiv:1610.09893

LightRNN: Memory and Computation-Efficient Recurrent Neural Networks

Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very big (e.g., possibly beyond the memory capacity of a GPU device) and its training will become very inefficient. In this work, we propose a novel technique to tackle this challenge. The key idea is to use 2-Component (2C) shared embedding for word representations. We allocate every word in the vocabulary into a table, each row of which is associated with a vector, and each column associated with another vector. Depending on its position in the table, a word is jointly represented by two components: a row vector and a column vector. Since the words in the same row share the row vector and the words in the same column share the column vector, we only need $2 \sqrt{|V|}$ vectors to represent a vocabulary of $|V|$ unique words, which are far less than the $|V|$ vectors required by existing approaches. Based on the 2-Component shared embedding, we design a new RNN algorithm and evaluate it using the language modeling task on several benchmark datasets. The results show that our algorithm significantly reduces the model size and speeds up the training process, without sacrifice of accuracy (it achieves similar, if not better, perplexity as compared to state-of-the-art language models). Remarkably, on the One-Billion-Word benchmark Dataset, our algorithm achieves comparable perplexity to previous language models, whilst reducing the model size by a factor of 40-100, and speeding up the training process by a factor of 2. We name our proposed algorithm \emph{LightRNN} to reflect its very small model size and very high training speed.

arXiv:1609.02549

Learning Lexical Entries for Robotic Commands using Crowdsourcing

Robotic commands in natural language usually contain various spatial descriptions that are semantically similar but syntactically different. Mapping such syntactic variants into semantic concepts that can be understood by robots is challenging due to the high flexibility of natural language expressions. To tackle this problem, we collect robotic commands for navigation and manipulation tasks using crowdsourcing. We further define a robot language and use a generative machine translation model to translate robotic commands from natural language to robot language. The main purpose of this paper is to simulate the interaction process between human and robots using crowdsourcing platforms, and investigate the possibility of translating natural language to robot language with paraphrases.

arXiv:1508.02225

Improve the Evaluation of Fluency Using Entropy for Machine Translation Evaluation Metrics

The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fragments to n and cannot catch the matched fragments longer than n, so they can only reflect the fluency indirectly. METEOR, which is not limited by n-gram, uses the number of matched chunks but it does not consider the length of each chunk. In this paper, we propose an entropy-based method, which can sufficiently reflect the fluency of translations through the distribution of matched words. This method can easily combine with the widely-used automatic evaluation metrics to improve the evaluation of fluency. Experiments show that the correlations of BLEU and METEOR are improved on sentence level after combining with the entropy-based method on WMT 2010 and WMT 2012.

arXiv:1508.01996

An Automatic Machine Translation Evaluation Metric Based on Dependency Parsing Model

Most of the syntax-based metrics obtain the similarity by comparing the sub-structures extracted from the trees of hypothesis and reference. These sub-structures are defined by human and can't express all the information in the trees because of the limited length of sub-structures. In addition, the overlapped parts between these sub-structures are computed repeatedly. To avoid these problems, we propose a novel automatic evaluation metric based on dependency parsing model, with no need to define sub-structures by human. First, we train a dependency parsing model by the reference dependency tree. Then we generate the hypothesis dependency tree and the corresponding probability by the dependency parsing model. The quality of the hypothesis can be judged by this probability. In order to obtain the lexicon similarity, we also introduce the unigram F-score to the new metric. Experiment results show that the new metric gets the state-of-the-art performance on system level, and is comparable with METEOR on sentence level.

