Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images and sentences while the decoder can generate novel descriptions from scratch. Using LSTM to encode sentences, we match the state-of-the-art performance on Flickr8K and Flickr30K without using object detections. We also set new best results when using the 19-layer Oxford convolutional network. Furthermore we show that with linear encoders, the learned embedding space captures multimodal regularities in terms of vector space arithmetic e.g. *image of a blue car* - "blue" + "red" is near images of red cars. Sample captions generated for 800 images are made available for comparison.
Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform those learned by cutting-edge monolingual models at single-language tasks requiring knowledge of conceptual similarity and/or syntactic role. The findings suggest that, while monolingual models learn information about how concepts are related, neural-translation models better capture their true ontological status.
Subset selection from massive data with noised information is increasingly popular for various applications. This problem is still highly challenging as current methods are generally slow in speed and sensitive to outliers. To address the above two issues, we propose an accelerated robust subset selection (ARSS) method. Specifically in the subset selection area, this is the first attempt to employ the $\ell_{p}(0<p\leq1)$-norm based measure for the representation loss, preventing large errors from dominating our objective. As a result, the robustness against outlier elements is greatly enhanced. Actually, data size is generally much larger than feature length, i.e. $N\gg L$. Based on this observation, we propose a speedup solver (via ALM and equivalent derivations) to highly reduce the computational cost, theoretically from $O(N^{4})$ to $O(N{}^{2}L)$. Extensive experiments on ten benchmark datasets verify that our method not only outperforms state of the art methods, but also runs 10,000+ times faster than the most related method.
Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
This paper presents novel Bayesian optimisation algorithms for minimum error rate training of statistical machine translation systems. We explore two classes of algorithms for efficiently exploring the translation space, with the first based on N-best lists and the second based on a hypergraph representation that compactly represents an exponential number of translation options. Our algorithms exhibit faster convergence and are capable of obtaining lower error rates than the existing translation model specific approaches, all within a generic Bayesian optimisation framework. Further more, we also introduce a random embedding algorithm to scale our approach to sparse high dimensional feature sets.
Mixed language data is one of the difficult yet less explored domains of natural language processing. Most research in fields like machine translation or sentiment analysis assume monolingual input. However, people who are capable of using more than one language often communicate using multiple languages at the same time. Sociolinguists believe this "code-switching" phenomenon to be socially motivated. For example, to express solidarity or to establish authority. Most past work depend on external tools or resources, such as part-of-speech tagging, dictionary look-up, or named-entity recognizers to extract rich features for training machine learning models. In this paper, we train recurrent neural networks with only raw features, and use word embedding to automatically learn meaningful representations. Using the same mixed-language Twitter corpus, our system is able to outperform the best SVM-based systems reported in the EMNLP'14 Code-Switching Workshop by 1% in accuracy, or by 17% in error rate reduction.
In this paper, we have used Recurrent Neural Networks to capture and model human motion data and generate motions by prediction of the next immediate data point at each time-step. Our RNN is armed with recently proposed Gated Recurrent Units which has shown promising results in some sequence modeling problems such as Machine Translation and Speech Synthesis. We demonstrate that this model is able to capture long-term dependencies in data and generate realistic motions.
We consider phrase based Language Models (LM), which generalize the commonly used word level models. Similar concept on phrase based LMs appears in speech recognition, which is rather specialized and thus less suitable for machine translation (MT). In contrast to the dependency LM, we first introduce the exhaustive phrase-based LMs tailored for MT use. Preliminary experimental results show that our approach outperform word based LMs with the respect to perplexity and translation quality.
This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs). We discuss how to train very large RNNs on GPUs and address the questions of how RNNLMs scale with respect to model size, training-set size, computational costs and memory. Our analysis shows that despite being more costly to train, RNNLMs obtain much lower perplexities on standard benchmarks than n-gram models. We train the largest known RNNs and present relative word error rates gains of 18% on an ASR task. We also present the new lowest perplexities on the recently released billion word language modelling benchmark, 1 BLEU point gain on machine translation and a 17% relative hit rate gain in word prediction.
Syntactic parsing is a necessary task which is required for NLP applications including machine translation. It is a challenging task to develop a qualitative parser for morphological rich and agglutinative languages. Syntactic analysis is used to understand the grammatical structure of a natural language sentence. It outputs all the grammatical information of each word and its constituent. Also issues related to it help us to understand the language in a more detailed way. This literature survey is groundwork to understand the different parser development for Indian languages and various approaches that are used to develop such tools and techniques. This paper provides a survey of research papers from well known journals and conferences.
