Articles

Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two key techni- cal problems that make them slow and un- wieldy for large-scale NLP tasks: they usu- ally operate on parsed sentences and they do not directly support batched computa- …...

This paper presents neural probabilistic parsing models which explore up to third- order graph-based parsing with maximum likelihood training criteria. Two neural network extensions are exploited for per- formance improvement. Firstly, a convo- lutional layer that absorbs the influences of all words in a sentence is used so that sentence-level …...

One of the major challenges for statisti- cal machine translation (SMT) is to choose the appropriate translation rules based on the sentence context. This paper pro- poses a continuous space rule selection (CSRS) model for syntax-based SMT to perform this context-dependent rule selec- tion. In contrast to existing maximum en- …...

We propose an approach for semantic parsing that uses a recurrent neural net- work to map a natural language question into a logical form representation of a KB query. Building on recent work by (Wang et al., 2015), the interpretable log- ical forms, which are structured objects obeying certain constraints, …...

In this paper, we investigate the possibil- ity to automatically generate sports news from live text commentary scripts. As a preliminary study, we treat this task as a special kind of document summarization based on sentence extraction. We for- mulate the task in a supervised learning to rank framework, utilizing …...

Word embeddings – distributed represen- tations of words – in deep learning are beneficial for many tasks in NLP. How- ever, different embedding sets vary greatly in quality and characteristics of the cap- tured information. Instead of relying on a more advanced algorithm for embed- ding learning, this paper proposes …...

Website privacy policies are often ignored by Internet users, because these docu- ments tend to be long and difficult to un- derstand. However, the significance of pri- vacy policies greatly exceeds the attention paid to them: these documents are binding legal agreements between website opera- tors and their users, and …...

In this work, we propose a novel method to incorporate corpus-level discourse infor- mation into language modelling. We call this larger-context language model. We in- troduce a late fusion approach to a recur- rent language model based on long short- term memory units (LSTM), which helps the LSTM unit keep …...

Relation classification is a crucial ingredi- ent in numerous information extraction sys- tems seeking to mine structured facts from text. We propose a novel convolutional neural network architecture for this task, relying on two levels of attention in order to better discern patterns in heterogeneous contexts. This architecture enables end- …...

Knowledge bases (KBs) are often greatly incomplete, necessitating a demand for K- B completion. The path ranking algorith- m (PRA) is one of the most promising ap- proaches to this task. Previous work on PRA usually follows a single-task learn- ing paradigm, building a prediction mod- el for each relation …...

Attention based recurrent neural networks have shown advantages in representing natural language sentences (Hermann et al., 2015; Rockt¨aschel et al., 2015; Tan et al., 2015). Based on recurrent neural networks (RNN), external attention infor- mation was added to hidden representa- tions to get an attentive sentence represen- tation. Despite the …...

This paper connects a vector-based com- position model to a formal semantics, the Dependency-based Compositional Se- mantics (DCS). We show theoretical evi- dence that the vector compositions in our model conform to the logic of DCS. Ex- perimentally, we show that vector-based composition brings a strong ability to calculate similar …...

This study proposes the bilingual seg- mented topic model (BiSTM), which hi- erarchically models documents by treat- ing each document as a set of segments, e.g., sections. While previous bilingual topic models, such as bilingual latent Dirichlet allocation (BiLDA) (Mimno et al., 2009; Ni et al., 2009), consider only cross-lingual …...

The distinction between restrictive and non-restrictive modification in noun phrases is a well studied subject in linguistics. Automatically identifying non-restrictive modifiers can provide NLP applications with shorter, more salient arguments, which were found beneficial by several recent works. While previous work showed that restrictiveness can be annotated with high agreement, …...

We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains. To that end, we first create (for experimental purposes) an entailment dataset for the clinical do- main, and a highly competitive supervised entailment system, ENT, that is effective (out of …...

Intelligent assistants on mobile devices, such as Siri, have recently gained con- siderable attention as novel applications of dialogue technologies. A tremendous amount of real users of intelligent assis- tants provide us with an opportunity to ex- plore a novel task of predicting whether users will continually use their intelligent …...

This paper introduces a novel model for semantic role labeling that makes use of neural sequence modeling techniques. Our approach is motivated by the obser- vation that complex syntactic structures and related phenomena, such as nested subordinations and nominal predicates, are not handled well by existing models. Our model treats …...

In this paper, we present the first exper- iments using neural network models for the task of error detection in learner writ- ing. We perform a systematic comparison of alternative compositional architectures and propose a framework for error detec- tion based on bidirectional LSTMs. Ex- periments on the CoNLL-14 shared …...

Computationally modeling the evolution of science by tracking how scientific top- ics rise and fall over time has important implications for research funding and pub- lic policy. However, little is known about the mechanisms underlying topic growth and decline. We investigate the role of rhetorical framing: whether the rhetori- cal …...

Effective text classification requires experts to annotate data with labels; these training data are time-consuming and expensive to obtain. If you know what labels you want, active learning can reduce the number of labeled documents needed. However, estab- lishing the label set remains difficult. An- notators often lack the global …...