This research was conducted when the authors were at Microsoft Research.

Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is restricted in plot planning, or can only generate stories in a narrow domain. In this paper, we explore open-domain story generation that writes stories given a title (topic) as input. We propose a plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The dynamic schema interweaves story planning and its surface realization in text, while the static schema plans out the entire storyline before generating stories. Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.

We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. In this work, we introduce the notion of the regard towards a demographic, use the varying levels of regard towards different demographics as a defining metric for bias in NLG, and analyze the extent to which sentiment scores are a relevant proxy metric for regard. To this end, we collect strategically-generated text from language models and manually annotate the text with both sentiment and regard scores. Additionally, we build an automatic regard classifier through transfer learning, so that we can analyze biases in unseen text. Together, these methods reveal the extent of the biased nature of language model generations. Our analysis provides a study of biases in NLG, bias metrics and correlated human judgments, and empirical evidence on the usefulness of our annotated dataset.

We consider the task of named entity recognition for Chinese social media. The long line of work in Chinese NER has focused on formal domains, and NER for social media has been largely restricted to English. We present a new corpus of Weibo messages annotated for both name and nominal mentions. Additionally, we evaluate three types of neural embeddings for representing Chinese text. Finally, we propose a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text. Our methods yield a 9% improvement over a stateof-the-art baseline.

We introduce a novel architecture for dependency parsing: stack-pointer networks (STACKPTR). Combining pointer networks (Vinyals et al., 2015) with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion. The stack tracks the status of the depthfirst search and the pointer networks select one child for the word at the top of the stack at each step. The STACKPTR parser benefits from the information of the whole sentence and all previously derived subtree structures, and removes the leftto-right restriction in classical transitionbased parsers. Yet, the number of steps for building any (including non-projective) parse tree is linear in the length of the sentence just as other transition-based parsers, yielding an efficient decoding algorithm with O(n 2 ) time complexity. We evaluate our model on 29 treebanks spanning 20 languages and different dependency annotation schemas, and achieve state-of-theart performance on 21 of them.

Named entity recognition, and other information extraction tasks, frequently use linguistic features such as part of speech tags or chunkings. For languages where word boundaries are not readily identified in text, word segmentation is a key first step to generating features for an NER system. While using word boundary tags as features are helpful, the signals that aid in identifying these boundaries may provide richer information for an NER system. New state-of-the-art word segmentation systems use neural models to learn representations for predicting word boundaries. We show that these same representations, jointly trained with an NER system, yield significant improvements in NER for Chinese social media. In our experiments, jointly training NER and word segmentation with an LSTM-CRF model yields nearly 5% absolute improvement over previously published results.

Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem. Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given context that share no common words with reference responses. A recent work proposed Referenced metric and Unreferenced metric Blended Evaluation Routine (RUBER) to combine a learning-based metric, which predicts relatedness between a generated response and a given query, with reference-based metric; it showed high correlation with human judgments. In this paper, we explore using contextualized word embeddings to compute more accurate relatedness scores, thus better evaluation metrics. Experiments show that our evaluation metrics outperform RUBER, which is trained on static embeddings.

We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence 1 (Egidi and Gerrig, 2009) and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.