No abstract

Abstract. In this paper, we provide a study on the use of tree kernels to encode syntactic parsing information in natural language learning. In particular, we propose a new convolution kernel, namely the Partial Tree (PT) kernel, to fully exploit dependency trees. We also propose an efficient algorithm for its computation which is futhermore sped-up by applying the selection of tree nodes with non-null kernel. The experiments with Support Vector Machines on the task of semantic role labeling and question classification show that (a) the kernel running time is linear on the average case and (b) the PT kernel improves on the other tree kernels when applied to the appropriate parsing paradigm.

This paper describes our deep learning system for sentiment analysis of tweets. The main contribution of this work is a new model for initializing the parameter weights of the convolutional neural network, which is crucial to train an accurate model while avoiding the need to inject any additional features. Briefly, we use an unsupervised neural language model to train initial word embeddings that are further tuned by our deep learning model on a distant supervised corpus. At a final stage, the pre-trained parameters of the network are used to initialize the model. We train the latter on the supervised training data recently made available by the official system evaluation campaign on Twitter Sentiment Analysis organized by Semeval-2015. A comparison between the results of our approach and the systems participating in the challenge on the official test sets, suggests that our model could be ranked in the first two positions in both the phrase-level subtask A (among 11 teams) and on the message-level subtask B (among 40 teams). This is an important evidence on the practical value of our solution.

We propose TandA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. Specifically, we first transfer a pre-trained model into a model for a general task by fine-tuning it with a large and high-quality dataset. We then perform a second fine-tuning step to adapt the transferred model to the target domain. We demonstrate the benefits of our approach for answer sentence selection, which is a well-known inference task in Question Answering. We built a large scale dataset to enable the transfer step, exploiting the Natural Questions dataset. Our approach establishes the state of the art on two well-known benchmarks, WikiQA and TREC-QA, achieving the impressive MAP scores of 92% and 94.3%, respectively, which largely outperform the the highest scores of 83.4% and 87.5% of previous work. We empirically show that TandA generates more stable and robust models reducing the effort required for selecting optimal hyper-parameters. Additionally, we show that the transfer step of TandA makes the adaptation step more robust to noise. This enables a more effective use of noisy datasets for fine-tuning. Finally, we also confirm the positive impact of TandA in an industrial setting, using domain specific datasets subject to different types of noise.

In this paper we have designed and experimented novel convolution kernels for automatic classification of predicate arguments. Their main property is the ability to process structured representations. Support Vector Machines (SVMs), using a combination of such kernels and the flat feature kernel, classify Prop-Bank predicate arguments with accuracy higher than the current argument classification stateof-the-art. Additionally, experiments on FrameNet data have shown that SVMs are appealing for the classification of semantic roles even if the proposed kernels do not produce any improvement.