As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials.However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally; while extractive MRC focuses on higher local boundary preciseness for answer extraction.Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks.To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously.Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components.The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://github. com/Yilin1111/poi-net.* Corresponding author.This paper was partially supported by Key Projects of National Natural Science Foundation of China under

Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-domain annotated data. In this paper, we tackle an even harder problem by further limiting the amount of data available at training time. We propose a few-shot learning framework for relation classification, which is particularly powerful when the training data is very small. In this framework, models not only strive to classify query instances, but also seek underlying knowledge about the support instances to obtain better instance representations. The framework also includes a method for aggregating cross-domain knowledge into models by open-source task enrichment. Additionally, we construct a brand new dataset: the TinyRel-CM dataset, a few-shot relation classification dataset in health domain with purposely small training data and challenging relation classes. Experimental results demonstrate that our framework brings performance gains for most underlying classification models, outperforms the state-of-the-art results given small training data, and achieves competitive results with sufficiently large training data.

Predicting endings for narrative stories is a grand challenge for machine commonsense reasoning. The task requires ac- curate representation of the story semantics and structured logic knowledge. Pre-trained language models, such as BERT, made progress recently in this task by exploiting spurious statistical patterns in the test dataset, instead of 'understanding' the stories per se. In this paper, we propose to improve the representation of stories by first simplifying the sentences to some key concepts and second modeling the latent relation- ship between the key ideas within the story. Such enhanced sentence representation, when used with pre-trained language models, makes substantial gains in prediction accuracy on the popular Story Cloze Test without utilizing the biased validation data.

Neural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable.On the other hand, symbolic rules such as regular expressions are interpretable, require no training, and often achieve decent accuracy; but rules cannot benefit from labeled data when available and hence underperform neural networks in rich-resource scenarios.In this paper, we propose a type of recurrent neural networks called FA-RNNs that combine the advantages of neural networks and regular expression rules.An FA-RNN can be converted from regular expressions and deployed in zero-shot and cold-start scenarios.It can also utilize labeled data for training to achieve improved prediction accuracy.After training, an FA-RNN often remains interpretable and can be converted back into regular expressions.We apply FA-RNNs to text classification and observe that FA-RNNs significantly outperform previous neural approaches in both zeroshot and low-resource settings and remain very competitive in rich-resource settings.

Most of the machine translation systems rely on a large set of translation rules.These rules are treated as discrete and independent events.In this short paper, we propose a novel method to model rules as observed generation output of a compact hidden model, which leads to better generalization capability.We present a preliminary generative model to test this idea.Experimental results show about one point improvement on TER-BLEU over a strong baseline in Chinese-to-English translation.

We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire evaluation sets.

Supertagging is the tagging process of assigning the correct elementary tree of LTAG, or the correct supertag, to each word of an input sentence. In this paper we propose to use supertags to expose syntactic dependencies which are unavailable with POS tags. We first propose a novel method of applying Sparse Network of Winnow (SNoW) to sequential models. Then we use it to construct a supertagger that uses long distance syntactical dependencies, and the supertagger achieves an accuracy of 92.41%. We apply the supertagger to NP chunking. The use of supertags in NP chunking gives rise to almost 1% absolute increase (from 92.03% to 92.95%) in F-score under Transformation Based Learning(TBL) frame. The surpertagger described here provides an effective and efficient way to exploit syntactic information.