Articles

Traditional convolutional neural network (CNN) based query classification uses linear feature mapping in its convolution opera- tion. The recurrent neural network (RNN), differs from a CNN in representing word sequence with their ordering information kept explicitly. We propose using a deep long-short-term-memory (DLSTM) based fea- ture mapping to learn feature …...

We compare different word embeddings from a standard window based skipgram model, a skipgram model trained using dependency context features and a novel skipgram variant that utilizes additional information from dependency graphs. We explore the effectiveness of the different types of word embeddings for word similarity and sentence classification tasks. …...

We propose a hierarchical attention network for document classification. Our model has two distinctive characteristics: (i) it has a hier- archical structure that mirrors the hierarchical structure of documents; (ii) it has two levels of attention mechanisms applied at the word- and sentence-level, enabling it to attend dif- ferentially to …...

Automatically generated databases of English paraphrases have the drawback that they re- turn a single list of paraphrases for an input word or phrase. This means that all senses of polysemous words are grouped together, un- like WordNet which partitions different senses into separate synsets. We present a new method …...

The goal of sentence and document model- ing is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN) as a general- purpose classification system for both sen- tences and documents. DSCNN hierarchically builds …...

We introduce a latent activity model for work- place emails, positing that communication at work is purposeful and organized by activities. We pose the problem as probabilistic infer- ence in graphical models that jointly capture the interplay between latent activities and the email contexts they govern, such as the recipi- …...

Natural language inference (NLI) is a funda- mentally important task in natural language processing that has many applications. The recently released Stanford Natural Language Inference (SNLI) corpus has made it possi- ble to develop and evaluate learning-centered methods such as deep neural networks for nat- ural language inference (NLI). In …...

This paper presents a methodology to extract positive interpretations from negated state- ments. First, we automatically generate plau- sible interpretations using well-known gram- mar rules and manipulating semantic roles. Second, we score plausible alternatives ac- cording to their likelihood. Manual annota- tions show that the positive interpretations are intuitive to …...

Coherence is established by semantic connec- tions between sentences of a text which can be modeled by lexical relations. In this pa- per, we introduce the lexical coherence graph (LCG), a new graph-based model to represent lexical relations among sentences. The fre- quency of subgraphs (coherence patterns) of this graph …...

While there is increasing interest in automat- ically recognizing the argumentative structure of a text, recognizing the argumentative pur- pose of revisions to such texts has been less explored. Furthermore, existing revision clas- sification approaches typically ignore contex- tual information. We propose two approaches for utilizing contextual information when pre- …...

Gold annotations for supervised implicit se- mantic role labeling are extremely sparse and costly. As a lightweight alternative, this paper describes an approach based on unsupervised parsing which can do without iSRL-specific training data: We induce prototypical roles from large amounts of explicit SRL annota- tions paired with their distributed …...

Persuasive communication is the process of shaping, reinforcing and changing others’ re- sponses. In political debates, speakers ex- press their views towards the debated topics by choosing both the content of their discourse and the argumentation process. In this work we study the use of semantic frames for mod- elling …...

Argumentation mining is considered as a key technology for future search engines and au- tomated decision making. In such applica- tions, argumentative text segments have to be mined from large and diverse document col- lections. However, most existing argumenta- tion mining approaches tackle the classifica- tion of argumentativeness only for …...

Jauhar et al. (2015) recently proposed to learn sense-specific word representations by “retrofitting” standard distributional word rep- resentations to an existing ontology. We ob- serve that this approach does not require an ontology, and can be generalized to any graph defining word senses and relations between them. We create such …...

Understanding the argumentative structure of a persuasive essay involves addressing two challenging tasks: identifying the components of the essay’s argument and identifying the relations that occur between them. We ex- amine the under-investigated task of end-to- end argument mining in persuasive student es- says, where we (1) present the first …...

Unsupervised methods for learning distributed representations of words are ubiquitous in to- day’s NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This paper is a systematic comparison of models that learn such representations. We find that the …...

We introduce polyglot language models, re- current neural network models trained to pre- dict symbol sequences in many different lan- guages using shared representations of sym- bols and conditioning on typological infor- mation about the language to be predicted. We apply these to the problem of modeling phone sequences—a domain …...

We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information. Our model consists of an encoder, which uses monolingual and bilingual context (i.e. a parallel sentence) to choose a sense for a given word, and a decoder which predicts context words based on the …...

In this study, the problem of shallow pars- ing of Hindi-English code-mixed social me- dia text (CSMT) has been addressed. We have annotated the data, developed a language identifier, a normalizer, a part-of-speech tag- ger and a shallow parser. To the best of our knowledge, we are the first to …...

Creole languages do not fit into the tradi- tional tree model of evolutionary history be- cause multiple languages are involved in their formation. In this paper, we present several statistical models to explore the nature of cre- ole genesis. After reviewing quantitative stud- ies on creole genesis, we first tackle …...