A Compositional and Interpretable Semantic Space

Vector Space Models (VSMs) of Semantics are useful tools for exploring the semantics of single words, and the composition of words to make phrasal meaning. While many methods can estimate the meaning (i.e. vector) of a phrase, few do so in an interpretable way. We introduce a new method (CNNSE) that allows word and phrase vectors to adapt to the notion of composition. Our method learns a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation. Interpretability allows for the exploration of phrasal semantics, which we leverage to analyze performance on a behavioral task.

Evidence of syntactic working memory usage in MEG data

While reading times are often used to measure working memory load, frequency effects (such as surprisal or n-gram frequencies) also have strong confounding effects on reading times. This work uses a naturalistic audio corpus with magnetoencephalographic (MEG) annotations to measure working memory load during sentence processing. Alpha oscillations in posterior regions of the brain have been found to correlate with working memory load in non-linguistic tasks (Jensen et al., 2002), and the present study extends these findings to working memory load caused by syntactic center embeddings. Moreover, this work finds that frequency effects in naturally-occurring stimuli do not significantly contribute to neural oscillations in any frequency band, which suggests that many modeling claims could be tested on this sort of data even without controlling for frequency effects.

Unsupervised Solution Post Identification from Discussion Forums

Discussion forums have evolved into a dependablesource of knowledge to solvecommon problems. However, only a minorityof the posts in discussion forumsare solution posts. Identifying solutionposts from discussion forums, hence, is animportant research problem. In this paper,we present a technique for unsupervisedsolution post identification leveraginga so far unexplored textual feature, thatof lexical correlations between problemsand solutions. We use translation modelsand language models to exploit lexicalcorrelations and solution post characterrespectively. Our technique is designedto not rely much on structural featuressuch as post metadata since suchfeatures are often not uniformly availableacross forums. Our clustering-based iterativesolution identification approach basedon the EM-formulation performs favorablyin an empirical evaluation, beatingthe only unsupervised solution identificationtechnique from literature by a verylarge margin. We also show that our unsupervisedtechnique is competitive againstmethods that require supervision, outperformingone such technique comfortably.

Detecting Adverse Events in Clinical Trial Free Text

Thesis (Master's)--University of Washington, 2013

Text Summarization by Sentence Extraction and Syntactic Pruning

Nous présentons une méthode hybride pour le résumé de texte, en combinant l'extraction de phrases et l'élagage syntaxique des phrases extraites. L'élagage syntaxique est effectué sur la base d’une analyse complète des phrases selon un parseur de dépendances, analyse réalisée par la grammaire développée au sein d'un logiciel commercial de correction grammaticale, le Correcteur 101. Des sous-arbres de l'analyse syntaxique sont supprimés quand ils sont identifiés par les relations ciblées. L'analyse est réalisée sur un corpus de divers textes. Le taux de réduction des phrases extraites est d’en moyenne environ 74%, tout en conservant la grammaticalité ou la lisibilité dans une proportion de plus de 64%. Étant donné ces premiers résultats sur un ensemble limité de relations syntaxiques, cela laisse entrevoir des possibilités pour une application de résumé automatique de texte.

A Document Browsing Tool Based on Book Indexes

This research project is a contribution to the global field of information retrieval, specifically, to develop tools to enable information access in digital documents. We recognize the need to provide the user with flexible access to the contents of large, potentially complex digital documents, with means other than a search function or a handful of metadata elements. The goal is to produce a text browsing tool offering a maximum of information based on a fairly superficial linguistic analysis. We are concerned with a type of extensive single-document indexing, and not indexing by a set of keywords (see Klement, 2002, for a clear distinction between the two). The desired browsing tool would not only give at a glance the main topics discussed in the document, but would also present relationships between these topics. It would also give direct access to the text (via hypertext links to specific passages). The present paper, after reviewing previous research on this and similar topics, discusses the methodology and the main characteristics of a prototype we have devised. Experimental results are presented, as well as an analysis of remaining hurdles and potential applications.

On Parallel Communicating Grammar Systems and Correctness Preserving Restarting Automata

This paper contributes to the study of Freely Rewriting Restarting Automata (FRR-automata) and Parallel Communicating Grammar Systems (PCGS), which both are useful models in computational linguistics. For PCGSs we study two complexity measures called 'generation complexity' and 'distribution complexity', and we prove that a PCGS Pi, for which the generation complexity and the distribution complexity are both bounded by constants, can be transformed into a freely rewriting restarting automaton of a very restricted form. From this characterization it follows that the language L(Pi) generated by Pi is semi-linear, that its characteristic analysis is of polynomial size, and that this analysis can be computed in polynomial time.

Bias in the Social Web

Abstract A frequent assumption in Social Media is that its open nature leads to a representative view of the world. In this talk we want to consider bias occurring in the Social Web. We will consider a case study of liquid feedback, a direct democracy platform of the German pirate party as well as models of (non-)discriminating systems. As a conclusion of this talk we stipulate the need of Social Media systems to bias their working according to social norms and to publish the bias they introduce. Speaker Biography: Prof Steffen Staab Steffen studied in Erlangen (Germany), Philadelphia (USA) and Freiburg (Germany) computer science and computational linguistics. Afterwards he worked as researcher at Uni. Stuttgart/Fraunhofer and Univ. Karlsruhe, before he became professor in Koblenz (Germany). Since March 2015 he also holds a chair for Web and Computer Science at Univ. of Southampton sharing his time between here and Koblenz. In his research career he has managed to avoid almost all good advice that he now gives to his team members. Such advise includes focusing on research (vs. company) or concentrating on only one or two research areas (vs. considering ontologies, semantic web, social web, data engineering, text mining, peer-to-peer, multimedia, HCI, services, software modelling and programming and some more). Though, actually, improving how we understand and use text and data is a good common denominator for a lot of Steffen's professional activities.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.