This paper describes the resource- and system-building efforts of an eight-week Johns Hopkins University Human Language Technology Center of Excellence Summer Camp for Applied Language Exploration (SCALE-2009) on Semantically-Informed Machine Translation (SIMT). We describe a new modality/negation (MN) annotation scheme, the creation of a (publicly available) MN lexicon, and two automated MN taggers that we built using the annotation scheme and lexicon. Our annotation scheme isolates three components of modality and negation: a trigger (a word that conveys modality or negation), a target (an action associated with modality or negation) and a holder (an experiencer of modality). We describe how our MN lexicon was semi-automatically produced and we demonstrate that a structure-based MN tagger results in precision around 86% (depending on genre) for tagging of a standard LDC data set. We apply our MN annotation scheme to statistical machine translation using a syntactic framework that supports the inclusion of semantic annotations. Syntactic tags enriched with semantic annotations are assigned to parse trees in the target-language training texts through a process of tree grafting. While the focus of our work is modality and negation, the tree grafting procedure is general and supports other types of semantic information. We exploit this capability by including named entities, produced by a pre-existing tagger, in addition to the MN elements produced by the taggers described in this paper. The resulting system significantly outperformed a linguistically naive baseline model (Hiero), and reached the highest scores yet reported on the NIST 2009 Urdu-English test set. This finding supports the hypothesis that both syntactic and semantic information can improve translation quality.
Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target language sentences by rendering and compositing the phrases rather than the words. Thus, it is much more reasonable to model dependency between phrases, but few research work succeed in solving this problem. In this paper, we tackle this problem by designing a novel phrase-based language model which attempts to solve three key sub-problems: 1, how to define a phrase in language model; 2, how to determine the phrase boundary in the large-scale monolingual data in order to enlarge the training set; 3, how to alleviate the data sparsity problem due to the huge vocabulary size of phrases. By carefully handling these issues, the extensive experiments on Chinese-to-English translation show that our phrase-based language model can significantly improve the translation quality by up to +1.47 absolute BLEU score.
Reordering is a challenge to machine translation (MT) systems. In MT, the widely used approach is to apply word based language model (LM) which considers the constituent units of a sentence as words. In speech recognition (SR), some phrase based LM have been proposed. However, those LMs are not necessarily suitable or optimal for reordering. We propose two phrase based LMs which considers the constituent units of a sentence as phrases. Experiments show that our phrase based LMs outperform the word based LM with the respect of perplexity and n-best list re-ranking.
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.
Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice, distinguishing good translations from bad ones does not only depend on the local features, but also rely on the global sentence-level information. In this paper, we explore the source-side global sentence-level features for target-side local translation prediction. We propose a novel bilingually-constrained chunk-based convolutional neural network to learn sentence semantic representations. With the sentence-level feature representation, we further design a feed-forward neural network to better predict translations using both local and global information. The large-scale experiments show that our method can obtain substantial improvements in translation quality over the strong baseline: the hierarchical phrase-based translation model augmented with the neural network joint model.
It is commonly accepted that machine translation is a more complex task than part of speech tagging. But how much more complex? In this paper we make an attempt to develop a general framework and methodology for computing the informational and/or processing complexity of NLP applications and tasks. We define a universal framework akin to a Turning Machine that attempts to fit (most) NLP tasks into one paradigm. We calculate the complexities of various NLP tasks using measures of Shannon Entropy, and compare `simple' ones such as part of speech tagging to `complex' ones such as machine translation. This paper provides a first, though far from perfect, attempt to quantify NLP tasks under a uniform paradigm. We point out current deficiencies and suggest some avenues for fruitful research.
Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and constrains that each feature interacts with the rest features in an linear manner, which might limit the expressive power of the model and lead to a under-fit model on the current data. In this paper, we propose a non-linear modeling for the quality of translation hypotheses based on neural networks, which allows more complex interaction between features. A learning framework is presented for training the non-linear models. We also discuss possible heuristics in designing the network structure which may improve the non-linear learning performance. Experimental results show that with the basic features of a hierarchical phrase-based machine translation system, our method produce translations that are better than a linear model.
In machine translation it is common phenomenon that machine-readable dictionaries and standard parsing rules are not enough to ensure accuracy in parsing and translating English phrases into Korean language, which is revealed in misleading translation results due to consequent structural and semantic ambiguities. This paper aims to suggest a solution to structural and semantic ambiguities due to the idiomaticity and non-grammaticalness of phrases commonly used in English language by applying bilingual phrase database in English-Korean Machine Translation (EKMT). This paper firstly clarifies what the phrase unit in EKMT is based on the definition of the English phrase, secondly clarifies what kind of language unit can be the target of the phrase database for EKMT, thirdly suggests a way to build the phrase database by presenting the format of the phrase database with examples, and finally discusses briefly the method to apply this bilingual phrase database to the EKMT for structural and semantic disambiguation.
The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call the model S-LSTM, which provides a principled way of considering long-distance interaction over hierarchies, e.g., language or image parse structures. We leverage the models for semantic composition to understand the meaning of text, a fundamental problem in natural language understanding, and show that it outperforms a state-of-the-art recursive model by replacing its composition layers with the S-LSTM memory blocks. We also show that utilizing the given structures is helpful in achieving a performance better than that without considering the structures.
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent success, neural machine translation has its limitation in handling a larger vocabulary, as training complexity as well as decoding complexity increase proportionally to the number of target words. In this paper, we propose a method that allows us to use a very large target vocabulary without increasing training complexity, based on importance sampling. We show that decoding can be efficiently done even with the model having a very large target vocabulary by selecting only a small subset of the whole target vocabulary. The models trained by the proposed approach are empirically found to outperform the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models. Furthermore, when we use the ensemble of a few models with very large target vocabularies, we achieve the state-of-the-art translation performance (measured by BLEU) on the English->German translation and almost as high performance as state-of-the-art English->French translation system.