Prodromos Malakasiotis

A survey of paraphrasing and textual entailment methods

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.

Learning Textual Entailment using SVMs and String Similarity Measures

We present the system that we submitted to the 3rd Pascal Recognizing Textual Entailment Challenge. It uses four Support Vector Machines, one for each subtask of the challenge, with features that correspond to string similarity measures operating at the lexical and shallow syntactic level.

An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition

BackgroundThis article provides an overview of the first BioASQ challenge, a competition on large-scale biomedical semantic indexing and question answering (QA), which took place between March and September 2013. BioASQ assesses the ability of systems to semantically index very large numbers of biomedical scientific articles, and to return concise and user-understandable answers to given natural language questions by combining information from biomedical articles and ontologies.ResultsThe 2013 BioASQ competition comprised two tasks, Task 1a and Task 1b. In Task 1a participants were asked to automatically annotate new PubMed documents with MeSH headings. Twelve teams participated in Task 1a, with a total of 46 system runs submitted, and one of the teams performing consistently better than the MTI indexer used by NLM to suggest MeSH headings to curators. Task 1b used benchmark datasets containing 29 development and 282 test English questions, along with gold standard (reference) answers, prepared by a team of biomedical experts from around Europe and participants had to automatically produce answers. Three teams participated in Task 1b, with 11 system runs. The BioASQ infrastructure, including benchmark datasets, evaluation mechanisms, and the results of the participants and baseline methods, is publicly available.ConclusionsA publicly available evaluation infrastructure for biomedical semantic indexing and QA has been developed, which includes benchmark datasets, and can be used to evaluate systems that: assign MeSH headings to published articles or to English questions; retrieve relevant RDF triples from ontologies, relevant articles and snippets from PubMed Central; produce “exact” and paragraph-sized “ideal” answers (summaries). The results of the systems that participated in the 2013 BioASQ competition are promising. In Task 1a one of the systems performed consistently better from the NLM’s MTI indexer. In Task 1b the systems received high scores in the manual evaluation of the “ideal” answers; hence, they produced high quality summaries as answers. Overall, BioASQ helped obtain a unified view of how techniques from text classification, semantic indexing, document and passage retrieval, question answering, and text summarization can be combined to allow biomedical experts to obtain concise, user-understandable answers to questions reflecting their real information needs.

Paraphrase Recognition Using Machine Learning to Combine Similarity Measures

This paper presents three methods that can be used to recognize paraphrases. They all employ string similarity measures applied to shallow abstractions of the input sentences, and a Maximum Entropy classifier to learn how to combine the resulting features. Two of the methods also exploit WordNet to detect synonyms and one of them also exploits a dependency parser. We experiment on two datasets, the MSR paraphrasing corpus and a dataset that we automatically created from the MTC corpus. Our system achieves state of the art or better results.

Using Centroids of Word Embeddings and Word Mover's Distance for Biomedical Document Retrieval in Question Answering.

We propose a document retrieval method for question answering that represents documents and questions as weighted centroids of word embeddings and reranks the retrieved documents with a relaxation of Word Movers Distance. Using biomedical questions and documents from BIOASQ, we show that our method is competitive with PUBMED. With a top-k approximation, our method is fast, and easily portable to other domains and languages.

AUEB: Two Stage Sentiment Analysis of Social Network Messages

This paper describes the system submitted for the Sentiment Analysis in Twitter Task of SEMEVAL 2014 and specifically the Message Polarity Classification subtask. We used a 2‐stage pipeline approach employing a linear SVM classifier at each stage and several features including morphological features, POS tags based features and lexicon based features.

MiniCount: Efficient Rewriting of COUNT-Queries Using Views

We present MiniCount, the first efficient sound and complete algorithm for finding maximally contained rewritings of conjunctive queries with count, using conjunctive views with count and conjunctive views without aggregation. An efficient and scalable solution to this problem yields significant benefits for data warehousing and decision support systems, as well as for powerful data integration systems.We first present a naive rewriting algorithm implicit in the recent theoretical results by Cohen et al. [5] and identify three independent sources of exponential complexity in the naive algorithm, including an expensive containment check. Then we present and discuss MiniCount and prove it sound and complete. We also present an experimental study that shows Mini- Count to be orders of magnitude faster than the naive algorithm, and to be able to scale to large numbers of views

aueb.twitter.sentiment at SemEval-2016 Task 4: A Weighted Ensemble of SVMs for Twitter Sentiment Analysis

This paper describes the system with which we participated in SemEval-2016 Task 4 (Sentiment Analysis in Twitter) and specifically the Message Polarity Classification subtask. Our system is a weighted ensemble of two systems. The first one is based on a previous sentiment analysis system and uses manually crafted features. The second system of our ensemble uses features based on word embeddings. Our ensemble was ranked 5th among 34 teams. The source code of our system is publicly available.

Adaptive Natural Language Interaction

The subject of this demonstration is natural language interaction, focusing on adaptivity and profiling of the dialogue management and the generated output (text and speech). These are demonstrated in a museum guide use-case, operating in a simulated environment. The main technical innovations presented are the profiling model, the dialogue and action management system, and the text generation and speech synthesis systems.

Deep Learning for User Comment Moderation

Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of English Wikipedia comments, we show that an RNN outperforms the previous state of the art in moderation. A deep, classification-specific attention mechanism improves further the overall performance of the RNN. We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation.