EMNLP 2015 Papers

We present a novel framework of system combination for multi-document summarization. For each input set (input), we generate candidate summaries by combining whole sentences from the summaries generated by different systems. We show that the oracle among these candidates is much better than the summaries that we have combined. We then present a supervised model to select among the candidates. The model relies on a rich set of features that capture content importance from different perspectives. Our model performs better than the systems that we combined based on manual and automatic evaluations. We also achieve very competitive performance on six DUC/TAC datasets, comparable to the state-of-the-art on most datasets.

Trending topics in microblogs such as Twitter are valuable resources to understand social aspects of real-world events. To enable deep analyses of such trends, semantic annotation is an effective approach; yet the problem of annotating microblog trending topics is largely unexplored by the research community. In this work, we tackle the problem of mapping trending Twitter topics to entities from Wikipedia. We propose a novel model that complements traditional text-based approaches by rewarding entities that exhibit a high temporal correlation with topics during their burst time period. By exploiting temporal information from the Wikipedia edit history and page view logs, we have improved the annotation performance by 17-28%, as compared to the competitive baselines.

In this paper, we present a comprehensive study of the relationship between an individual’s personal traits and his/her brand preferences. In our analysis, we included a large number of character traits such as personality, personal values and individual needs. These trait features were obtained from both a psychometric survey and automated social media analytics. We also included an extensive set of brand names from diverse product categories. From this analysis, we want to shed some light on (1) whether it is possible to use personal traits to infer an individual’s brand preferences (2) whether the trait features automatically inferred from social media are good proxies for the ground truth character traits in brand preference prediction.

Text data has recently been used as evidence in estimating the political ideologies of individuals, including political elites and social media users. While inferences about people are often the intrinsic quantity of interest, we draw inspiration from open information extraction to identify a new task: inferring the political import of propositions like OBAMA IS A SOCIALIST. We present several models that exploit the structure that exists between people and the assertions they make to learn latent positions of people and propositions at the same time, and we evaluate them on a novel dataset of propositions judged on a political spectrum.

This paper describes an approach to largescale modeling of sentiment analysis for the social sciences. The goal is to model relations between nation states through social media. Many cross-disciplinary applications of NLP involve making predictions (such as predicting political elections), but this paper instead focuses on a model that is applicable to broader analysis. Do citizens express opinions in line with their home country’s formal relations? When opinions diverge over time, what is the cause and can social media serve to detect these changes? We describe several learning algorithms to study how the populace of a country discusses foreign nations on Twitter, ranging from state-of-theart contextual sentiment analysis to some required practical learners that filter irrelevant tweets. We evaluate on standard sentiment evaluations, but we also show strong correlations with two public opinion polls and current international alliance relationships. We conclude with some political science use cases.

Divergent word order between languages causes delay in simultaneous machine translation. We present a sentence rewriting method that generates more monotonic translations to improve the speedaccuracy tradeoff. We design grammaticality and meaning-preserving syntactic transformation rules that operate on constituent parse trees. We apply the rules to reference translations to make their word order closer to the source language word order. On Japanese-English translation (two languages with substantially different structure), incorporating the rewritten, more monotonic reference translation into a phrase-based machine translation system enables better translations faster than a baseline system that only uses gold reference translations.

We present a novel approach for unsupervised induction of a Reordering Grammar using a modified form of permutation trees (Zhang and Gildea, 2007), which we apply to preordering in phrase-based machine translation. Unlike previous approaches, we induce in one step both the hierarchical structure and the transduction function over it from word-aligned parallel corpora. Furthermore, our model (1) handles non-ITG reordering patterns (up to 5-ary branching), (2) is learned from all derivations by treating not only labeling but also bracketing as latent variable, (3) is entirely unlexicalized at the level of reordering rules, and (4) requires no linguistic annotation. Our model is evaluated both for accuracy in predicting target order, and for its impact on translation quality. We report significant performance gains over phrase reordering, and over two known preordering baselines for English-Japanese.

Compared to tree grammars, graph grammars have stronger generative capacity over structures. Based on an edge replacement grammar, in this paper we propose to use a synchronous graph-to-string grammar for statistical machine translation. The graph we use is directly converted from a dependency tree by labelling edges. We build our translation model in the log-linear framework with standard features. Large-scale experiments on Chinese‐English and German‐English tasks show that our model is significantly better than the state-of-the-art hierarchical phrase-based (HPB) model and a recently improved dependency tree-to-string model on BLEU, METEOR and TER scores. Experiments also suggest that our model has better capability to perform long-distance reordering and is more suitable for translating long sentences.

In this paper, we introduce an approach to automatically map a standard distributional semantic space onto a set-theoretic model. We predict that there is a functional relationship between distributional information and vectorial concept representations in which dimensions are predicates and weights are generalised quantifiers. In order to test our prediction, we learn a model of such relationship over a publicly available dataset of feature norms annotated with natural language quantifiers. Our initial experimental results show that, at least for domain-specific data, we can indeed map between formalisms, and generate high-quality vector representations which encapsulate set overlap information. We further investigate the generation of natural language quantifiers from such vectors.

Distributional methods have proven to excel at capturing fuzzy, graded aspects of meaning (Italy is more similar to Spain than to Germany). In contrast, it is difficult to extract the values of more specific attributes of word referents from distributional representations, attributes of the kind typically found in structured knowledge bases (Italy has 60 million inhabitants). In this paper, we pursue the hypothesis that distributional vectors also implicitly encode referential attributes. We show that a standard supervised regression model is in fact sufficient to retrieve such attributes to a reasonable degree of accuracy: When evaluated on the prediction of both categorical and numeric attributes of countries and cities, the model consistently reduces baseline error by 30%, and is not far from the upper bound. Further analysis suggests that our model is able to “objectify” distributional representations for entities, anchoring them more firmly in the external world in measurable ways.

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-ofwords and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations. 1