Articles

AbstractWe propose a new, socially-impactful task for natural language processing: from a news corpus, extract names of persons who have been killed by police. We present a newly collected police fatality corpus, which we release publicly, and present a model to solve this problem that uses EM-based distant supervision with …...

AbstractThe ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date rely on hand-engineered features and there is still no consensus in the field as to which features are optimal for this task. In this …...

AbstractQuestions play a prominent role in social interactions, performing rhetorical functions that go beyond that of simple informational exchange. The surface form of a question can signal the intention and background of the person asking it, as well as the nature of their relation with the interlocutor. While the informational …...

Implicit discourse relation recognition is a crucial component for automatic discourse- level analysis and nature language understand- ing. Previous studies exploit discriminative models that are built on either powerful man- ual features or deep discourse representations. In this paper, instead, we explore generative models and propose a variational neural dis- …...

In this paper, we study the task of response selection for multi-turn human-computer con- versation. Previous approaches take word as a unit and view context and response as se- quences of words. This kind of approaches do not explicitly take each utterance as a unit, therefore it is difficult to …...

In this paper we present PaCCSS–IT, a Paral- lel Corpus of Complex–Simple Sentences for ITalian. To build the resource we develop a new method for automatically acquiring a cor- pus of complex–simple paired sentences able to intercept structural transformations and par- ticularly suitable for text simplification. The method requires a …...

RST-style document-level discourse parsing remains a difficult task and efficient deep learning models on this task have rarely been presented. In this paper, we propose an attention-based hierarchical neural network model for discourse parsing. We also incor- porate tensor-based transformation function to model complicated feature interactions. Ex- perimental results show …...

ive Compression of Sentences and Short Paragraphs Kristina Toutanova Microsoft Research Redmond, WA, USA Chris Brockett Microsoft Research Redmond, WA, USA Ke M. Tran∗ University of Amsterdam Amsterdam, The Netherlands Saleema Amershi Microsoft Research Redmond, WA, USA Abstract We introduce a manually-created, multi- reference dataset for abstractive sentence and short …...

Recurrent neural networks can generate lo- cally coherent text but often have difficulties representing what has already been generated and what still needs to be said – especially when constructing long texts. We present the neural checklist model, a recurrent neural net- work that models global coherence by stor- ing …...

In this work we explore deep generative mod- els of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and apply it to the task of compressing sentences. In this application …...

Automatically solving algebra word problems has raised considerable interest recently. Ex- isting state-of-the-art approaches mainly rely on learning from human annotated equations. In this paper, we demonstrate that it is pos- sible to efficiently mine algebra problems and their numerical solutions with little to no man- ual effort. To leverage …...

We propose a fast and scalable method for semi-supervised learning of sequence models, based on anchor words and moment matching. Our method can handle hidden Markov mod- els with feature-based log-linear emissions. Unlike other semi-supervised methods, no de- coding passes are necessary on the unlabeled data and no graph needs …...

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but power- ful extension to the state in the decoding RNN. This memory-enhanced RNN de- coder is called MEMDEC. At each time during decoding, MEMDEC will read from this memory and …...

In this paper, we propose a novel finetuning algorithm for the recently introduced multi- way, multilingual neural machine translate that enables zero-resource machine transla- tion. When used together with novel many- to-one translation strategies, we empirically show that this finetuning algorithm allows the multi-way, multilingual model to translate a zero-resource …...

Most of the state-of-the-art sentiment classifi- cation methods are based on supervised learn- ing algorithms which require large amounts of manually labeled data. However, the labeled resources are usually imbalanced in different languages. Cross-lingual sentiment classification tackles the problem by adapting the sentiment resources in a resource-rich language to resource-poor …...

Within the field of Statistical Machine Trans- lation (SMT), the neural approach (NMT) has recently emerged as the first technology able to challenge the long-standing dominance of phrase-based approaches (PBMT). In particu- lar, at the IWSLT 2015 evaluation campaign, NMT outperformed well established state-of- the-art PBMT systems on English-German, a …...

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expres- sions in Twitter. Most previous work in so- cial media analysis has to rely on tempo- ral resolvers that are designed for well-edited text, and therefore suffer from reduced perfor- mance due to domain mismatch. We present a …...

In this paper, we study cross-domain senti- ment classification with neural network archi- tectures. We borrow the idea from Structural Correspondence Learning and use two auxil- iary tasks to help induce a sentence embedding that supposedly works well across domains for sentiment classification. We also propose to jointly learn this …...

It is well-known that opinions have targets. Extracting such targets is an important prob- lem of opinion mining because without know- ing the target of an opinion, the opinion is of limited use. So far many algorithms have been proposed to extract opinion targets. However, an opinion target can be …...

We introduce a deep memory network for aspect level sentiment classification. Un- like feature-based SVM and sequential neural models such as LSTM, this approach explic- itly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and tex- t representation are calculated …...