In this paper, we present a novel approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. Specifically, we take a CFG authored to generate dialogue for our target application, a videogame, and train a long short-term memory (LSTM) recurrent neural network (RNN) to translate the surface utterances tha...

Grammatical constraints impose diverse requirements on the relations between words and phrases in a sentence. Research on the online implementation of grammatical constraints reveals a strikingly uneven profile. The parser shows impressive accuracy in the application of some rather complex constraints, but makes many errors in the implementation of some relatively simple constraints. Just as th...

This paper presents a deterministic dependency parser based on memory-based learning, which parses English text in linear time. When trained and evaluated on the Wall Street Journal section of the Penn Treebank, the parser achieves a maximum attachment score of 87.1%. Unlike most previous systems, the parser produces labeled dependency graphs, using as arc labels a combination of bracket labels...

Morphological analysis is concerned with retrieving the syntactic and morphological properties or the meaning of a morphologically complex word. Morphological analysis retrieves the grammatical features and properties of an inflected word. However, this paper introduces the design and implementation of a Morphological Analyzer for Kokborok, a resource constrained and less computerized Indian la...

The notion of a “thematic role” has been an important one in linguistic theories concerning the syntax/semantics interface (Fillmore, 1968), but their effects on high-level cognition remain relatively unexplored. Thematic roles,like AGENT and PATIENT, are said to be linked with specific grammatical positions like that of “subject” and “direct object”. Here we ask if the link between grammatical...

We automatically classify verbs into lexical semantic classes, based on distributions of indicators of verb alternations, extracted from a very large annotated corpus. We address a problem which is particularly di cult because the verb classes, although semantically di erent, show similar surface syntactic behavior. Five grammatical features are su cient to reduce error rate by more than 50% ov...

We have recently made significant changes to the BBN DELPHI syntactic and semantic analysis component. These goal of these changes was to maintain the fight coupling between syntax and semantics characteristic of earlier versions of DELPHI, while making it possible for the system to provide useful semantic interpretations of input for which complete syntactic analysis is impossible. Semantic in...

Recent analyses have revealed that child-directed speech contains distributional regularities that could, in principle, support young children's discovery of distinct grammatical categories (noun, verb, adjective). In particular, a distributional unit known as the frequent frame appears to be especially informative (Mintz, 2003). However, analyses have focused almost exclusively on the distribu...