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.

While parallel corpora are an indispensable resource for data-driven multilingual natural language processing tasks such as machine translation, they are limited in quantity, quality and coverage. As a result, learning translation models from non-parallel corpora has become increasingly important nowadays, especially for low-resource languages. In this work, we propose a joint model for iteratively learning parallel lexicons and phrases from nonparallel corpora. The model is trained using a Viterbi EM algorithm that alternates between constructing parallel phrases using lexicons and updating lexicons based on the constructed parallel phrases. Experiments on Chinese-English datasets show that our approach learns better parallel lexicons and phrases and improves translation performance significantly.

Computer-aided translation (CAT) system is the most popular tool which helps human translators perform language translation efficiently. To further improve the efficiency, there is an increasing interest in applying the machine translation (MT) technology to upgrade CAT. Post-editing is a standard approach: human translators generate the translation by correcting MT outputs. In this paper, we propose a novel approach deeply integrating MT into CAT systems: a well-designed input method which makes full use of the knowledge adopted by MT systems, such as translation rules, decoding hypotheses and n-best translation lists. Our proposed approach allows human translators to focus on choosing better translation results with less time rather than just complete translation themselves. The extensive experiments demonstrate that our method saves more than 14% time and over 33% keystrokes, and it improves the translation quality as well by more than 3 absolute BLEU scores compared with the strong baseline, i.e., post-editing using Google Pinyin.

Reordering model adaptation remains a big challenge in statistical machine translation because reordering patterns of translation units often vary dramatically from one domain to another. In this paper, we propose a novel adaptive discriminative reordering model (DRM) based on structural learning, which can capture correspondences among reordering features from two different domains. Exploiting both in-domain and out-of-domain monolingual corpora, our model learns a shared feature representation for cross-domain phrase reordering. Incorporating features of this representation, the DRM trained on out-of-domain corpus generalizes better to in-domain data. Experiment results on the NIST Chinese-English translation task show that our approach significantly outperforms a variety of baselines.

This paper explores the use of general-purpose machine translation (MT) in assisting the users of computer-aided translation (CAT) systems based on translation memory (TM) to identify the target words in the translation proposals that need to be changed (either replaced or removed) or kept unedited, a task we term as "word-keeping recommendation". MT is used as a black box to align source and target sub-segments on the fly in the translation units (TUs) suggested to the user. Source-language (SL) and target-language (TL) segments in the matching TUs are segmented into overlapping sub-segments of variable length and machine-translated into the TL and the SL, respectively. The bilingual sub-segments obtained and the matching between the SL segment in the TU and the segment to be translated are employed to build the features that are then used by a binary classifier to determine the target words to be changed and those to be kept unedited. In this approach, MT results are never presented to the translator. Two approaches are presented in this work: one using a word-keeping recommendation system which can be trained on the TM used with the CAT system, and a more basic approach which does not require any training. Experiments are conducted by simulating the translation of texts in several language pairs with corpora belonging to different domains and using three different MT systems. We compare the performance obtained to that of previous works that have used statistical word alignment for word-keeping recommendation, and show that the MT-based approaches presented in this paper are more accurate in most scenarios. In particular, our results confirm that the MT-based approaches are better than the alignment-based approach when using models trained on out-of-domain TMs. Additional experiments were performed to check how dependent the MT-based recommender is on the language pair and MT system used for training. These experiments confirm a high degree of reusability of the recommendation models across various MT systems, but a low level of reusability across language pairs.

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in reaches a competitive 18.7% phoneme error rate (PER) on the TIMIT phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitative explanation of this failure and propose a novel and generic method of adding location-awareness to the attention mechanism to alleviate this issue. The new method yields a model that is robust to long inputs and achieves 18% PER in single utterances and 20% in 10-times longer (repeated) utterances. Finally, we propose a change to the at- tention mechanism that prevents it from concentrating too much on single frames, which further reduces PER to 17.6% level.

Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has therefore attracted significant attention in the theoretical and applied machine learning literature. In this paper, we analyze a recently proposed technique known as "self-normalization", which introduces a regularization term in training to penalize log normalizers for deviating from zero. This makes it possible to use unnormalized model scores as approximate probabilities. Empirical evidence suggests that self-normalization is extremely effective, but a theoretical understanding of why it should work, and how generally it can be applied, is largely lacking. We prove generalization bounds on the estimated variance of normalizers and upper bounds on the loss in accuracy due to self-normalization, describe classes of input distributions that self-normalize easily, and construct explicit examples of high-variance input distributions. Our theoretical results make predictions about the difficulty of fitting self-normalized models to several classes of distributions, and we conclude with empirical validation of these predictions.

Question retrieval in current community-based question answering (CQA) services does not, in general, work well for long and complex queries. One of the main difficulties lies in the word mismatch between queries and candidate questions. Existing solutions try to expand the queries at word level, but they usually fail to consider concept level enrichment. In this paper, we explore a pivot language translation based approach to derive the paraphrases of key concepts. We further propose a unified question retrieval model which integrates the keyconcepts and their paraphrases for the query question. Experimental results demonstrate that the paraphrase enhanced retrieval model significantly outperforms the state-of-the-art models in question retrieval.

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.

I am quite ready to subscribe to the already mentioned slogan that "whatever a human being can do,an appropriate machine can do, too"; but I do this only because.I regard the slogan as utterly trivial. At the moment, I am not talking about what maohines could do in principle but only about what actually existing or blueprinted machines could do, and it Is with regard to these that I utter my definite opinions. If someone wishes to write sciencefiction about information-processing centres of the (undetermined) future, let him do so and I shall discuss it with him over a glass of beer and even offer some startling suggestions of my own. If he is interested in improving the literature search process today, I would strongly advise him to forget about mechanizing abstracting or indexing. May I add that it is with a good amount of sorrow that I have come to this conclusion which is quite counter, to my temperament and my convictions (never published) of a few years ago.