Question Answering (QA) evaluation potentially provides a way to evaluate systems that attempt to understand texts automatically. Although current QA technologies are still unable to answer complex questions that require deep inference, we believe QA evaluation techniques must be adapted to drive QA research in the direction of deeper understanding of texts. In this paper we propose such evolut...

The problem of finding an energy conserving norm for the solution of the hyperbolic system of partial differential equations du/dt = Adu/dx, subject to boundary conditions, is reduced to the problem of characterizing those matrices appearing in the boundary conditions which satisfy two specific matrix equations. Necessary and sufficient conditions on the coefficient matrix A and the matrices ap...

social interaction requires the ability to understand people’s mental states (their intentions, desires and believes). the ability for attributing mental states is called “theory of mind.” theory of mind leads the person to explain and predict behavior. researchers showed a great interest in the relation of language and mind/language and thought. some researchers focused on methodological conce...

Machine Reading Comprehension (MRC) has become enormously popular recently and has attracted a lot of attentions. However, existing reading comprehension datasets are mostly in English. To add diversity in reading comprehension datasets, in this paper we propose a new Chinese reading comprehension dataset for accelerating related research in the community. The proposed dataset contains two diff...

Language comprehension in grounded contexts involves integrating visual and linguistic information through decisions about visual fixation. But when the visual signal also contains information about the language source – as in the case of written text or sign language – how do we decide where to look? Here, we hypothesize that eye movements during language comprehension represent an adaptive re...

Markov Logic for Machine Reading

We present a supervised learning approach to identification of anaphoric and non-anaphoric noun phrases and show how such information can be incorporated into a coreference resolution system. The resulting system outperforms the best MUC-6 and MUC-7 coreference resolution systems on the corresponding MUC coreference data sets, obtaining F-measures of 66.2 and 64.0, respectively.

Our response to the questions posed to this panel is influenced by a number of beliefs (or biasesl) which we h a v e d e v e l o p e d i n t h e c o u r s e o f b u i l d i n g and a n a l y z i n ~ the operation of several natural language understanding (NLU) systems. [I, 2, 3, 12] While the emphasis of the panel i~ on parslnK, we feel that the recovery of the syntactic structure of a natural ...

In an effort to focus on tractable problems, computational natural-language-understanding systems have typically addressed language phenomena that are amenable to combinatorial approaches using static and stereotypical semantic representations. Although such approaches are adequate for much of language, they’re not easily extended to capture humans’ more creative language interpretation capacit...