Articles

An extensive literature in computational social science examines how features of messages, advertisements, and other cor- pora affect individuals’ decisions, but these analyses must specify the relevant features of the text before the experiment. Automated text analysis methods are able to discover features of text, but these meth- ods cannot …...

We propose a new task in the field of computational argumentation in which we investigate qualitative properties of Web arguments, namely their convincingness. We cast the problem as relation classifica- tion, where a pair of arguments having the same stance to the same prompt is judged. We annotate a large …...

State legislatures often rely on existing text when drafting new bills. Resource and expertise constraints, which often drive this copying behavior, can be taken ad- vantage of by lobbyists and special inter- est groups. These groups provide model bills, which encode policy agendas, with the intent that the models become …...

We examine communications in a social network to study user emotional contrast – the propensity of users to express dif- ferent emotions than those expressed by their neighbors. Our analysis is based on a large Twitter dataset, consisting of the tweets of 123,513 users from the USA and Canada. Focusing …...

Traditional syntax models typically lever- age part-of-speech (POS) information by constructing features from hand-tuned templates. We demonstrate that a better approach is to utilize POS tags as a reg- ularizer of learned representations. We propose a simple method for learning a stacked pipeline of models which we call “stack-propagation”. We …...

The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation. In this paper, we ask a fundamental question: can neural machine translation generate a character sequence without any explicit segmentation? To answer this question, we evaluate an attention-based encoder– decoder with …...

We describe a search algorithm for opti- mizing the number of latent states when estimating latent-variable PCFGs with spectral methods. Our results show that contrary to the common belief that the number of latent states for each nontermi- nal in an L-PCFG can be decided in isola- tion with spectral …...

We present WIKIREADING, a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the cor- responding Wikipedia articles. The task contains a rich variety of challenging clas- sification and …...

We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages shar- ing the characteristic that human subjects are able to guess their last word if they are exposed to the whole …...

There has recently been a lot of interest in unsupervised methods for learning sense distributions, particularly in applications where sense distinctions are needed. This paper analyses a state-of-the-art method for sense distribution learning, and op- timises it for application to the entire vocabulary of a given language. The optimised method …...

This paper complements semantic role representations with spatial knowledge be- yond indicating plain locations. Namely, we extract where entities are (and are not) located, and for how long (seconds, hours, days, etc.). Crowdsourced annotations show that this additional knowledge is in- tuitive to humans and can be annotated by non-experts. …...

Understanding how words change their meanings over time is key to models of language and cultural evolution, but his- torical data on meaning is scarce, mak- ing theories hard to develop and test. Word embeddings show promise as a di- achronic tool, but have not been carefully evaluated. We develop …...

Recently, many NLP tasks have benefit- ed from distributed word representation. However, it remains unknown whether embedding models are really immune to the typological diversity of languages, despite the language-independent archi- tecture. Here we investigate three repre- sentative models on a large set of language samples by mapping dense embedding …...

We consider the task of learning a context- dependent mapping from utterances to de- notations. With only denotations at train- ing time, we must search over a combina- torially large space of logical forms, which is even larger with context-dependent ut- terances. To cope with this challenge, we perform successive …...

We enrich a curated resource of common- sense knowledge by formulating the prob- lem as one of knowledge base comple- tion (KBC). Most work in KBC focuses on knowledge bases like Freebase that re- late entities drawn from a fixed set. How- ever, the tuples in ConceptNet (Speer and Havasi, …...

Modeling relation paths has offered sig- nificant gains in embedding models for knowledge base (KB) completion. How- ever, enumerating paths between two en- tities is very expensive, and existing ap- proaches typically resort to approxima- tion with a sampled subset. This problem is particularly acute when text is jointly modeled …...

The automatic detection of causal relation- ships in text is important for natural lan- guage understanding. This task has proven to be difficult, however, due to the need for world knowledge and inference. We fo- cus on a sub-task of this problem where an open class set of linguistic markers …...

Most of the sequence tagging tasks in nat- ural language processing require to recog- nize segments with certain syntactic role or semantic meaning in a sentence. They are usually tackled with Conditional Ran- dom Fields (CRFs), which do indirect word-level modeling over word-level fea- tures and thus cannot make full …...

Cross-lingual sentiment classification aims to adapt the sentiment resource in a resource-rich language to a resource-poor language. In this study, we propose a representation learning approach which simultaneously learns vector representa- tions for the texts in both the source and the target languages. Different from pre- vious research which only …...

We propose a novel reranking method to extend a deterministic neural dependency parser. Different to conventional k-best reranking, the proposed model integrates search and learning by utilizing a dynamic action revising process, using the rerank- ing model to guide modification for the base outputs and to rerank the candidates. The …...