In this paper, we study, compare and combine two state-of-the-art approaches to automatic feature engineering: Convolution Tree Kernels (CTKs) and Convolutional Neural Networks (CNNs) for learning to rank answer sentences in a Question Answering (QA) setting. When dealing with QA, the key aspect is to encode relational information between the constituents of question and answer in learning algorithms. For this purpose, we propose novel CNNs using relational information and combined them with relational CTKs. The results show that (i) both approaches achieve the state of the art on a question answering task, where CTKs produce higher accuracy and (ii) combining such methods leads to unprecedented high results.

An important asset of using Deep Neural Networks (DNNs) for text applications is their ability to automatically engineer features. Unfortunately, DNNs usually require a lot of training data, especially for high-level semantic tasks such as community Question Answering (cQA). In this paper, we tackle the problem of data scarcity by learning the target DNN together with two auxiliary tasks in a multitask learning setting. We exploit the strong semantic connection between selection of comments relevant to (i) new questions and (ii) forum questions. This enables a global representation for comments, new and previous questions. The experiments of our model on a SemEval challenge dataset for cQA show a 20% relative improvement over standard DNNs.

English.In this paper, we introduce a Deep Neural Network (DNN) for engineering Named Entity Recognizers (NERs) in Italian. Our network uses a sliding window of word contexts to predict tags. It relies on a simple word-level log-likelihood as a cost function and uses a new recurrent feedback mechanism to ensure that the dependencies between the output tags are properly modeled. The evaluation on the Evalita 2009 benchmark shows that our DNN performs on par with the best NERs, outperforming the state of the art when gazetteer features are used.Italiano. In questo lavoro, si introduce una rete neurale deep (DNN) per progettare estrattori automatici di entitá nominate (NER) per la lingua italiana. La rete utilizza una finestra scorrevole di contesti delle parole per predire le loro etichette con associata probabilitá, la qualeè usata come funzione di costo. Inoltre si utilizza un nuovo meccanismo di retroazione ricorrente per modellare le dipendenze tra le etichette di uscita. La valutazione della DNN sul dataset di Evalita 2009 indica chè e alla pari con i migliori NER e migliora lo stato dell'arte quando si aggiungono delle features derivate dai dizionari.

Recent work has shown that Tree Kernels (TKs) and Convolutional Neural Networks (CNNs) obtain the state of the art in answer sentence reranking. Additionally, their combination used in Support Vector Machines (SVMs) is promising as it can exploit both the syntactic patterns captured by TKs and the embeddings learned by CNNs. However, the embeddings are constructed according to a classification function, which is not directly exploitable in the preference ranking algorithm of SVMs. In this work, we propose a new hybrid approach combining preference ranking applied to TKs and pointwise ranking applied to CNNs. We show that our approach produces better results on two well-known and rather different datasets: WikiQA for answer sentence selection and SemEval cQA for comment selection in Community Question Answering.

Effectively using full syntactic parsing information in Neural Networks (NNs) to solve relational tasks, e.g., question similarity, is still an open problem. In this paper, we propose to inject structural representations in NNs by (i) learning an SVM model using Tree Kernels (TKs) on relatively few pairs of questions (few thousands) as gold standard (GS) training data is typically scarce, (ii) predicting labels on a very large corpus of question pairs, and (iii) pre-training NNs on such large corpus. The results on Quora and SemEval question similarity datasets show that NNs trained with our approach can learn more accurate models, especially after fine tuning on GS.