k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model. However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance. In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model. To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training. Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight. Meanwhile we inject two types of perturbations into the retrieved pairs for robust training. Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness. Our code is available at https://github.com/DeepLearnXMU/Robust-knn-mt.

Due to the great potential in facilitating software development, code generation has attracted increasing attention recently. Generally, dominant models are Seq2Tree models, which convert the input natural language description into a sequence of tree-construction actions corresponding to the pre-order traversal of an Abstract Syntax Tree (AST). However, such a traversal order may not be suitable for handling all multi-branch nodes. In this paper, we propose to equip the Seq2Tree model with a context-based Branch Selector, which is able to dynamically determine optimal expansion orders of branches for multi-branch nodes. Particularly, since the selection of expansion orders is a non-differentiable multi-step operation, we optimize the selector through reinforcement learning, and formulate the reward function as the difference of model losses obtained through different expansion orders. Experimental results and in-depth analysis on several commonly-used datasets demonstrate the effectiveness and generality of our approach. We have released our code at https://github.com/DeepLearnXMU/CG-RL.

To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.

In this paper, we present a new data set, named FreebaseQA, for open-domain factoid question answering (QA) tasks over structured knowledge bases, like Freebase. The data set is generated by matching trivia-type question-answer pairs with subject-predicate-object triples in Freebase. For each collected question-answer pair, we first tag all entities in each question and search for relevant predicates that bridge a tagged entity with the answer in Freebase. Finally, human annotation is used to remove any false positive in these matched triples. Using this method, we are able to efficiently generate over 54K matches from about 28K unique questions with minimal cost. Our analysis shows that this data set is suitable for model training in factoid QA tasks beyond simpler questions since FreebaseQA provides more linguistically sophisticated questions than other existing data sets.

To improve the training efficiency of hierarchical recurrent models without compromising their performance, we propose a strategy named as “the lower the simpler”, which is to simplify the baseline models by making the lower layers simpler than the upper layers. We carry out this strategy to simplify two typical hierarchical recurrent models, namely Hierarchical Recurrent Encoder-Decoder (HRED) and R-NET, whose basic building block is GRU. Specifically, we propose Scalar Gated Unit (SGU), which is a simplified variant of GRU, and use it to replace the GRUs at the middle layers of HRED and R-NET. Besides, we also use Fixed-size Ordinally-Forgetting Encoding (FOFE), which is an efficient encoding method without any trainable parameter, to replace the GRUs at the bottom layers of HRED and R-NET. The experimental results show that the simplified HRED and the simplified R-NET contain significantly less trainable parameters, consume significantly less training time, and achieve slightly better performance than their baseline models.

In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) (Zhang et al., 2015b) in neural languages modelling, called dual-FOFE. The main idea of dual-FOFE is that it allows to use two different forgetting factors so that it can avoid the trade-off in choosing either a small or large values for the single forgetting factor. In our experiments, we have compared the dual-FOFE based neural network language models (NNLM) against the original FOFE counterparts and various traditional NNLMs. Our results on the challenging Google Billion word corpus show that both FOFE and dual FOFE yield very strong performance while significantly reducing the computational complexity over other NNLMs. Furthermore, the proposed dual-FOFE method further gives over 10% improvement in perplexity over the original FOFE model.

In this paper, we propose to learn word embeddings based on the recent fixed-size ordinally forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence into a fixed-size representation. We use FOFE to fully encode the left and right context of each word in a corpus to construct a novel word-context matrix, which is further weighted and factorized using truncated SVD to generate low-dimension word embedding vectors. We evaluate this alternate method in encoding word-context statistics and show the new FOFE method has a notable effect on the resulting word embeddings. Experimental results on several popular word similarity tasks have demonstrated that the proposed method outperforms other SVD models that use canonical count based techniques to generate word context matrices.

The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task. This paper describes our system (alpha) that is ranked among the top in the Shared Task, on both the in-domain test set (obtaining a 74.9% accuracy) and on the cross-domain test set (also attaining a 74.9% accuracy), demonstrating that the model generalizes well to the cross-domain data. Our model is equipped with intra-sentence gated-attention composition which helps achieve a better performance. In addition to submitting our model to the Shared Task, we have also tested it on the Stanford Natural Language Inference (SNLI) dataset. We obtain an accuracy of 85.5%, which is the best reported result on SNLI when cross-sentence attention is not allowed, the same condition enforced in RepEval 2017.

In this paper, we study a novel approach for named entity recognition (NER) and mention detection (MD) in natural language processing. Instead of treating NER as a sequence labeling problem, we propose a new local detection approach, which relies on the recent fixed-size ordinally forgetting encoding (FOFE) method to fully encode each sentence fragment and its left/right contexts into a fixed-size representation. Subsequently, a simple feedforward neural network (FFNN) is learned to either reject or predict entity label for each individual text fragment. The proposed method has been evaluated in several popular NER and MD tasks, including CoNLL 2003 NER task and TAC-KBP2015 and TAC-KBP2016 Tri-lingual Entity Discovery and Linking (EDL) tasks. Our method has yielded pretty strong performance in all of these examined tasks. This local detection approach has shown many advantages over the traditional sequence labeling methods.

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result—it further improves the performance even when added to the already very strong model.