Articles

A common use of language is to refer to visually present objects. Modelling it in computers requires modelling the link between language and perception. The “words as classifiers” model of grounded semantics views words as classifiers of perceptual contexts, and composes the meaning of a phrase through composition of the …...

Event extraction is a particularly chal- lenging information extraction task, which intends to identify and classify event triggers and arguments from raw text. In recent works, when determining event types (trigger classification), most of the works are either pattern-only or feature-only. However, although patterns cannot cover all representations of an …...

This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is chal- lenging due to the tangled characteristics of the Japanese language, such as case dis- appearance and argument omission. To unravel this problem, we learn selectional preferences …...

A key goal in natural language genera- tion (NLG) is to enable fast generation even with large vocabularies, grammars and worlds. In this work, we build upon a recently proposed NLG system, Sentence Tree Realization with UCT (STRUCT). We describe four enhancements to this system: (i) pruning the grammar based …...

We present several methods for stemming and lemmatization based on discrimina- tive string transduction. We exploit the paradigmatic regularity of semi-structured inflection tables to identify stems in an un- supervised manner with over 85% accu- racy. Experiments on English, Dutch and German show that our stemmers substan- tially outperform Snowball …...

We present a new proof that O2 is a mul- tiple context-free language. It contrasts with a recent proof by Salvati (2015) in its avoidance of concepts that seem specific to two-dimensional geometry, such as the complex exponential function. Our simple proof creates realistic prospects of widen- ing the results …...

Context is crucial for identifying argumen- tative relations in text, but many argument mining methods make little use of contex- tual features. This paper presents context- aware argumentative relation mining that uses features extracted from writing top- ics as well as from windows of context sentences. Experiments on student essays …...

We present a novel end-to-end neural model to extract entities and relations be- tween them. Our recurrent neural net- work based model captures both word se- quence and dependency tree substructure information by stacking bidirectional tree- structured LSTM-RNNs on bidirectional sequential LSTM-RNNs. This allows our model to jointly represent both …...

In this paper, we propose a novel mecha- nism for enriching the feature vector, for the task of sarcasm detection, with cogni- tive features extracted from eye-movement patterns of human readers. Sarcasm detec- tion has been a challenging research prob- lem, and its importance for NLP applica- tions such as …...

Most machine translation systems con- struct translations from a closed vocabu- lary of target word forms, posing problems for translating into languages that have productive compounding processes. We present a simple and effective approach that deals with this problem in two phases. First, we build a classifier that identifies spans …...

Automatic spoken language assessment systems are becoming increasingly impor- tant to meet the demand for English sec- ond language learning. This is a challeng- ing task due to the high error rates of, even state-of-the-art, non-native speech recog- nition. Consequently current systems pri- marily assess fluency and pronunciation. However, content …...

State-of-the-art sequence labeling systems traditionally require large amounts of task- specific knowledge in the form of hand- crafted features and data pre-processing. In this paper, we introduce a novel neu- tral network architecture that benefits from both word- and character-level representa- tions automatically, by using combination of bidirectional LSTM, CNN …...

Nearly all previous work on neural ma- chine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel word- character solution to achieving open vo- cabulary NMT. We build hybrid systems that translate mostly at the word level …...

We construct a humans-in-the-loop super- vised learning framework that integrates crowdsourcing feedback and local knowl- edge to detect job-related tweets from in- dividual and business accounts. Using data-driven ethnography, we examine dis- course about work by fusing language- based analysis with temporal, geospa- tional, and labor statistics information. 1...

Recently, there is rising interest in mod- elling the interactions of text pair with deep neural networks. In this paper, we propose a model of deep fusion LSTMs (DF-LSTMs) to model the strong inter- action of text pair in a recursive match- ing way. Specifically, DF-LSTMs con- sist of two …...

We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asym- metric latent-variable translation models (i.e., source-to-target and target-to-source) to agree on identifying latent phrase and word alignments. The agreement is de- fined at both word and phrase …...

Automatically recognising medical con- cepts mentioned in social media messages (e.g. tweets) enables several applications for enhancing health quality of people in a community, e.g. real-time monitoring of infectious diseases in population. How- ever, the discrepancy between the type of language used in social media and med- ical ontologies poses …...

We present persona-based models for han- dling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed em- beddings that capture individual charac- teristics such as background information and speaking style. A dyadic speaker- addressee model captures properties of in- teractions between two interlocutors. …...

Lexico-semantic knowledge of our native language provides an initial foundation for second language learning. In this paper, we investigate whether and to what extent the lexico-semantic models of the native language (L1) are transferred to the sec- ond language (L2). Specifically, we focus on the problem of lexical choice and …...

Dialogue topic tracking is a sequential la- belling problem of recognizing the topic state at each time step in given dialogue sequences. This paper presents various ar- tificial neural network models for dialogue topic tracking, including convolutional neural networks to account for semantics at each individual utterance, and recurrent neural …...