In this article, we extensively study the use of syntactic and semantic structures obtained with shallow and full syntactic parsers for answer passage reranking. We propose several dependency and constituent-based structures, also enriched with Linked Open Data (LD) knowledge to represent pairs of questions and answer passages. We encode such tree structures in learning-to-rank (L2R) algorithms using tree kernels, which can project them in tree substructure spaces, where each dimension represents a powerful syntactic/semantic feature. Additionally, since we define links between question and passage structures, our tree kernel spaces also include relational structural features. We carried out an extensive comparative experimentation of our models for automatic answer selection benchmarks on different TREC QA corpora as well as the newer Wikipedia-based dataset, namely WikiQA, which has been widely used to test sentence rerankers. The results consistently demonstrate that our structural semantic models achieve the state of the art in passage reranking. In particular, we derived the following important findings: (i) relational syntactic structures are essential to achieve superior results; (ii) models trained with dependency trees can outperform those trained with shallow trees, e.g., in case of sentence reranking; (iii) external knowledge automatically generated with focus and question classifiers is very effective; and (iv) the semantic information derived by LD and incorporated in syntactic structures can be used to replace the knowledge provided by the above-mentioned classifiers. This is a remarkable advantage as it enables our models to increase coverage and portability over new domains.

High-level semantics tasks, e.g., paraphrasing, textual entailment or question answering, involve modeling of text pairs.Before the emergence of neural networks, this has been mostly performed using intra-pair features, which incorporate similarity scores or rewrite rules computed between the members within the same pair.In this paper, we compute scalar products between vectors representing similarity between members of different pairs, in place of simply using a single vector for each pair.This allows us to obtain a representation specific to any pair of pairs, which delivers the state of the art in answer sentence selection.Most importantly, our approach can outperform much more complex algorithms based on neural networks.

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.

Recent initiatives in IR community have shown the importance of going beyond factoid Question Answering (QA) in order to design useful real-world applications. Questions asking for descriptions or explanations are much more difficult to be solved, e.g., the machine learning models cannot focus on specific answer words or their lexical type. Thus, researchers have started to explore powerful methods for feature engineering. Two of the most promising methods are convolution tree kernels (CTKs) and convolutional neural networks (CNNs) as they have been shown to obtain high performance in the task of answer sentence selection in factoid QA. In this paper, we design state-of-the-art models for non-factoid QA also carried out on noisy data. In particular, we study and compare models for comment selection in a community QA (cQA) scenario, where the majority of questions regard descriptions or explanations. To deal with such complex task, we incorporate relational information holding between questions and comments as well as domain-specific features into both convolutional models above.

Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Kateryna Tymoshenko, Alessandro Moschitti, Lluís Màrquez. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

In this paper, we extensively study the use of syntactic and semantic structures obtained with shallow and deeper syntactic parsers in the answer passage reranking task. We propose several dependency-based structures enriched with Linked Open Data (LD) knowledge for representing pairs of questions and answer passages. We use such tree structures in learning to rank (L2R) algorithms based on tree kernel. The latter can represent questions and passages in a tree fragment space, where each substructure represents a powerful syntactic/semantic feature. Additionally since we define links between structures, tree kernels also generate relational features spanning question and passage structures. We derive very important findings, which can be useful to build state-of-the-art systems: (i) full syntactic dependencies can outperform shallow models also using external knowledge and (ii) the semantic information should be derived by effective and high-coverage resources, e.g., LD, and incorporated in syntactic structures to be effective. We demonstrate our findings by carrying out an extensive comparative experimentation on two different TREC QA corpora and one community question answer dataset, namely Answerbag. Our comparative analysis on well-defined answer selection benchmarks consistently demonstrates that our structural semantic models largely outperform the state of the art in passage reranking.

In this paper, we propose to use semantic knowledge from Wikipedia and largescale structured knowledge datasets available as Linked Open Data (LOD) for the answer passage reranking task.We represent question and candidate answer passages with pairs of shallow syntactic/semantic trees, whose constituents are connected using LOD.The trees are processed by SVMs and tree kernels, which can automatically exploit tree fragments.The experiments with our SVM rank algorithm on the TREC Question Answering (QA) corpus show that the added relational information highly improves over the state of the art, e.g., about 15.4% of relative improvement in P@1.

Systems based on statistical and machine learning methods have been shown to be extremely effective and scalable for the analysis of large amount of textual data. However, in the recent years, it becomes evident that one of the most important direction of improvement in natural language processing (NLP) tasks, like word sense disambiguation, coreference resolution, relation extraction, and other tasks related to knowledge extraction, is by exploiting semantics. While in the past, the unavailability of rich and complete semantic descriptions constituted a serious limitation of their applicability, nowadays, the Semantic Web made available a large amount of logically encoded information (e.g. ontologies, RDF(S)-data, linked data, etc.), which constitute a valuable source of semantics. However, web semantics cannot be easily plugged into machine learning systems. Therefore the objective of this paper is to define a reference methodology for combining semantics information available in the web under the form of logical theories, with statistical methods for NLP. The major problems that we have to solve to implement our methodology concern (i) the selection of the correct and minimal knowledge among the large amount available in the web, (ii) the representation of uncertain knowledge, and (iii) the resolution and the encoding of the rules that combine knowledge retrieved from Semantic Web sources with semantics in the text. In order to evaluate the appropriateness of our approach, we present an application of the methodology to the problem of intra-document coreference resolution, and we show by means of some experiments on the ACE 2005 dataset, how the injection of knowledge is correlated to the improvement of the performance of our approach on this tasks.