arXiv:1611.03777

Tricks from Deep Learning

The deep learning community has devised a diverse set of methods to make gradient optimization, using large datasets, of large and highly complex models with deeply cascaded nonlinearities, practical. Taken as a whole, these methods constitute a breakthrough, allowing computational structures which are quite wide, very deep, and with an enormous number and variety of free parameters to be effectively optimized. The result now dominates much of practical machine learning, with applications in machine translation, computer vision, and speech recognition. Many of these methods, viewed through the lens of algorithmic differentiation (AD), can be seen as either addressing issues with the gradient itself, or finding ways of achieving increased efficiency using tricks that are AD-related, but not provided by current AD systems. The goal of this paper is to explain not just those methods of most relevance to AD, but also the technical constraints and mindset which led to their discovery. After explaining this context, we present a "laundry list" of methods developed by the deep learning community. Two of these are discussed in further mathematical detail: a way to dramatically reduce the size of the tape when performing reverse-mode AD on a (theoretically) time-reversible process like an ODE integrator; and a new mathematical insight that allows for the implementation of a stochastic Newton's method.

arXiv:1611.02944

Increasing the throughput of machine translation systems using clouds

The manuscript presents an experiment at implementation of a Machine Translation system in a MapReduce model. The empirical evaluation was done using fully implemented translation systems embedded into the MapReduce programming model. Two machine translation paradigms were studied: shallow transfer Rule Based Machine Translation and Statistical Machine Translation. The results show that the MapReduce model can be successfully used to increase the throughput of a machine translation system. Furthermore this method enhances the throughput of a machine translation system without decreasing the quality of the translation output. Thus, the present manuscript also represents a contribution to the seminal work in natural language processing, specifically Machine Translation. It first points toward the importance of the definition of the metric of throughput of translation system and, second, the applicability of the machine translation task to the MapReduce paradigm.

arXiv:1606.02960공식 코드 · Papers with Code

Sequence-to-Sequence Learning as Beam-Search Optimization

Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores. This structured approach avoids classical biases associated with local training and unifies the training loss with the test-time usage, while preserving the proven model architecture of seq2seq and its efficient training approach. We show that our system outperforms a highly-optimized attention-based seq2seq system and other baselines on three different sequence to sequence tasks: word ordering, parsing, and machine translation.

arXiv:1611.04798

Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our approach does not require any special treatment on the network architecture and it allows us to learn minimal number of free parameters in a standard way of training. Our approach has shown its effectiveness in an under-resourced translation scenario with considerable improvements up to 2.6 BLEU points. In addition, the approach has achieved interesting and promising results when applied in the translation task that there is no direct parallel corpus between source and target languages.

arXiv:1611.04122

Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence

This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingual Dataless Document Classification (CLDDC) relies on mapping the English labels or short category description into a Wikipedia-based semantic representation, and on the use of the target language Wikipedia. Consequently, performance could suffer when Wikipedia in the target language is small. In this paper, we focus on languages with small Wikipedias, (Small-Wikipedia languages, SWLs). We use a word-level dictionary to convert documents in a SWL to a large-Wikipedia language (LWLs), and then perform CLDDC based on the LWL's Wikipedia. This approach can be applied to thousands of languages, which can be contrasted with machine translation, which is a supervision heavy approach and can be done for about 100 languages. We also develop a ranking algorithm that makes use of language similarity metrics to automatically select a good LWL, and show that this significantly improves classification of SWLs' documents, performing comparably to the best bridge possible.

arXiv:1611.06722

False-Friend Detection and Entity Matching via Unsupervised Transliteration

Transliterations play an important role in multilingual entity reference resolution, because proper names increasingly travel between languages in news and social media. Previous work associated with machine translation targets transliteration only single between language pairs, focuses on specific classes of entities (such as cities and celebrities) and relies on manual curation, which limits the expression power of transliteration in multilingual environment. By contrast, we present an unsupervised transliteration model covering 69 major languages that can generate good transliterations for arbitrary strings between any language pair. Our model yields top-(1, 20, 100) averages of (32.85%, 60.44%, 83.20%) in matching gold standard transliteration compared to results from a recently-published system of (26.71%, 50.27%, 72.79%). We also show the quality of our model in detecting true and false friends from Wikipedia high frequency lexicons. Our method indicates a strong signal of pronunciation similarity and boosts the probability of finding true friends in 68 out of 69 languages.